Stop the war!Остановите войну!
for scientists:
default search action
Google
Google Scholar
Semantic Scholar
Internet Archive Scholar
CiteSeerX
ORCIDSearch dblp for Publications
export results for "audio-visual feature"
download as .bib file
@article{DBLP:journals/ipm/MotamediKSEBT24,
author = {Elham Motamedi and
Danial Khosh Kholgh and
Sorush Saghari and
Mehdi Elahi and
Francesco Barile and
Marko Tkalcic},
title = {Predicting movies' eudaimonic and hedonic scores: {A} machine learning
approach using metadata, audio and visual features},
journal = {Inf. Process. Manag.},
volume = {61},
number = {2},
pages = {103610},
year = {2024},
url = {https://doi.org/10.1016/j.ipm.2023.103610},
doi = {10.1016/J.IPM.2023.103610},
timestamp = {Mon, 05 Feb 2024 00:00:00 +0100},
biburl = {https://dblp.org/rec/journals/ipm/MotamediKSEBT24.bib},
bibsource = {dblp computer science bibliography, https://dblp.org}
}
@article{DBLP:journals/tomccap/BingolPFA24,
author = {G{\"{u}}lnaziye Bing{\"{o}}l and
Simone Porcu and
Alessandro Floris and
Luigi Atzori},
title = {QoE Estimation of WebRTC-based Audio-visual Conversations from Facial
and Speech Features},
journal = {{ACM} Trans. Multim. Comput. Commun. Appl.},
volume = {20},
number = {5},
pages = {130:1--130:23},
year = {2024},
url = {https://doi.org/10.1145/3638251},
doi = {10.1145/3638251},
timestamp = {Fri, 22 Mar 2024 00:00:00 +0100},
biburl = {https://dblp.org/rec/journals/tomccap/BingolPFA24.bib},
bibsource = {dblp computer science bibliography, https://dblp.org}
}
@inproceedings{DBLP:conf/mmm/TanGZ24,
author = {Sze An Peter Tan and
Guangyu Gao and
Jia Zhao},
editor = {Stevan Rudinac and
Alan Hanjalic and
Cynthia C. S. Liem and
Marcel Worring and
Bj{\"{o}}rn {\TH}{\'{o}}r J{\'{o}}nsson and
Bei Liu and
Yoko Yamakata},
title = {Audio-Visual Segmentation by Leveraging Multi-scaled Features Learning},
booktitle = {MultiMedia Modeling - 30th International Conference, {MMM} 2024, Amsterdam,
The Netherlands, January 29 - February 2, 2024, Proceedings, Part
{II}},
series = {Lecture Notes in Computer Science},
volume = {14555},
pages = {156--169},
publisher = {Springer},
year = {2024},
url = {https://doi.org/10.1007/978-3-031-53308-2\_12},
doi = {10.1007/978-3-031-53308-2\_12},
timestamp = {Sat, 16 Mar 2024 00:00:00 +0100},
biburl = {https://dblp.org/rec/conf/mmm/TanGZ24.bib},
bibsource = {dblp computer science bibliography, https://dblp.org}
}
@article{DBLP:journals/corr/abs-2401-17796,
author = {Xueyuan Chen and
Yuejiao Wang and
Xixin Wu and
Disong Wang and
Zhiyong Wu and
Xunying Liu and
Helen Meng},
title = {Exploiting Audio-Visual Features with Pretrained AV-HuBERT for Multi-Modal
Dysarthric Speech Reconstruction},
journal = {CoRR},
volume = {abs/2401.17796},
year = {2024},
url = {https://doi.org/10.48550/arXiv.2401.17796},
doi = {10.48550/ARXIV.2401.17796},
eprinttype = {arXiv},
eprint = {2401.17796},
timestamp = {Wed, 07 Feb 2024 00:00:00 +0100},
biburl = {https://dblp.org/rec/journals/corr/abs-2401-17796.bib},
bibsource = {dblp computer science bibliography, https://dblp.org}
}
@article{DBLP:journals/ijon/LiZ23,
author = {Yangke Li and
Xinman Zhang},
title = {Lip landmark-based audio-visual speech enhancement with multimodal
feature fusion network},
journal = {Neurocomputing},
volume = {549},
pages = {126432},
year = {2023},
url = {https://doi.org/10.1016/j.neucom.2023.126432},
doi = {10.1016/J.NEUCOM.2023.126432},
timestamp = {Tue, 07 May 2024 01:00:00 +0200},
biburl = {https://dblp.org/rec/journals/ijon/LiZ23.bib},
bibsource = {dblp computer science bibliography, https://dblp.org}
}
@article{DBLP:journals/jifs/ZhaoZZL23,
author = {Yiming Zhao and
Hongdong Zhao and
Xuezhi Zhang and
Weina Liu},
title = {Vehicle classification based on audio-visual feature fusion with low-quality
images and noise},
journal = {J. Intell. Fuzzy Syst.},
volume = {45},
number = {5},
pages = {8931--8944},
year = {2023},
url = {https://doi.org/10.3233/jifs-232812},
doi = {10.3233/JIFS-232812},
timestamp = {Mon, 18 Mar 2024 00:00:00 +0100},
biburl = {https://dblp.org/rec/journals/jifs/ZhaoZZL23.bib},
bibsource = {dblp computer science bibliography, https://dblp.org}
}
@article{DBLP:journals/mta/KihalH23,
author = {Marouane Kihal and
Lamia Hamza},
title = {Robust multimedia spam filtering based on visual, textual, and audio
deep features and random forest},
journal = {Multim. Tools Appl.},
volume = {82},
number = {26},
pages = {40819--40837},
year = {2023},
url = {https://doi.org/10.1007/s11042-023-15170-x},
doi = {10.1007/S11042-023-15170-X},
timestamp = {Thu, 09 Nov 2023 00:00:00 +0100},
biburl = {https://dblp.org/rec/journals/mta/KihalH23.bib},
bibsource = {dblp computer science bibliography, https://dblp.org}
}
@article{DBLP:journals/mta/MistryBK23,
author = {Yogita D. Mistry and
Gajanan K. Birajdar and
Archana M. Khodke},
title = {Time-frequency visual representation and texture features for audio
applications: a comprehensive review, recent trends, and challenges},
journal = {Multim. Tools Appl.},
volume = {82},
number = {23},
pages = {36143--36177},
year = {2023},
url = {https://doi.org/10.1007/s11042-023-14734-1},
doi = {10.1007/S11042-023-14734-1},
timestamp = {Sat, 14 Oct 2023 01:00:00 +0200},
biburl = {https://dblp.org/rec/journals/mta/MistryBK23.bib},
bibsource = {dblp computer science bibliography, https://dblp.org}
}
@article{DBLP:journals/sensors/LiFSLZ23,
author = {Guizhu Li and
Min Fu and
Mengnan Sun and
Xuefeng Liu and
Bing Zheng},
title = {A Facial Feature and Lip Movement Enhanced Audio-Visual Speech Separation
Model},
journal = {Sensors},
volume = {23},
number = {21},
pages = {8770},
year = {2023},
url = {https://doi.org/10.3390/s23218770},
doi = {10.3390/S23218770},
timestamp = {Sat, 20 Jan 2024 00:00:00 +0100},
biburl = {https://dblp.org/rec/journals/sensors/LiFSLZ23.bib},
bibsource = {dblp computer science bibliography, https://dblp.org}
}
@inproceedings{DBLP:conf/apsipa/ChungHWZSL23,
author = {Yu{-}Ching Chung and
Ji{-}Yan Han and
Bo{-}Sin Wang and
Wei{-}Zhong Zheng and
Kung{-}Yao Shen and
Ying{-}Hui Lai},
title = {An Audio-Visual Speech Enhancement System Based on 3D Image Features:
An Application in Hearing Aids},
booktitle = {Asia Pacific Signal and Information Processing Association Annual
Summit and Conference, {APSIPA} {ASC} 2023, Taipei, Taiwan, October
31 - Nov. 3, 2023},
pages = {1131--1137},
publisher = {{IEEE}},
year = {2023},
url = {https://doi.org/10.1109/APSIPAASC58517.2023.10317139},
doi = {10.1109/APSIPAASC58517.2023.10317139},
timestamp = {Sat, 02 Dec 2023 14:05:45 +0100},
biburl = {https://dblp.org/rec/conf/apsipa/ChungHWZSL23.bib},
bibsource = {dblp computer science bibliography, https://dblp.org}
}
@inproceedings{DBLP:conf/dagm/MerceaHKA23,
author = {Otniel{-}Bogdan Mercea and
Thomas Hummel and
A. Sophia Koepke and
Zeynep Akata},
editor = {Ullrich K{\"{o}}the and
Carsten Rother},
title = {Text-to-Feature Diffusion for Audio-Visual Few-Shot Learning},
booktitle = {Pattern Recognition - 45th {DAGM} German Conference, {DAGM} {GCPR}
2023, Heidelberg, Germany, September 19-22, 2023, Proceedings},
series = {Lecture Notes in Computer Science},
volume = {14264},
pages = {491--507},
publisher = {Springer},
year = {2023},
url = {https://doi.org/10.1007/978-3-031-54605-1\_32},
doi = {10.1007/978-3-031-54605-1\_32},
timestamp = {Sat, 16 Mar 2024 00:00:00 +0100},
biburl = {https://dblp.org/rec/conf/dagm/MerceaHKA23.bib},
bibsource = {dblp computer science bibliography, https://dblp.org}
}
@inproceedings{DBLP:conf/embc/SinghTKG23,
author = {Prerna Singh and
Ayush Tripathi and
Lalan Kumar and
Tapan Kumar Gandhi},
title = {Brain Connectivity Features-based Age Group Classification using Temporal
Asynchrony Audio-Visual Integration Task},
booktitle = {45th Annual International Conference of the {IEEE} Engineering in
Medicine {\&} Biology Society, {EMBC} 2023, Sydney, Australia,
July 24-27, 2023},
pages = {1--4},
publisher = {{IEEE}},
year = {2023},
url = {https://doi.org/10.1109/EMBC40787.2023.10341177},
doi = {10.1109/EMBC40787.2023.10341177},
timestamp = {Thu, 11 Jan 2024 15:01:18 +0100},
biburl = {https://dblp.org/rec/conf/embc/SinghTKG23.bib},
bibsource = {dblp computer science bibliography, https://dblp.org}
}
@inproceedings{DBLP:conf/eusipco/MezzaSS23,
author = {Alessandro Ilic Mezza and
Paolo Sani and
Augusto Sarti},
title = {Automatic {TV} Genre Classification Based on Visually-Conditioned
Deep Audio Features},
booktitle = {31st European Signal Processing Conference, {EUSIPCO} 2023, Helsinki,
Finland, September 4-8, 2023},
pages = {166--170},
publisher = {{IEEE}},
year = {2023},
url = {https://doi.org/10.23919/EUSIPCO58844.2023.10289723},
doi = {10.23919/EUSIPCO58844.2023.10289723},
timestamp = {Mon, 06 Nov 2023 12:35:15 +0100},
biburl = {https://dblp.org/rec/conf/eusipco/MezzaSS23.bib},
bibsource = {dblp computer science bibliography, https://dblp.org}
}
@inproceedings{DBLP:conf/hci/SetoA23,
author = {Kazuki Seto and
Yumi Asahi},
editor = {Hirohiko Mori and
Yumi Asahi},
title = {Sound Logo to Increase {TV} Advertising Effectiveness Based on Audio-Visual
Features},
booktitle = {Human Interface and the Management of Information - Thematic Area,
{HIMI} 2023, Held as Part of the 25th {HCI} International Conference,
{HCII} 2023, Copenhagen, Denmark, July 23-28, 2023, Proceedings, Part
{I}},
series = {Lecture Notes in Computer Science},
volume = {14015},
pages = {136--151},
publisher = {Springer},
year = {2023},
url = {https://doi.org/10.1007/978-3-031-35132-7\_10},
doi = {10.1007/978-3-031-35132-7\_10},
timestamp = {Thu, 13 Jul 2023 10:09:58 +0200},
biburl = {https://dblp.org/rec/conf/hci/SetoA23.bib},
bibsource = {dblp computer science bibliography, https://dblp.org}
}
@inproceedings{DBLP:conf/icassp/ChenZZSZL23,
author = {Hongbo Chen and
Dongchen Zhu and
Guanghui Zhang and
Wenjun Shi and
Xiaolin Zhang and
Jiamao Li},
title = {{CM-CS:} Cross-Modal Common-Specific Feature Learning For Audio-Visual
Video Parsing},
booktitle = {{IEEE} International Conference on Acoustics, Speech and Signal Processing
{ICASSP} 2023, Rhodes Island, Greece, June 4-10, 2023},
pages = {1--5},
publisher = {{IEEE}},
year = {2023},
url = {https://doi.org/10.1109/ICASSP49357.2023.10097072},
doi = {10.1109/ICASSP49357.2023.10097072},
timestamp = {Sun, 05 Nov 2023 16:51:21 +0100},
biburl = {https://dblp.org/rec/conf/icassp/ChenZZSZL23.bib},
bibsource = {dblp computer science bibliography, https://dblp.org}
}
@inproceedings{DBLP:conf/icassp/JiangCDWL23,
author = {Ya Jiang and
Hang Chen and
Jun Du and
Qing Wang and
Chin{-}Hui Lee},
title = {Incorporating Lip Features into Audio-Visual Multi-Speaker {DOA} Estimation
by Gated Fusion},
booktitle = {{IEEE} International Conference on Acoustics, Speech and Signal Processing
{ICASSP} 2023, Rhodes Island, Greece, June 4-10, 2023},
pages = {1--5},
publisher = {{IEEE}},
year = {2023},
url = {https://doi.org/10.1109/ICASSP49357.2023.10095549},
doi = {10.1109/ICASSP49357.2023.10095549},
timestamp = {Sun, 05 Nov 2023 00:00:00 +0100},
biburl = {https://dblp.org/rec/conf/icassp/JiangCDWL23.bib},
bibsource = {dblp computer science bibliography, https://dblp.org}
}
@inproceedings{DBLP:conf/icassp/XuWZYWGFD23,
author = {Haitao Xu and
Liangfa Wei and
Jie Zhang and
Jianming Yang and
Yannan Wang and
Tian Gao and
Xin Fang and
Li{-}Rong Dai},
title = {A Multi-Scale Feature Aggregation Based Lightweight Network for Audio-Visual
Speech Enhancement},
booktitle = {{IEEE} International Conference on Acoustics, Speech and Signal Processing
{ICASSP} 2023, Rhodes Island, Greece, June 4-10, 2023},
pages = {1--5},
publisher = {{IEEE}},
year = {2023},
url = {https://doi.org/10.1109/ICASSP49357.2023.10096565},
doi = {10.1109/ICASSP49357.2023.10096565},
timestamp = {Tue, 23 Apr 2024 01:00:00 +0200},
biburl = {https://dblp.org/rec/conf/icassp/XuWZYWGFD23.bib},
bibsource = {dblp computer science bibliography, https://dblp.org}
}
@inproceedings{DBLP:conf/icmi/LiLLZTZZ23,
author = {Sunan Li and
Hailun Lian and
Cheng Lu and
Yan Zhao and
Chuangao Tang and
Yuan Zong and
Wenming Zheng},
editor = {Elisabeth Andr{\'{e}} and
Mohamed Chetouani and
Dominique Vaufreydaz and
Gale M. Lucas and
Tanja Schultz and
Louis{-}Philippe Morency and
Alessandro Vinciarelli},
title = {Audio-Visual Group-based Emotion Recognition using Local and Global
Feature Aggregation based Multi-Task Learning},
booktitle = {Proceedings of the 25th International Conference on Multimodal Interaction,
{ICMI} 2023, Paris, France, October 9-13, 2023},
pages = {741--745},
publisher = {{ACM}},
year = {2023},
url = {https://doi.org/10.1145/3577190.3616544},
doi = {10.1145/3577190.3616544},
timestamp = {Mon, 05 Feb 2024 20:29:19 +0100},
biburl = {https://dblp.org/rec/conf/icmi/LiLLZTZZ23.bib},
bibsource = {dblp computer science bibliography, https://dblp.org}
}
@inproceedings{DBLP:conf/micad/BhattacharyaP23,
author = {Moinak Bhattacharya and
Prateek Prasanna},
editor = {Khan M. Iftekharuddin and
Weijie Chen},
title = {Audio-visual feature fusion for improved thoracic disease classification},
booktitle = {Medical Imaging 2023: Computer-Aided Diagnosis, San Diego, CA, USA,
February 19-23, 2023},
series = {{SPIE} Proceedings},
volume = {12465},
publisher = {{SPIE}},
year = {2023},
url = {https://doi.org/10.1117/12.2654571},
doi = {10.1117/12.2654571},
timestamp = {Tue, 19 Mar 2024 12:50:04 +0100},
biburl = {https://dblp.org/rec/conf/micad/BhattacharyaP23.bib},
bibsource = {dblp computer science bibliography, https://dblp.org}
}
@inproceedings{DBLP:conf/smc/WangYGLW23,
author = {Jinxin Wang and
Chao Yang and
Zhongwen Guo and
Xiaomei Li and
Weigang Wang},
title = {An End-to-End Mandarin Audio-Visual Speech Recognition Model with
a Feature Enhancement Module},
booktitle = {{IEEE} International Conference on Systems, Man, and Cybernetics,
{SMC} 2023, Honolulu, Oahu, HI, USA, October 1-4, 2023},
pages = {572--577},
publisher = {{IEEE}},
year = {2023},
url = {https://doi.org/10.1109/SMC53992.2023.10394108},
doi = {10.1109/SMC53992.2023.10394108},
timestamp = {Sun, 03 Mar 2024 00:00:00 +0100},
biburl = {https://dblp.org/rec/conf/smc/WangYGLW23.bib},
bibsource = {dblp computer science bibliography, https://dblp.org}
}
@inproceedings{DBLP:conf/specom/NandakishorP23,
author = {Salam Nandakishor and
Debadatta Pati},
editor = {Alexey Karpov and
K. Samudravijaya and
K. T. Deepak and
Rajesh M. Hegde and
Shyam S. Agrawal and
S. R. Mahadeva Prasanna},
title = {Improvement of Audio-Visual Keyword Spotting System Accuracy Using
Excitation Source Feature},
booktitle = {Speech and Computer - 25th International Conference, {SPECOM} 2023,
Dharwad, India, November 29 - December 2, 2023, Proceedings, Part
{II}},
series = {Lecture Notes in Computer Science},
volume = {14339},
pages = {344--356},
publisher = {Springer},
year = {2023},
url = {https://doi.org/10.1007/978-3-031-48312-7\_28},
doi = {10.1007/978-3-031-48312-7\_28},
timestamp = {Tue, 07 May 2024 01:00:00 +0200},
biburl = {https://dblp.org/rec/conf/specom/NandakishorP23.bib},
bibsource = {dblp computer science bibliography, https://dblp.org}
}
@article{DBLP:journals/corr/abs-2304-06315,
author = {Prerna Singh and
Ayush Tripathi and
Lalan Kumar and
Tapan Kumar Gandhi},
title = {Brain Connectivity Features-based Age Group Classification using Temporal
Asynchrony Audio-Visual Integration Task},
journal = {CoRR},
volume = {abs/2304.06315},
year = {2023},
url = {https://doi.org/10.48550/arXiv.2304.06315},
doi = {10.48550/ARXIV.2304.06315},
eprinttype = {arXiv},
eprint = {2304.06315},
timestamp = {Thu, 20 Apr 2023 01:00:00 +0200},
biburl = {https://dblp.org/rec/journals/corr/abs-2304-06315.bib},
bibsource = {dblp computer science bibliography, https://dblp.org}
}
@article{DBLP:journals/corr/abs-2307-04760,
author = {Sagnik Majumder and
Ziad Al{-}Halah and
Kristen Grauman},
title = {Learning Spatial Features from Audio-Visual Correspondence in Egocentric
Videos},
journal = {CoRR},
volume = {abs/2307.04760},
year = {2023},
url = {https://doi.org/10.48550/arXiv.2307.04760},
doi = {10.48550/ARXIV.2307.04760},
eprinttype = {arXiv},
eprint = {2307.04760},
timestamp = {Mon, 24 Jul 2023 01:00:00 +0200},
biburl = {https://dblp.org/rec/journals/corr/abs-2307-04760.bib},
bibsource = {dblp computer science bibliography, https://dblp.org}
}
@article{DBLP:journals/corr/abs-2309-03869,
author = {Otniel{-}Bogdan Mercea and
Thomas Hummel and
A. Sophia Koepke and
Zeynep Akata},
title = {Text-to-feature diffusion for audio-visual few-shot learning},
journal = {CoRR},
volume = {abs/2309.03869},
year = {2023},
url = {https://doi.org/10.48550/arXiv.2309.03869},
doi = {10.48550/ARXIV.2309.03869},
eprinttype = {arXiv},
eprint = {2309.03869},
timestamp = {Tue, 12 Sep 2023 01:00:00 +0200},
biburl = {https://dblp.org/rec/journals/corr/abs-2309-03869.bib},
bibsource = {dblp computer science bibliography, https://dblp.org}
}
@article{DBLP:journals/corr/abs-2309-08030,
author = {Ju{-}Chieh Chou and
Chung{-}Ming Chien and
Karen Livescu},
title = {AV2Wav: Diffusion-Based Re-synthesis from Continuous Self-supervised
Features for Audio-Visual Speech Enhancement},
journal = {CoRR},
volume = {abs/2309.08030},
year = {2023},
url = {https://doi.org/10.48550/arXiv.2309.08030},
doi = {10.48550/ARXIV.2309.08030},
eprinttype = {arXiv},
eprint = {2309.08030},
timestamp = {Tue, 26 Sep 2023 01:00:00 +0200},
biburl = {https://dblp.org/rec/journals/corr/abs-2309-08030.bib},
bibsource = {dblp computer science bibliography, https://dblp.org}
}
@article{DBLP:journals/corr/abs-2310-03456,
author = {Edward Fish and
Jon Weinbren and
Andrew Gilbert},
title = {Multi-Resolution Audio-Visual Feature Fusion for Temporal Action Localization},
journal = {CoRR},
volume = {abs/2310.03456},
year = {2023},
url = {https://doi.org/10.48550/arXiv.2310.03456},
doi = {10.48550/ARXIV.2310.03456},
eprinttype = {arXiv},
eprint = {2310.03456},
timestamp = {Thu, 19 Oct 2023 01:00:00 +0200},
biburl = {https://dblp.org/rec/journals/corr/abs-2310-03456.bib},
bibsource = {dblp computer science bibliography, https://dblp.org}
}
@article{DBLP:journals/corr/abs-2310-03827,
author = {Sneha Muppalla and
Shan Jia and
Siwei Lyu},
title = {Integrating Audio-Visual Features for Multimodal Deepfake Detection},
journal = {CoRR},
volume = {abs/2310.03827},
year = {2023},
url = {https://doi.org/10.48550/arXiv.2310.03827},
doi = {10.48550/ARXIV.2310.03827},
eprinttype = {arXiv},
eprint = {2310.03827},
timestamp = {Thu, 19 Oct 2023 01:00:00 +0200},
biburl = {https://dblp.org/rec/journals/corr/abs-2310-03827.bib},
bibsource = {dblp computer science bibliography, https://dblp.org}
}
@article{DBLP:journals/vi/WangSWMZL22,
author = {Lei Wang and
Guodao Sun and
Yunchao Wang and
Ji Ma and
Xiaomin Zhao and
Ronghua Liang},
title = {AFExplorer: Visual analysis and interactive selection of audio features},
journal = {Vis. Informatics},
volume = {6},
number = {1},
pages = {47--55},
year = {2022},
url = {https://doi.org/10.1016/j.visinf.2022.02.003},
doi = {10.1016/J.VISINF.2022.02.003},
timestamp = {Thu, 02 Jun 2022 01:00:00 +0200},
biburl = {https://dblp.org/rec/journals/vi/WangSWMZL22.bib},
bibsource = {dblp computer science bibliography, https://dblp.org}
}
@inproceedings{DBLP:conf/ialp/LuDLZZSWY22,
author = {Shangjun Lu and
Xiaoxia Du and
Juan Liu and
Yu{-}Mei Zhang and
Shaofeng Zhao and
Rongfeng Su and
Lan Wang and
Nan Yan},
editor = {Rong Tong and
Yanfeng Lu and
Minghui Dong and
Wengao Gong and
Haizhou Li},
title = {A New Method for Predicting Severity Level of Dysarthric Speech Based
on Joint Feature-Sample Selection using Audio-Visual Data},
booktitle = {International Conference on Asian Language Processing, {IALP} 2022,
Singapore, October 27-28, 2022},
pages = {190--195},
publisher = {{IEEE}},
year = {2022},
url = {https://doi.org/10.1109/IALP57159.2022.9961300},
doi = {10.1109/IALP57159.2022.9961300},
timestamp = {Fri, 09 Dec 2022 16:21:50 +0100},
biburl = {https://dblp.org/rec/conf/ialp/LuDLZZSWY22.bib},
bibsource = {dblp computer science bibliography, https://dblp.org}
}
@inproceedings{DBLP:conf/interspeech/HongKYR22,
author = {Joanna Hong and
Minsu Kim and
Daehun Yoo and
Yong Man Ro},
editor = {Hanseok Ko and
John H. L. Hansen},
title = {Visual Context-driven Audio Feature Enhancement for Robust End-to-End
Audio-Visual Speech Recognition},
booktitle = {Interspeech 2022, 23rd Annual Conference of the International Speech
Communication Association, Incheon, Korea, 18-22 September 2022},
pages = {2838--2842},
publisher = {{ISCA}},
year = {2022},
url = {https://doi.org/10.21437/Interspeech.2022-11311},
doi = {10.21437/INTERSPEECH.2022-11311},
timestamp = {Wed, 21 Jun 2023 01:00:00 +0200},
biburl = {https://dblp.org/rec/conf/interspeech/HongKYR22.bib},
bibsource = {dblp computer science bibliography, https://dblp.org}
}
@inproceedings{DBLP:conf/interspeech/WeiHYLD22,
author = {Jie Wei and
Guanyu Hu and
Xinyu Yang and
Anh Tuan Luu and
Yizhuo Dong},
editor = {Hanseok Ko and
John H. L. Hansen},
title = {Audio-Visual Domain Adaptation Feature Fusion for Speech Emotion Recognition},
booktitle = {Interspeech 2022, 23rd Annual Conference of the International Speech
Communication Association, Incheon, Korea, 18-22 September 2022},
pages = {1988--1992},
publisher = {{ISCA}},
year = {2022},
url = {https://doi.org/10.21437/Interspeech.2022-703},
doi = {10.21437/INTERSPEECH.2022-703},
timestamp = {Wed, 21 Jun 2023 01:00:00 +0200},
biburl = {https://dblp.org/rec/conf/interspeech/WeiHYLD22.bib},
bibsource = {dblp computer science bibliography, https://dblp.org}
}
@inproceedings{DBLP:conf/mwscas/FanarasTAM22,
author = {Konstantinos Fanaras and
Antonios Tragoudaras and
Charalampos Antoniadis and
Yehia Massoud},
title = {Audio-visual Speaker Diarization: Improved Voice Activity Detection
with {CNN} based Feature Extraction},
booktitle = {65th {IEEE} International Midwest Symposium on Circuits and Systems,
{MWSCAS} 2022, Fukuoka, Japan, August 7-10, 2022},
pages = {1--4},
publisher = {{IEEE}},
year = {2022},
url = {https://doi.org/10.1109/MWSCAS54063.2022.9859533},
doi = {10.1109/MWSCAS54063.2022.9859533},
timestamp = {Mon, 01 May 2023 01:00:00 +0200},
biburl = {https://dblp.org/rec/conf/mwscas/FanarasTAM22.bib},
bibsource = {dblp computer science bibliography, https://dblp.org}
}
@inproceedings{DBLP:conf/sdf/GeeromsAKKVM22,
author = {Warre Geeroms and
Gianni Allebosch and
Stijn Kindt and
Loubna Kadri and
Peter Veelaert and
Nilesh Madhu},
title = {Audio-Visual Active Speaker Identification: {A} comparison of dense
image-based features and sparse facial landmark-based features},
booktitle = {Sensor Data Fusion: Trends, Solutions, Applications, {SDF} 2022, Bonn,
Germany, October 12-14, 2022},
pages = {1--6},
publisher = {{IEEE}},
year = {2022},
url = {https://doi.org/10.1109/SDF55338.2022.9931697},
doi = {10.1109/SDF55338.2022.9931697},
timestamp = {Fri, 18 Nov 2022 20:51:17 +0100},
biburl = {https://dblp.org/rec/conf/sdf/GeeromsAKKVM22.bib},
bibsource = {dblp computer science bibliography, https://dblp.org}
}
@article{DBLP:journals/corr/abs-2203-02655,
author = {Junwen Xiong and
Peng Zhang and
Lei Xie and
Wei Huang and
Yufei Zha and
Yanning Zhang},
title = {Audio-visual speech separation based on joint feature representation
with cross-modal attention},
journal = {CoRR},
volume = {abs/2203.02655},
year = {2022},
url = {https://doi.org/10.48550/arXiv.2203.02655},
doi = {10.48550/ARXIV.2203.02655},
eprinttype = {arXiv},
eprint = {2203.02655},
timestamp = {Fri, 10 Mar 2023 00:00:00 +0100},
biburl = {https://dblp.org/rec/journals/corr/abs-2203-02655.bib},
bibsource = {dblp computer science bibliography, https://dblp.org}
}
@article{DBLP:journals/corr/abs-2203-15183,
author = {Jialu Li and
Mark Hasegawa{-}Johnson and
Nancy L. McElwain},
title = {Visualizations of Complex Sequences of Family-Infant Vocalizations
Using Bag-of-Audio-Words Approach Based on Wav2vec 2.0 Features},
journal = {CoRR},
volume = {abs/2203.15183},
year = {2022},
url = {https://doi.org/10.48550/arXiv.2203.15183},
doi = {10.48550/ARXIV.2203.15183},
eprinttype = {arXiv},
eprint = {2203.15183},
timestamp = {Tue, 05 Apr 2022 01:00:00 +0200},
biburl = {https://dblp.org/rec/journals/corr/abs-2203-15183.bib},
bibsource = {dblp computer science bibliography, https://dblp.org}
}
@article{DBLP:journals/corr/abs-2207-06020,
author = {Joanna Hong and
Minsu Kim and
Daehun Yoo and
Yong Man Ro},
title = {Visual Context-driven Audio Feature Enhancement for Robust End-to-End
Audio-Visual Speech Recognition},
journal = {CoRR},
volume = {abs/2207.06020},
year = {2022},
url = {https://doi.org/10.48550/arXiv.2207.06020},
doi = {10.48550/ARXIV.2207.06020},
eprinttype = {arXiv},
eprint = {2207.06020},
timestamp = {Sun, 02 Oct 2022 01:00:00 +0200},
biburl = {https://dblp.org/rec/journals/corr/abs-2207-06020.bib},
bibsource = {dblp computer science bibliography, https://dblp.org}
}
@article{DBLP:journals/access/IshikawaHS21,
author = {Reina Ishikawa and
Ryo Hachiuma and
Hideo Saito},
title = {Self-Supervised Audio-Visual Feature Learning for Single-Modal Incremental
Terrain Type Clustering},
journal = {{IEEE} Access},
volume = {9},
pages = {64346--64357},
year = {2021},
url = {https://doi.org/10.1109/ACCESS.2021.3075582},
doi = {10.1109/ACCESS.2021.3075582},
timestamp = {Sun, 16 May 2021 01:00:00 +0200},
biburl = {https://dblp.org/rec/journals/access/IshikawaHS21.bib},
bibsource = {dblp computer science bibliography, https://dblp.org}
}
@article{DBLP:journals/eetct/MehtaKK21,
author = {Pooja Mehta and
Sahil Kaswan and
Jaspreet Kaur},
title = {An Enhanced {ANN-HMM} based classification of video recordings with
the aid of audio-visual feature extraction},
journal = {{EAI} Endorsed Trans. Creative Technol.},
volume = {8},
number = {28},
pages = {e1},
year = {2021},
url = {https://doi.org/10.4108/eai.31-3-2021.169172},
doi = {10.4108/EAI.31-3-2021.169172},
timestamp = {Mon, 25 Oct 2021 01:00:00 +0200},
biburl = {https://dblp.org/rec/journals/eetct/MehtaKK21.bib},
bibsource = {dblp computer science bibliography, https://dblp.org}
}
@article{DBLP:journals/entropy/WilkesVM21,
author = {Ben Wilkes and
Igor Vatolkin and
Heinrich M{\"{u}}ller},
title = {Statistical and Visual Analysis of Audio, Text, and Image Features
for Multi-Modal Music Genre Recognition},
journal = {Entropy},
volume = {23},
number = {11},
pages = {1502},
year = {2021},
url = {https://doi.org/10.3390/e23111502},
doi = {10.3390/E23111502},
timestamp = {Wed, 15 Dec 2021 00:00:00 +0100},
biburl = {https://dblp.org/rec/journals/entropy/WilkesVM21.bib},
bibsource = {dblp computer science bibliography, https://dblp.org}
}
@article{DBLP:journals/fi/IsobeTHGN21,
author = {Shinnosuke Isobe and
Satoshi Tamura and
Satoru Hayamizu and
Yuuto Gotoh and
Masaki Nose},
title = {Multi-Angle Lipreading with Angle Classification-Based Feature Extraction
and Its Application to Audio-Visual Speech Recognition},
journal = {Future Internet},
volume = {13},
number = {7},
pages = {182},
year = {2021},
url = {https://doi.org/10.3390/fi13070182},
doi = {10.3390/FI13070182},
timestamp = {Thu, 12 Aug 2021 01:00:00 +0200},
biburl = {https://dblp.org/rec/journals/fi/IsobeTHGN21.bib},
bibsource = {dblp computer science bibliography, https://dblp.org}
}
@article{DBLP:journals/ijcini/HandaAK21,
author = {Anand Handa and
Rashi Agarwal and
Narendra Kohli},
title = {Audio-Visual Emotion Recognition System Using Multi-Modal Features},
journal = {Int. J. Cogn. Informatics Nat. Intell.},
volume = {15},
number = {4},
pages = {1--14},
year = {2021},
url = {https://doi.org/10.4018/ijcini.20211001.oa34},
doi = {10.4018/IJCINI.20211001.OA34},
timestamp = {Tue, 28 Feb 2023 00:00:00 +0100},
biburl = {https://dblp.org/rec/journals/ijcini/HandaAK21.bib},
bibsource = {dblp computer science bibliography, https://dblp.org}
}
@article{DBLP:journals/sensors/QuanMN21,
author = {Jingyu Quan and
Yoshihiro Miyake and
Takayuki Nozawa},
title = {Incorporating Interpersonal Synchronization Features for Automatic
Emotion Recognition from Visual and Audio Data during Communication},
journal = {Sensors},
volume = {21},
number = {16},
pages = {5317},
year = {2021},
url = {https://doi.org/10.3390/s21165317},
doi = {10.3390/S21165317},
timestamp = {Wed, 01 Sep 2021 01:00:00 +0200},
biburl = {https://dblp.org/rec/journals/sensors/QuanMN21.bib},
bibsource = {dblp computer science bibliography, https://dblp.org}
}
@article{DBLP:journals/sivp/DebnathR21,
author = {Saswati Debnath and
Pinki Roy},
title = {Appearance and shape-based hybrid visual feature extraction: toward
audio-visual automatic speech recognition},
journal = {Signal Image Video Process.},
volume = {15},
number = {1},
pages = {25--32},
year = {2021},
url = {https://doi.org/10.1007/s11760-020-01717-0},
doi = {10.1007/S11760-020-01717-0},
timestamp = {Thu, 14 Oct 2021 01:00:00 +0200},
biburl = {https://dblp.org/rec/journals/sivp/DebnathR21.bib},
bibsource = {dblp computer science bibliography, https://dblp.org}
}
@article{DBLP:journals/speech/FarhoudiS21,
author = {Zeinab Farhoudi and
Saeed Setayeshi},
title = {Fusion of deep learning features with mixture of brain emotional learning
for audio-visual emotion recognition},
journal = {Speech Commun.},
volume = {127},
pages = {92--103},
year = {2021},
url = {https://doi.org/10.1016/j.specom.2020.12.001},
doi = {10.1016/J.SPECOM.2020.12.001},
timestamp = {Mon, 05 Feb 2024 00:00:00 +0100},
biburl = {https://dblp.org/rec/journals/speech/FarhoudiS21.bib},
bibsource = {dblp computer science bibliography, https://dblp.org}
}
@inproceedings{DBLP:conf/cascon/ZhouGMSRY21,
author = {Jingmin Zhou and
Adam Gariba and
Vida Movahedi and
Mariah Martin Shein and
Andre Rosa and
Ruiqi Yu},
editor = {Vio Onut and
Farhana H. Zulkernine},
title = {Multi-label video categorization using visual and audio transcript
features},
booktitle = {{CASCON} '21: Proceedings of the 31st Annual International Conference
on Computer Science and Software Engineering, Toronto, Ontario, Canada,
November 22 - 25, 2021},
pages = {23--32},
publisher = {{ACM}},
year = {2021},
url = {https://dl.acm.org/doi/10.5555/3507788.3507793},
doi = {10.5555/3507788.3507793},
timestamp = {Fri, 29 Jul 2022 16:56:38 +0200},
biburl = {https://dblp.org/rec/conf/cascon/ZhouGMSRY21.bib},
bibsource = {dblp computer science bibliography, https://dblp.org}
}
@inproceedings{DBLP:conf/cis/Wang21,
author = {Yufei Wang},
title = {Efficient Audio-Visual Speaker Recognition Via Deep Multi-Modal Feature
Fusion},
booktitle = {17th International Conference on Computational Intelligence and Security
{CIS} 2021, Chengdu, China, November 19-22, 2021},
pages = {99--103},
publisher = {{IEEE}},
year = {2021},
url = {https://doi.org/10.1109/CIS54983.2021.00029},
doi = {10.1109/CIS54983.2021.00029},
timestamp = {Wed, 16 Feb 2022 17:26:48 +0100},
biburl = {https://dblp.org/rec/conf/cis/Wang21.bib},
bibsource = {dblp computer science bibliography, https://dblp.org}
}
@inproceedings{DBLP:conf/icassp/ShetuCH21,
author = {Shrishti Saha Shetu and
Soumitro Chakrabarty and
Emanu{\"{e}}l Anco Peter Habets},
title = {An Empirical Study of Visual Features for {DNN} Based Audio-Visual
Speech Enhancement in Multi-Talker Environments},
booktitle = {{IEEE} International Conference on Acoustics, Speech and Signal Processing,
{ICASSP} 2021, Toronto, ON, Canada, June 6-11, 2021},
pages = {8418--8422},
publisher = {{IEEE}},
year = {2021},
url = {https://doi.org/10.1109/ICASSP39728.2021.9414000},
doi = {10.1109/ICASSP39728.2021.9414000},
timestamp = {Fri, 09 Jul 2021 01:00:00 +0200},
biburl = {https://dblp.org/rec/conf/icassp/ShetuCH21.bib},
bibsource = {dblp computer science bibliography, https://dblp.org}
}
@inproceedings{DBLP:conf/ijcnn/ChengTQJ21,
author = {Huijie Cheng and
Yun Tie and
Lin Qi and
Cong Jin},
title = {Context-Aware Based Visual-Audio Feature Fusion for Emotion Recognition},
booktitle = {International Joint Conference on Neural Networks, {IJCNN} 2021, Shenzhen,
China, July 18-22, 2021},
pages = {1--8},
publisher = {{IEEE}},
year = {2021},
url = {https://doi.org/10.1109/IJCNN52387.2021.9533473},
doi = {10.1109/IJCNN52387.2021.9533473},
timestamp = {Thu, 17 Mar 2022 00:00:00 +0100},
biburl = {https://dblp.org/rec/conf/ijcnn/ChengTQJ21.bib},
bibsource = {dblp computer science bibliography, https://dblp.org}
}
@inproceedings{DBLP:conf/ijcnn/ZhangXSHQX21,
author = {Peng Zhang and
Jiaming Xu and
Jing Shi and
Yunzhe Hao and
Lei Qin and
Bo Xu},
title = {Audio-Visual Speech Separation with Visual Features Enhanced by Adversarial
Training},
booktitle = {International Joint Conference on Neural Networks, {IJCNN} 2021, Shenzhen,
China, July 18-22, 2021},
pages = {1--8},
publisher = {{IEEE}},
year = {2021},
url = {https://doi.org/10.1109/IJCNN52387.2021.9533660},
doi = {10.1109/IJCNN52387.2021.9533660},
timestamp = {Wed, 29 Sep 2021 01:00:00 +0200},
biburl = {https://dblp.org/rec/conf/ijcnn/ZhangXSHQX21.bib},
bibsource = {dblp computer science bibliography, https://dblp.org}
}
@inproceedings{DBLP:conf/mm/TaoPDQS021,
author = {Ruijie Tao and
Zexu Pan and
Rohan Kumar Das and
Xinyuan Qian and
Mike Zheng Shou and
Haizhou Li},
editor = {Heng Tao Shen and
Yueting Zhuang and
John R. Smith and
Yang Yang and
Pablo C{\'{e}}sar and
Florian Metze and
Balakrishnan Prabhakaran},
title = {Is Someone Speaking?: Exploring Long-term Temporal Features for Audio-visual
Active Speaker Detection},
booktitle = {{MM} '21: {ACM} Multimedia Conference, Virtual Event, China, October
20 - 24, 2021},
pages = {3927--3935},
publisher = {{ACM}},
year = {2021},
url = {https://doi.org/10.1145/3474085.3475587},
doi = {10.1145/3474085.3475587},
timestamp = {Mon, 22 Apr 2024 21:24:20 +0200},
biburl = {https://dblp.org/rec/conf/mm/TaoPDQS021.bib},
bibsource = {dblp computer science bibliography, https://dblp.org}
}
@inproceedings{DBLP:conf/visapp/HuMOM21,
author = {Feiyan Hu and
Eva Mohedano and
Noel E. O'Connor and
Kevin McGuinness},
editor = {Giovanni Maria Farinella and
Petia Radeva and
Jos{\'{e}} Braz and
Kadi Bouatouch},
title = {Temporal Bilinear Encoding Network of Audio-visual Features at Low
Sampling Rates},
booktitle = {Proceedings of the 16th International Joint Conference on Computer
Vision, Imaging and Computer Graphics Theory and Applications, {VISIGRAPP}
2021, Volume 5: VISAPP, Online Streaming, February 8-10, 2021},
pages = {637--644},
publisher = {{SCITEPRESS}},
year = {2021},
url = {https://doi.org/10.5220/0010337306370644},
doi = {10.5220/0010337306370644},
timestamp = {Tue, 06 Jun 2023 14:58:00 +0200},
biburl = {https://dblp.org/rec/conf/visapp/HuMOM21.bib},
bibsource = {dblp computer science bibliography, https://dblp.org}
}
@inproceedings{DBLP:conf/wacv/MazumderSPN21,
author = {Pratik Mazumder and
Pravendra Singh and
Kranti Kumar Parida and
Vinay P. Namboodiri},
title = {AVGZSLNet: Audio-Visual Generalized Zero-Shot Learning by Reconstructing
Label Features from Multi-Modal Embeddings},
booktitle = {{IEEE} Winter Conference on Applications of Computer Vision, {WACV}
2021, Waikoloa, HI, USA, January 3-8, 2021},
pages = {3089--3098},
publisher = {{IEEE}},
year = {2021},
url = {https://doi.org/10.1109/WACV48630.2021.00313},
doi = {10.1109/WACV48630.2021.00313},
timestamp = {Mon, 03 Jan 2022 00:00:00 +0100},
biburl = {https://dblp.org/rec/conf/wacv/MazumderSPN21.bib},
bibsource = {dblp computer science bibliography, https://dblp.org}
}
@article{DBLP:journals/corr/abs-2101-05975,
author = {Xinmeng Xu and
Dongxiang Xu and
Jie Jia and
Yang Wang and
Binbin Chen},
title = {{MFFCN:} Multi-layer Feature Fusion Convolution Network for Audio-visual
Speech Enhancement},
journal = {CoRR},
volume = {abs/2101.05975},
year = {2021},
url = {https://arxiv.org/abs/2101.05975},
eprinttype = {arXiv},
eprint = {2101.05975},
timestamp = {Fri, 20 Jan 2023 00:00:00 +0100},
biburl = {https://dblp.org/rec/journals/corr/abs-2101-05975.bib},
bibsource = {dblp computer science bibliography, https://dblp.org}
}
@article{DBLP:journals/corr/abs-2101-06268,
author = {Xinmeng Xu and
Yang Wang and
Dongxiang Xu and
Cong Zhang and
Yiyuan Peng and
Jie Jia and
Binbin Chen},
title = {Attentional Multi-layer Feature Fusion Convolution Network for Audio-visual
Speech Enhancement},
journal = {CoRR},
volume = {abs/2101.06268},
year = {2021},
url = {https://arxiv.org/abs/2101.06268},
eprinttype = {arXiv},
eprint = {2101.06268},
timestamp = {Fri, 20 Jan 2023 00:00:00 +0100},
biburl = {https://dblp.org/rec/journals/corr/abs-2101-06268.bib},
bibsource = {dblp computer science bibliography, https://dblp.org}
}
@article{DBLP:journals/corr/abs-2103-14189,
author = {Taylan K. Sen and
Gazi Naven and
Luke Gerstner and
Daryl Bagley and
Raiyan Abdul Baten and
Wasifur Rahman and
Md. Kamrul Hasan and
Kurtis Glenn Haut and
Abdullah Al Mamun and
Samiha Samrose and
Anne Solbu and
R. Eric Barnes and
Mark G. Frank and
Ehsan Hoque},
title = {{DBATES:} DataBase of Audio features, Text, and visual Expressions
in competitive debate Speeches},
journal = {CoRR},
volume = {abs/2103.14189},
year = {2021},
url = {https://arxiv.org/abs/2103.14189},
eprinttype = {arXiv},
eprint = {2103.14189},
timestamp = {Thu, 17 Nov 2022 00:00:00 +0100},
biburl = {https://dblp.org/rec/journals/corr/abs-2103-14189.bib},
bibsource = {dblp computer science bibliography, https://dblp.org}
}
@article{DBLP:journals/corr/abs-2107-06592,
author = {Ruijie Tao and
Zexu Pan and
Rohan Kumar Das and
Xinyuan Qian and
Mike Zheng Shou and
Haizhou Li},
title = {Is Someone Speaking? Exploring Long-term Temporal Features for Audio-visual
Active Speaker Detection},
journal = {CoRR},
volume = {abs/2107.06592},
year = {2021},
url = {https://arxiv.org/abs/2107.06592},
eprinttype = {arXiv},
eprint = {2107.06592},
timestamp = {Thu, 22 Jul 2021 01:00:00 +0200},
biburl = {https://dblp.org/rec/journals/corr/abs-2107-06592.bib},
bibsource = {dblp computer science bibliography, https://dblp.org}
}
@article{DBLP:journals/computers/FeradovMG20,
author = {Firgan Feradov and
Iosif Mporas and
Todor Ganchev},
title = {Evaluation of Features in Detection of Dislike Responses to Audio-Visual
Stimuli from {EEG} Signals},
journal = {Comput.},
volume = {9},
number = {2},
pages = {33},
year = {2020},
url = {https://doi.org/10.3390/computers9020033},
doi = {10.3390/COMPUTERS9020033},
timestamp = {Sat, 05 Sep 2020 01:00:00 +0200},
biburl = {https://dblp.org/rec/journals/computers/FeradovMG20.bib},
bibsource = {dblp computer science bibliography, https://dblp.org}
}
@article{DBLP:journals/ijon/HaoCLWX20,
author = {Man Hao and
Weihua Cao and
Zhentao Liu and
Min Wu and
Peng Xiao},
title = {Visual-audio emotion recognition based on multi-task and ensemble
learning with multiple features},
journal = {Neurocomputing},
volume = {391},
pages = {42--51},
year = {2020},
url = {https://doi.org/10.1016/j.neucom.2020.01.048},
doi = {10.1016/J.NEUCOM.2020.01.048},
timestamp = {Fri, 22 May 2020 01:00:00 +0200},
biburl = {https://dblp.org/rec/journals/ijon/HaoCLWX20.bib},
bibsource = {dblp computer science bibliography, https://dblp.org}
}
@article{DBLP:journals/ijon/WangWH20a,
author = {Zhan Wang and
Lizhi Wang and
Hua Huang},
title = {Joint low rank embedded multiple features learning for audio-visual
emotion recognition},
journal = {Neurocomputing},
volume = {388},
pages = {324--333},
year = {2020},
url = {https://doi.org/10.1016/j.neucom.2020.01.017},
doi = {10.1016/J.NEUCOM.2020.01.017},
timestamp = {Mon, 05 Feb 2024 00:00:00 +0100},
biburl = {https://dblp.org/rec/journals/ijon/WangWH20a.bib},
bibsource = {dblp computer science bibliography, https://dblp.org}
}
@article{DBLP:journals/npl/KhanSAT20,
author = {Abdullah Aman Khan and
Jie Shao and
Waqar Ali and
Saifullah Tumrani},
title = {Content-Aware Summarization of Broadcast Sports Videos: An Audio-Visual
Feature Extraction Approach},
journal = {Neural Process. Lett.},
volume = {52},
number = {3},
pages = {1945--1968},
year = {2020},
url = {https://doi.org/10.1007/s11063-020-10200-3},
doi = {10.1007/S11063-020-10200-3},
timestamp = {Tue, 28 Mar 2023 01:00:00 +0200},
biburl = {https://dblp.org/rec/journals/npl/KhanSAT20.bib},
bibsource = {dblp computer science bibliography, https://dblp.org}
}
@article{DBLP:journals/sensors/JamilFRUBFM20,
author = {Sonain Jamil and
Fawad and
MuhibUr Rahman and
Amin Ullah and
Salman Badnava and
Masoud Forsat and
Seyed Sajad Mirjavadi},
title = {Malicious {UAV} Detection Using Integrated Audio and Visual Features
for Public Safety Applications},
journal = {Sensors},
volume = {20},
number = {14},
pages = {3923},
year = {2020},
url = {https://doi.org/10.3390/s20143923},
doi = {10.3390/S20143923},
timestamp = {Thu, 13 Aug 2020 01:00:00 +0200},
biburl = {https://dblp.org/rec/journals/sensors/JamilFRUBFM20.bib},
bibsource = {dblp computer science bibliography, https://dblp.org}
}
@article{DBLP:journals/taslp/SuLWY20,
author = {Rongfeng Su and
Xunying Liu and
Lan Wang and
Jingzhou Yang},
title = {Cross-Domain Deep Visual Feature Generation for Mandarin Audio-Visual
Speech Recognition},
journal = {{IEEE} {ACM} Trans. Audio Speech Lang. Process.},
volume = {28},
pages = {185--197},
year = {2020},
url = {https://doi.org/10.1109/TASLP.2019.2950602},
doi = {10.1109/TASLP.2019.2950602},
timestamp = {Fri, 13 Mar 2020 00:00:00 +0100},
biburl = {https://dblp.org/rec/journals/taslp/SuLWY20.bib},
bibsource = {dblp computer science bibliography, https://dblp.org}
}
@inproceedings{DBLP:conf/fgr/HormannMKR20,
author = {Stefan H{\"{o}}rmann and
Abdul Moiz and
Martin Knoche and
Gerhard Rigoll},
title = {Attention Fusion for Audio-Visual Person Verification Using Multi-Scale
Features},
booktitle = {15th {IEEE} International Conference on Automatic Face and Gesture
Recognition, {FG} 2020, Buenos Aires, Argentina, November 16-20, 2020},
pages = {281--285},
publisher = {{IEEE}},
year = {2020},
url = {https://doi.org/10.1109/FG47880.2020.00074},
doi = {10.1109/FG47880.2020.00074},
timestamp = {Tue, 18 Jul 2023 01:00:00 +0200},
biburl = {https://dblp.org/rec/conf/fgr/HormannMKR20.bib},
bibsource = {dblp computer science bibliography, https://dblp.org}
}
@inproceedings{DBLP:conf/icip/LeeL20,
author = {Hansol Lee and
Gyemin Lee},
title = {Hierarchical Model For Long-Length Video Summarization With Adversarially
Enhanced Audio/Visual Features},
booktitle = {{IEEE} International Conference on Image Processing, {ICIP} 2020,
Abu Dhabi, United Arab Emirates, October 25-28, 2020},
pages = {723--727},
publisher = {{IEEE}},
year = {2020},
url = {https://doi.org/10.1109/ICIP40778.2020.9190636},
doi = {10.1109/ICIP40778.2020.9190636},
timestamp = {Tue, 07 May 2024 01:00:00 +0200},
biburl = {https://dblp.org/rec/conf/icip/LeeL20.bib},
bibsource = {dblp computer science bibliography, https://dblp.org}
}
@inproceedings{DBLP:conf/icip/LiuCS20,
author = {Hong Liu and
Zhengyan Chen and
Wei Shi},
title = {Robust Audio-Visual Mandarin Speech Recognition Based On Adaptive
Decision Fusion And Tone Features},
booktitle = {{IEEE} International Conference on Image Processing, {ICIP} 2020,
Abu Dhabi, United Arab Emirates, October 25-28, 2020},
pages = {1381--1385},
publisher = {{IEEE}},
year = {2020},
url = {https://doi.org/10.1109/ICIP40778.2020.9190894},
doi = {10.1109/ICIP40778.2020.9190894},
timestamp = {Wed, 08 Dec 2021 00:00:00 +0100},
biburl = {https://dblp.org/rec/conf/icip/LiuCS20.bib},
bibsource = {dblp computer science bibliography, https://dblp.org}
}
@inproceedings{DBLP:conf/icpr/IshikawaHKS20,
author = {Reina Ishikawa and
Ryo Hachiuma and
Akiyoshi Kurobe and
Hideo Saito},
title = {Single-modal Incremental Terrain Clustering from Self-Supervised Audio-Visual
Feature Learning},
booktitle = {25th International Conference on Pattern Recognition, {ICPR} 2020,
Virtual Event / Milan, Italy, January 10-15, 2021},
pages = {9399--9406},
publisher = {{IEEE}},
year = {2020},
url = {https://doi.org/10.1109/ICPR48806.2021.9412638},
doi = {10.1109/ICPR48806.2021.9412638},
timestamp = {Fri, 07 May 2021 08:42:33 +0200},
biburl = {https://dblp.org/rec/conf/icpr/IshikawaHKS20.bib},
bibsource = {dblp computer science bibliography, https://dblp.org}
}
@inproceedings{DBLP:conf/icpr/LiuXY20,
author = {Hong Liu and
Wanlu Xu and
Bing Yang},
title = {Audio-Visual Speech Recognition Using {A} Two-Step Feature Fusion
Strategy},
booktitle = {25th International Conference on Pattern Recognition, {ICPR} 2020,
Virtual Event / Milan, Italy, January 10-15, 2021},
pages = {1896--1903},
publisher = {{IEEE}},
year = {2020},
url = {https://doi.org/10.1109/ICPR48806.2021.9412454},
doi = {10.1109/ICPR48806.2021.9412454},
timestamp = {Tue, 14 Mar 2023 00:00:00 +0100},
biburl = {https://dblp.org/rec/conf/icpr/LiuXY20.bib},
bibsource = {dblp computer science bibliography, https://dblp.org}
}
@inproceedings{DBLP:conf/mapr/VoNDNDNNL020,
author = {Hung{-}Quoc Vo and
Dung{-}Minh Nguyen and
Tien Do and
Vinh{-}Tiep Nguyen and
Vu{-}Minh{-}Hieu Dang and
Nhat{-}Duy Nguyen and
Thanh Duc Ngo and
Duy{-}Dinh Le and
Shin'ichi Satoh},
title = {Searching For Desired Person Doing Desired Action based on Visual
and Audio Feature in Large Scale Video Database},
booktitle = {International Conference on Multimedia Analysis and Pattern Recognition,
{MAPR} 2020, Hanoi, Vietnam, October 8-9, 2020},
pages = {1--6},
publisher = {{IEEE}},
year = {2020},
url = {https://doi.org/10.1109/MAPR49794.2020.9237781},
doi = {10.1109/MAPR49794.2020.9237781},
timestamp = {Wed, 03 Nov 2021 16:47:39 +0100},
biburl = {https://dblp.org/rec/conf/mapr/VoNDNDNNL020.bib},
bibsource = {dblp computer science bibliography, https://dblp.org}
}
@inproceedings{DBLP:conf/mmm/GuoZYFH020,
author = {Xiaona Guo and
Wei Zhong and
Long Ye and
Li Fang and
Yan Heng and
Qin Zhang},
editor = {Yong Man Ro and
Wen{-}Huang Cheng and
Junmo Kim and
Wei{-}Ta Chu and
Peng Cui and
Jung{-}Woo Choi and
Min{-}Chun Hu and
Wesley De Neve},
title = {Global Affective Video Content Regression Based on Complementary Audio-Visual
Features},
booktitle = {MultiMedia Modeling - 26th International Conference, {MMM} 2020, Daejeon,
South Korea, January 5-8, 2020, Proceedings, Part {II}},
series = {Lecture Notes in Computer Science},
volume = {11962},
pages = {540--550},
publisher = {Springer},
year = {2020},
url = {https://doi.org/10.1007/978-3-030-37734-2\_44},
doi = {10.1007/978-3-030-37734-2\_44},
timestamp = {Mon, 09 Nov 2020 15:46:42 +0100},
biburl = {https://dblp.org/rec/conf/mmm/GuoZYFH020.bib},
bibsource = {dblp computer science bibliography, https://dblp.org}
}
@inproceedings{DBLP:conf/qomex/MartinezHF20,
author = {Helard Becerra Martinez and
Andrew Hines and
Myl{\`{e}}ne C. Q. Farias},
title = {How Deep is Your Encoder: An Analysis of Features Descriptors for
an Autoencoder-Based Audio-Visual Quality Metric},
booktitle = {Twelfth International Conference on Quality of Multimedia Experience,
QoMEX 2020, Athlone, Ireland, May 26-28, 2020},
pages = {1--6},
publisher = {{IEEE}},
year = {2020},
url = {https://doi.org/10.1109/QoMEX48832.2020.9123142},
doi = {10.1109/QOMEX48832.2020.9123142},
timestamp = {Thu, 14 Oct 2021 01:00:00 +0200},
biburl = {https://dblp.org/rec/conf/qomex/MartinezHF20.bib},
bibsource = {dblp computer science bibliography, https://dblp.org}
}
@inproceedings{DBLP:conf/visapp/ChebbiJ20,
author = {Safa Chebbi and
Sofia Ben Jebara},
editor = {Giovanni Maria Farinella and
Petia Radeva and
Jos{\'{e}} Braz},
title = {An Audio-Visual based Feature Level Fusion Approach Applied to Deception
Detection},
booktitle = {Proceedings of the 15th International Joint Conference on Computer
Vision, Imaging and Computer Graphics Theory and Applications, {VISIGRAPP}
2020, Volume 4: VISAPP, Valletta, Malta, February 27-29, 2020},
pages = {197--205},
publisher = {{SCITEPRESS}},
year = {2020},
url = {https://doi.org/10.5220/0008896201970205},
doi = {10.5220/0008896201970205},
timestamp = {Thu, 16 Apr 2020 15:04:56 +0200},
biburl = {https://dblp.org/rec/conf/visapp/ChebbiJ20.bib},
bibsource = {dblp computer science bibliography, https://dblp.org}
}
@article{DBLP:journals/corr/abs-2003-11100,
author = {Helard Becerra Martinez and
Andrew Hines and
Myl{\`{e}}ne C. Q. Farias},
title = {How deep is your encoder: an analysis of features descriptors for
an autoencoder-based audio-visual quality metric},
journal = {CoRR},
volume = {abs/2003.11100},
year = {2020},
url = {https://arxiv.org/abs/2003.11100},
eprinttype = {arXiv},
eprint = {2003.11100},
timestamp = {Wed, 01 Apr 2020 01:00:00 +0200},
biburl = {https://dblp.org/rec/journals/corr/abs-2003-11100.bib},
bibsource = {dblp computer science bibliography, https://dblp.org}
}
@article{DBLP:journals/corr/abs-2004-12031,
author = {Zakaria Aldeneh and
Anushree Prasanna Kumar and
Barry{-}John Theobald and
Erik Marchi and
Sachin Kajarekar and
Devang Naik and
Ahmed Hussen Abdelaziz},
title = {Self-supervised Learning of Visual Speech Features with Audiovisual
Speech Enhancement},
journal = {CoRR},
volume = {abs/2004.12031},
year = {2020},
url = {https://arxiv.org/abs/2004.12031},
eprinttype = {arXiv},
eprint = {2004.12031},
timestamp = {Tue, 28 Apr 2020 01:00:00 +0200},
biburl = {https://dblp.org/rec/journals/corr/abs-2004-12031.bib},
bibsource = {dblp computer science bibliography, https://dblp.org}
}
@article{DBLP:journals/corr/abs-2005-13402,
author = {Pratik Mazumder and
Pravendra Singh and
Kranti Kumar Parida and
Vinay P. Namboodiri},
title = {AVGZSLNet: Audio-Visual Generalized Zero-Shot Learning by Reconstructing
Label Features from Multi-Modal Embeddings},
journal = {CoRR},
volume = {abs/2005.13402},
year = {2020},
url = {https://arxiv.org/abs/2005.13402},
eprinttype = {arXiv},
eprint = {2005.13402},
timestamp = {Thu, 28 May 2020 01:00:00 +0200},
biburl = {https://dblp.org/rec/journals/corr/abs-2005-13402.bib},
bibsource = {dblp computer science bibliography, https://dblp.org}
}
@article{DBLP:journals/corr/abs-2011-04359,
author = {Shrishti Saha Shetu and
Soumitro Chakrabarty and
Emanu{\"{e}}l Anco Peter Habets},
title = {An Empirical Study of Visual Features for {DNN} based Audio-Visual
Speech Enhancement in Multi-talker Environments},
journal = {CoRR},
volume = {abs/2011.04359},
year = {2020},
url = {https://arxiv.org/abs/2011.04359},
eprinttype = {arXiv},
eprint = {2011.04359},
timestamp = {Thu, 12 Nov 2020 00:00:00 +0100},
biburl = {https://dblp.org/rec/journals/corr/abs-2011-04359.bib},
bibsource = {dblp computer science bibliography, https://dblp.org}
}
@article{DBLP:journals/corr/abs-2012-10283,
author = {Feiyan Hu and
Eva Mohedano and
Noel E. O'Connor and
Kevin McGuinness},
title = {Temporal Bilinear Encoding Network of Audio-Visual Features at Low
Sampling Rates},
journal = {CoRR},
volume = {abs/2012.10283},
year = {2020},
url = {https://arxiv.org/abs/2012.10283},
eprinttype = {arXiv},
eprint = {2012.10283},
timestamp = {Mon, 04 Jan 2021 00:00:00 +0100},
biburl = {https://dblp.org/rec/journals/corr/abs-2012-10283.bib},
bibsource = {dblp computer science bibliography, https://dblp.org}
}
@article{DBLP:journals/dsp/SaudiKA19,
author = {Ali S. Saudi and
Mahmoud I. Khalil and
Hazem M. Abbas},
title = {Improved features and dynamic stream weight adaption for robust Audio-Visual
Speech Recognition framework},
journal = {Digit. Signal Process.},
volume = {89},
pages = {17--29},
year = {2019},
url = {https://doi.org/10.1016/j.dsp.2019.02.016},
doi = {10.1016/J.DSP.2019.02.016},
timestamp = {Mon, 26 Jun 2023 01:00:00 +0200},
biburl = {https://dblp.org/rec/journals/dsp/SaudiKA19.bib},
bibsource = {dblp computer science bibliography, https://dblp.org}
}
@article{DBLP:journals/ieicet/NaranchimegZA19,
author = {Bold Naranchimeg and
Chao Zhang and
Takuya Akashi},
title = {Cross-Domain Deep Feature Combination for Bird Species Classification
with Audio-Visual Data},
journal = {{IEICE} Trans. Inf. Syst.},
volume = {102-D},
number = {10},
pages = {2033--2042},
year = {2019},
url = {https://doi.org/10.1587/transinf.2018EDP7383},
doi = {10.1587/TRANSINF.2018EDP7383},
timestamp = {Thu, 23 Jun 2022 01:00:00 +0200},
biburl = {https://dblp.org/rec/journals/ieicet/NaranchimegZA19.bib},
bibsource = {dblp computer science bibliography, https://dblp.org}
}
@article{DBLP:journals/iet-ipr/JavedIMMA19,
author = {Ali Javed and
Aun Irtaza and
Hafiz Malik and
Muhammad Tariq Mahmood and
Syed Muhammad Adnan Shah},
title = {Multimodal framework based on audio-visual features for summarisation
of cricket videos},
journal = {{IET} Image Process.},
volume = {13},
number = {4},
pages = {615--622},
year = {2019},
url = {https://doi.org/10.1049/iet-ipr.2018.5589},
doi = {10.1049/IET-IPR.2018.5589},
timestamp = {Tue, 21 Mar 2023 00:00:00 +0100},
biburl = {https://dblp.org/rec/journals/iet-ipr/JavedIMMA19.bib},
bibsource = {dblp computer science bibliography, https://dblp.org}
}
@article{DBLP:journals/mta/DhirajBG19,
author = {Dhiraj and
Rohit Biswas and
Nischay Ghattamaraju},
title = {An effective analysis of deep learning based approaches for audio
based feature extraction and its visualization},
journal = {Multim. Tools Appl.},
volume = {78},
number = {17},
pages = {23949--23972},
year = {2019},
url = {https://doi.org/10.1007/s11042-018-6706-x},
doi = {10.1007/S11042-018-6706-X},
timestamp = {Mon, 11 May 2020 01:00:00 +0200},
biburl = {https://dblp.org/rec/journals/mta/DhirajBG19.bib},
bibsource = {dblp computer science bibliography, https://dblp.org}
}
@inproceedings{DBLP:conf/globalsip/HaiderPAL19,
author = {Fasih Haider and
Senja Pollak and
Pierre Albert and
Saturnino Luz},
title = {Extracting Audio-Visual Features for Emotion Recognition Through Active
Feature Selection},
booktitle = {2019 {IEEE} Global Conference on Signal and Information Processing,
GlobalSIP 2019, Ottawa, ON, Canada, November 11-14, 2019},
pages = {1--5},
publisher = {{IEEE}},
year = {2019},
url = {https://doi.org/10.1109/GlobalSIP45357.2019.8969360},
doi = {10.1109/GLOBALSIP45357.2019.8969360},
timestamp = {Wed, 07 Dec 2022 00:00:00 +0100},
biburl = {https://dblp.org/rec/conf/globalsip/HaiderPAL19.bib},
bibsource = {dblp computer science bibliography, https://dblp.org}
}
@inproceedings{DBLP:conf/icassp/HoriA0WHCMCLDEB19,
author = {Chiori Hori and
Huda AlAmri and
Jue Wang and
Gordon Wichern and
Takaaki Hori and
Anoop Cherian and
Tim K. Marks and
Vincent Cartillier and
Raphael Gontijo Lopes and
Abhishek Das and
Irfan Essa and
Dhruv Batra and
Devi Parikh},
title = {End-to-end Audio Visual Scene-aware Dialog Using Multimodal Attention-based
Video Features},
booktitle = {{IEEE} International Conference on Acoustics, Speech and Signal Processing,
{ICASSP} 2019, Brighton, United Kingdom, May 12-17, 2019},
pages = {2352--2356},
publisher = {{IEEE}},
year = {2019},
url = {https://doi.org/10.1109/ICASSP.2019.8682583},
doi = {10.1109/ICASSP.2019.8682583},
timestamp = {Wed, 16 Oct 2019 14:14:52 +0200},
biburl = {https://dblp.org/rec/conf/icassp/HoriA0WHCMCLDEB19.bib},
bibsource = {dblp computer science bibliography, https://dblp.org}
}
@inproceedings{DBLP:conf/iccvw/LeeL19,
author = {Hansol Lee and
Gyemin Lee},
title = {Summarizing Long-Length Videos with GAN-Enhanced Audio/Visual Features},
booktitle = {2019 {IEEE/CVF} International Conference on Computer Vision Workshops,
{ICCV} Workshops 2019, Seoul, Korea (South), October 27-28, 2019},
pages = {3727--3731},
publisher = {{IEEE}},
year = {2019},
url = {https://doi.org/10.1109/ICCVW.2019.00462},
doi = {10.1109/ICCVW.2019.00462},
timestamp = {Tue, 07 May 2024 01:00:00 +0200},
biburl = {https://dblp.org/rec/conf/iccvw/LeeL19.bib},
bibsource = {dblp computer science bibliography, https://dblp.org}
}
@inproceedings{DBLP:conf/iftc/GuoZYF019,
author = {Xiaona Guo and
Wei Zhong and
Long Ye and
Li Fang and
Qin Zhang},
editor = {Guangtao Zhai and
Jun Zhou and
Hua Yang and
Ping An and
Xiaokang Yang},
title = {Affective Video Content Analysis Based on Two Compact Audio-Visual
Features},
booktitle = {Digital {TV} and Wireless Multimedia Communication - 16th International
Forum, {IFTC} 2019, Shanghai, China, September 19-20, 2019, Revised
Selected Papers},
series = {Communications in Computer and Information Science},
volume = {1181},
pages = {355--364},
publisher = {Springer},
year = {2019},
url = {https://doi.org/10.1007/978-981-15-3341-9\_29},
doi = {10.1007/978-981-15-3341-9\_29},
timestamp = {Wed, 11 Mar 2020 14:23:07 +0100},
biburl = {https://dblp.org/rec/conf/iftc/GuoZYF019.bib},
bibsource = {dblp computer science bibliography, https://dblp.org}
}
@inproceedings{DBLP:conf/nips/KumarOSHN19,
author = {Shachi H. Kumar and
Eda Okur and
Saurav Sahay and
Jonathan Huang and
Lama Nachman},
title = {Leveraging Topics and Audio Features with Multimodal Attention for
Audio Visual Scene-Aware Dialog},
booktitle = {Visually Grounded Interaction and Language (ViGIL), NeurIPS 2019 Workshop,
Vancouver, Canada, December 13, 2019},
year = {2019},
url = {https://vigilworkshop.github.io/static/papers/39.pdf},
timestamp = {Thu, 12 Mar 2020 00:00:00 +0100},
biburl = {https://dblp.org/rec/conf/nips/KumarOSHN19.bib},
bibsource = {dblp computer science bibliography, https://dblp.org}
}
@article{DBLP:journals/corr/abs-1912-10131,
author = {Shachi H. Kumar and
Eda Okur and
Saurav Sahay and
Jonathan Huang and
Lama Nachman},
title = {Leveraging Topics and Audio Features with Multimodal Attention for
Audio Visual Scene-Aware Dialog},
journal = {CoRR},
volume = {abs/1912.10131},
year = {2019},
url = {http://arxiv.org/abs/1912.10131},
eprinttype = {arXiv},
eprint = {1912.10131},
timestamp = {Fri, 03 Jan 2020 00:00:00 +0100},
biburl = {https://dblp.org/rec/journals/corr/abs-1912-10131.bib},
bibsource = {dblp computer science bibliography, https://dblp.org}
}
@article{DBLP:journals/corr/abs-1912-10132,
author = {Shachi H. Kumar and
Eda Okur and
Saurav Sahay and
Jonathan Huang and
Lama Nachman},
title = {Exploring Context, Attention and Audio Features for Audio Visual Scene-Aware
Dialog},
journal = {CoRR},
volume = {abs/1912.10132},
year = {2019},
url = {http://arxiv.org/abs/1912.10132},
eprinttype = {arXiv},
eprint = {1912.10132},
timestamp = {Fri, 03 Jan 2020 00:00:00 +0100},
biburl = {https://dblp.org/rec/journals/corr/abs-1912-10132.bib},
bibsource = {dblp computer science bibliography, https://dblp.org}
}
@article{DBLP:journals/dsp/RahmaniAS18,
author = {Mohammad Hasan Rahmani and
Farshad Almasganj and
Seyyed Ali Seyyedsalehi},
title = {Audio-visual feature fusion via deep neural networks for automatic
speech recognition},
journal = {Digit. Signal Process.},
volume = {82},
pages = {54--63},
year = {2018},
url = {https://doi.org/10.1016/j.dsp.2018.06.004},
doi = {10.1016/J.DSP.2018.06.004},
timestamp = {Sat, 30 Sep 2023 01:00:00 +0200},
biburl = {https://dblp.org/rec/journals/dsp/RahmaniAS18.bib},
bibsource = {dblp computer science bibliography, https://dblp.org}
}
@article{DBLP:journals/tcsv/ZhangZHGT18,
author = {Shiqing Zhang and
Shiliang Zhang and
Tiejun Huang and
Wen Gao and
Qi Tian},
title = {Learning Affective Features With a Hybrid Deep Model for Audio-Visual
Emotion Recognition},
journal = {{IEEE} Trans. Circuits Syst. Video Technol.},
volume = {28},
number = {10},
pages = {3030--3043},
year = {2018},
url = {https://doi.org/10.1109/TCSVT.2017.2719043},
doi = {10.1109/TCSVT.2017.2719043},
timestamp = {Thu, 02 Dec 2021 00:00:00 +0100},
biburl = {https://dblp.org/rec/journals/tcsv/ZhangZHGT18.bib},
bibsource = {dblp computer science bibliography, https://dblp.org}
}
@article{DBLP:journals/tmm/BeyanCBM18,
author = {Cigdem Beyan and
Francesca Capozzi and
Cristina Becchio and
Vittorio Murino},
title = {Prediction of the Leadership Style of an Emergent Leader Using Audio
and Visual Nonverbal Features},
journal = {{IEEE} Trans. Multim.},
volume = {20},
number = {2},
pages = {441--456},
year = {2018},
url = {https://doi.org/10.1109/TMM.2017.2740062},
doi = {10.1109/TMM.2017.2740062},
timestamp = {Thu, 01 Oct 2020 01:00:00 +0200},
biburl = {https://dblp.org/rec/journals/tmm/BeyanCBM18.bib},
bibsource = {dblp computer science bibliography, https://dblp.org}
}
@inproceedings{DBLP:conf/eccv/OwensE18,
author = {Andrew Owens and
Alexei A. Efros},
editor = {Vittorio Ferrari and
Martial Hebert and
Cristian Sminchisescu and
Yair Weiss},
title = {Audio-Visual Scene Analysis with Self-Supervised Multisensory Features},
booktitle = {Computer Vision - {ECCV} 2018 - 15th European Conference, Munich,
Germany, September 8-14, 2018, Proceedings, Part {VI}},
series = {Lecture Notes in Computer Science},
volume = {11210},
pages = {639--658},
publisher = {Springer},
year = {2018},
url = {https://doi.org/10.1007/978-3-030-01231-1\_39},
doi = {10.1007/978-3-030-01231-1\_39},
timestamp = {Sun, 02 Oct 2022 01:00:00 +0200},
biburl = {https://dblp.org/rec/conf/eccv/OwensE18.bib},
bibsource = {dblp computer science bibliography, https://dblp.org}
}
@inproceedings{DBLP:conf/gcce/HaruyamaTOH18,
author = {Tomoki Haruyama and
Sho Takahashi and
Takahiro Ogawa and
Miki Haseyama},
title = {Estimation of Important Scenes in Soccer Videos Based on Collaborative
Use of Audio-Visual {CNN} Features},
booktitle = {{IEEE} 7th Global Conference on Consumer Electronics, {GCCE} 2018,
Nara, Japan, October 9-12, 2018},
pages = {710--711},
publisher = {{IEEE}},
year = {2018},
url = {https://doi.org/10.1109/GCCE.2018.8574727},
doi = {10.1109/GCCE.2018.8574727},
timestamp = {Wed, 12 Jan 2022 00:00:00 +0100},
biburl = {https://dblp.org/rec/conf/gcce/HaruyamaTOH18.bib},
bibsource = {dblp computer science bibliography, https://dblp.org}
}
@inproceedings{DBLP:conf/huc/MatsudaFTAYM18,
author = {Yuki Matsuda and
Dmitrii Fedotov and
Yuta Takahashi and
Yutaka Arakawa and
Keiichi Yasumoto and
Wolfgang Minker},
title = {EmoTour: Multimodal Emotion Recognition using Physiological and Audio-Visual
Features},
booktitle = {Proceedings of the 2018 {ACM} International Joint Conference and 2018
International Symposium on Pervasive and Ubiquitous Computing and
Wearable Computers, UbiComp/ISWC 2018 Adjunct, Singapore, October
08-12, 2018},
pages = {946--951},
publisher = {{ACM}},
year = {2018},
url = {https://doi.org/10.1145/3267305.3267687},
doi = {10.1145/3267305.3267687},
timestamp = {Mon, 28 Aug 2023 21:17:48 +0200},
biburl = {https://dblp.org/rec/conf/huc/MatsudaFTAYM18.bib},
bibsource = {dblp computer science bibliography, https://dblp.org}
}
@inproceedings{DBLP:conf/icassp/AkhtarBF18,
author = {Zahid Akhtar and
Stefany Bedoya and
Tiago H. Falk},
title = {Improved Audio-Visual Laughter Detection Via Multi-Scale Multi-Resolution
Image Texture Features and Classifier Fusion},
booktitle = {2018 {IEEE} International Conference on Acoustics, Speech and Signal
Processing, {ICASSP} 2018, Calgary, AB, Canada, April 15-20, 2018},
pages = {3106--3110},
publisher = {{IEEE}},
year = {2018},
url = {https://doi.org/10.1109/ICASSP.2018.8461611},
doi = {10.1109/ICASSP.2018.8461611},
timestamp = {Tue, 21 Mar 2023 00:00:00 +0100},
biburl = {https://dblp.org/rec/conf/icassp/AkhtarBF18.bib},
bibsource = {dblp computer science bibliography, https://dblp.org}
}
@inproceedings{DBLP:conf/interspeech/SuLW18,
author = {Rongfeng Su and
Xunying Liu and
Lan Wang},
editor = {B. Yegnanarayana},
title = {Semi-supervised Cross-domain Visual Feature Learning for Audio-Visual
Broadcast Speech Transcription},
booktitle = {Interspeech 2018, 19th Annual Conference of the International Speech
Communication Association, Hyderabad, India, 2-6 September 2018},
pages = {3509--3513},
publisher = {{ISCA}},
year = {2018},
url = {https://doi.org/10.21437/Interspeech.2018-1063},
doi = {10.21437/INTERSPEECH.2018-1063},
timestamp = {Fri, 21 May 2021 08:16:43 +0200},
biburl = {https://dblp.org/rec/conf/interspeech/SuLW18.bib},
bibsource = {dblp computer science bibliography, https://dblp.org}
}
@inproceedings{DBLP:conf/interspeech/TamuraHEHT18,
author = {Satoshi Tamura and
Kento Horio and
Hajime Endo and
Satoru Hayamizu and
Tomoki Toda},
editor = {B. Yegnanarayana},
title = {Audio-visual Voice Conversion Using Deep Canonical Correlation Analysis
for Deep Bottleneck Features},
booktitle = {Interspeech 2018, 19th Annual Conference of the International Speech
Communication Association, Hyderabad, India, 2-6 September 2018},
pages = {2469--2473},
publisher = {{ISCA}},
year = {2018},
url = {https://doi.org/10.21437/Interspeech.2018-2286},
doi = {10.21437/INTERSPEECH.2018-2286},
timestamp = {Fri, 09 Apr 2021 01:00:00 +0200},
biburl = {https://dblp.org/rec/conf/interspeech/TamuraHEHT18.bib},
bibsource = {dblp computer science bibliography, https://dblp.org}
}
@inproceedings{DBLP:conf/prcv/HouWW18,
author = {Congcong Hou and
Xiaoyu Wu and
Ge Wang},
editor = {Jian{-}Huang Lai and
Cheng{-}Lin Liu and
Xilin Chen and
Jie Zhou and
Tieniu Tan and
Nanning Zheng and
Hongbin Zha},
title = {End-to-End Bloody Video Recognition by Audio-Visual Feature Fusion},
booktitle = {Pattern Recognition and Computer Vision - First Chinese Conference,
{PRCV} 2018, Guangzhou, China, November 23-26, 2018, Proceedings,
Part {I}},
series = {Lecture Notes in Computer Science},
volume = {11256},
pages = {501--510},
publisher = {Springer},
year = {2018},
url = {https://doi.org/10.1007/978-3-030-03398-9\_43},
doi = {10.1007/978-3-030-03398-9\_43},
timestamp = {Fri, 03 Dec 2021 12:20:53 +0100},
biburl = {https://dblp.org/rec/conf/prcv/HouWW18.bib},
bibsource = {dblp computer science bibliography, https://dblp.org}
}
@article{DBLP:journals/corr/abs-1804-03641,
author = {Andrew Owens and
Alexei A. Efros},
title = {Audio-Visual Scene Analysis with Self-Supervised Multisensory Features},
journal = {CoRR},
volume = {abs/1804.03641},
year = {2018},
url = {http://arxiv.org/abs/1804.03641},
eprinttype = {arXiv},
eprint = {1804.03641},
timestamp = {Mon, 13 Aug 2018 01:00:00 +0200},
biburl = {https://dblp.org/rec/journals/corr/abs-1804-03641.bib},
bibsource = {dblp computer science bibliography, https://dblp.org}
}
@article{DBLP:journals/corr/abs-1805-00625,
author = {Didan Deng and
Yuqian Zhou and
Jimin Pi and
Bertram E. Shi},
title = {Multimodal Utterance-level Affect Analysis using Visual, Audio and
Text Features},
journal = {CoRR},
volume = {abs/1805.00625},
year = {2018},
url = {http://arxiv.org/abs/1805.00625},
eprinttype = {arXiv},
eprint = {1805.00625},
timestamp = {Mon, 13 Aug 2018 01:00:00 +0200},
biburl = {https://dblp.org/rec/journals/corr/abs-1805-00625.bib},
bibsource = {dblp computer science bibliography, https://dblp.org}
}
@article{DBLP:journals/corr/abs-1806-08409,
author = {Chiori Hori and
Huda AlAmri and
Jue Wang and
Gordon Wichern and
Takaaki Hori and
Anoop Cherian and
Tim K. Marks and
Vincent Cartillier and
Raphael Gontijo Lopes and
Abhishek Das and
Irfan Essa and
Dhruv Batra and
Devi Parikh},
title = {End-to-End Audio Visual Scene-Aware Dialog using Multimodal Attention-Based
Video Features},
journal = {CoRR},
volume = {abs/1806.08409},
year = {2018},
url = {http://arxiv.org/abs/1806.08409},
eprinttype = {arXiv},
eprint = {1806.08409},
timestamp = {Thu, 31 Jan 2019 00:00:00 +0100},
biburl = {https://dblp.org/rec/journals/corr/abs-1806-08409.bib},
bibsource = {dblp computer science bibliography, https://dblp.org}
}
@article{DBLP:journals/corr/abs-1807-00612,
author = {Mehmet Ali Arabaci and
Fatih {\"{O}}zkan and
Elif S{\"{u}}rer and
Peter Jancovic and
Alptekin Temizel},
title = {Multi-modal Egocentric Activity Recognition using Audio-Visual Features},
journal = {CoRR},
volume = {abs/1807.00612},
year = {2018},
url = {http://arxiv.org/abs/1807.00612},
eprinttype = {arXiv},
eprint = {1807.00612},
timestamp = {Mon, 17 May 2021 01:00:00 +0200},
biburl = {https://dblp.org/rec/journals/corr/abs-1807-00612.bib},
bibsource = {dblp computer science bibliography, https://dblp.org}
}
@article{DBLP:journals/corr/abs-1811-10199,
author = {Bold Naranchimeg and
Chao Zhang and
Takuya Akashi},
title = {Cross-domain Deep Feature Combination for Bird Species Classification
with Audio-visual Data},
journal = {CoRR},
volume = {abs/1811.10199},
year = {2018},
url = {http://arxiv.org/abs/1811.10199},
eprinttype = {arXiv},
eprint = {1811.10199},
timestamp = {Tue, 14 Jan 2020 00:00:00 +0100},
biburl = {https://dblp.org/rec/journals/corr/abs-1811-10199.bib},
bibsource = {dblp computer science bibliography, https://dblp.org}
}
@article{DBLP:journals/corr/abs-1812-08407,
author = {Shachi H. Kumar and
Eda Okur and
Saurav Sahay and
Juan Jose Alvarado Leanos and
Jonathan Huang and
Lama Nachman},
title = {Context, Attention and Audio Feature Explorations for Audio Visual
Scene-Aware Dialog},
journal = {CoRR},
volume = {abs/1812.08407},
year = {2018},
url = {http://arxiv.org/abs/1812.08407},
eprinttype = {arXiv},
eprint = {1812.08407},
timestamp = {Wed, 02 Jan 2019 00:00:00 +0100},
biburl = {https://dblp.org/rec/journals/corr/abs-1812-08407.bib},
bibsource = {dblp computer science bibliography, https://dblp.org}
}
@article{DBLP:journals/computation/PapakostasSGSSM17,
author = {Michalis Papakostas and
Evaggelos Spyrou and
Theodoros Giannakopoulos and
Giorgos Siantikos and
Dimitrios Sgouropoulos and
Phivos Mylonas and
Fillia Makedon},
title = {Deep Visual Attributes vs. Hand-Crafted Audio Features on Multidomain
Speech Emotion Recognition},
journal = {Comput.},
volume = {5},
number = {2},
pages = {26},
year = {2017},
url = {https://doi.org/10.3390/computation5020026},
doi = {10.3390/COMPUTATION5020026},
timestamp = {Thu, 01 Oct 2020 01:00:00 +0200},
biburl = {https://dblp.org/rec/journals/computation/PapakostasSGSSM17.bib},
bibsource = {dblp computer science bibliography, https://dblp.org}
}
@article{DBLP:journals/jrm/NakadaiK17,
author = {Kazuhiro Nakadai and
Tomoaki Koiwa},
title = {Psychologically-Inspired Audio-Visual Speech Recognition Using Coarse
Speech Recognition and Missing Feature Theory},
journal = {J. Robotics Mechatronics},
volume = {29},
number = {1},
pages = {105--113},
year = {2017},
url = {https://doi.org/10.20965/jrm.2017.p0105},
doi = {10.20965/JRM.2017.P0105},
timestamp = {Wed, 01 Apr 2020 01:00:00 +0200},
biburl = {https://dblp.org/rec/journals/jrm/NakadaiK17.bib},
bibsource = {dblp computer science bibliography, https://dblp.org}
}
@article{DBLP:journals/mta/GharavianBS17,
author = {Davood Gharavian and
Mahdi Bejani and
Mansour Sheikhan},
title = {Audio-visual emotion recognition using {FCBF} feature selection method
and particle swarm optimization for fuzzy {ARTMAP} neural networks},
journal = {Multim. Tools Appl.},
volume = {76},
number = {2},
pages = {2331--2352},
year = {2017},
url = {https://doi.org/10.1007/s11042-015-3180-6},
doi = {10.1007/S11042-015-3180-6},
timestamp = {Mon, 26 Oct 2020 00:00:00 +0100},
biburl = {https://dblp.org/rec/journals/mta/GharavianBS17.bib},
bibsource = {dblp computer science bibliography, https://dblp.org}
}
@article{DBLP:journals/prl/NanniCLSB17,
author = {Loris Nanni and
Yandre M. G. Costa and
Diego Rafael Lucio and
Carlos Nascimento Silla Jr. and
Sheryl Brahnam},
title = {Combining visual and acoustic features for audio classification tasks},
journal = {Pattern Recognit. Lett.},
volume = {88},
pages = {49--56},
year = {2017},
url = {https://doi.org/10.1016/j.patrec.2017.01.013},
doi = {10.1016/J.PATREC.2017.01.013},
timestamp = {Sat, 22 Feb 2020 00:00:00 +0100},
biburl = {https://dblp.org/rec/journals/prl/NanniCLSB17.bib},
bibsource = {dblp computer science bibliography, https://dblp.org}
}
@article{DBLP:journals/speech/SuiTB17,
author = {Chao Sui and
Roberto Togneri and
Mohammed Bennamoun},
title = {A cascade gray-stereo visual feature extraction method for visual
and audio-visual speech recognition},
journal = {Speech Commun.},
volume = {90},
pages = {26--38},
year = {2017},
url = {https://doi.org/10.1016/j.specom.2017.01.005},
doi = {10.1016/J.SPECOM.2017.01.005},
timestamp = {Sat, 22 Feb 2020 00:00:00 +0100},
biburl = {https://dblp.org/rec/journals/speech/SuiTB17.bib},
bibsource = {dblp computer science bibliography, https://dblp.org}
}
@inproceedings{DBLP:conf/ccbr/LiuLFZD17,
author = {Yu{-}Hang Liu and
Xin Liu and
Wentao Fan and
Bineng Zhong and
Ji{-}Xiang Du},
editor = {Jie Zhou and
Yunhong Wang and
Zhenan Sun and
Yong Xu and
Linlin Shen and
Jianjiang Feng and
Shiguang Shan and
Yu Qiao and
Zhenhua Guo and
Shiqi Yu},
title = {Efficient Audio-Visual Speaker Recognition via Deep Heterogeneous
Feature Fusion},
booktitle = {Biometric Recognition - 12th Chinese Conference, {CCBR} 2017, Shenzhen,
China, October 28-29, 2017, Proceedings},
series = {Lecture Notes in Computer Science},
volume = {10568},
pages = {575--583},
publisher = {Springer},
year = {2017},
url = {https://doi.org/10.1007/978-3-319-69923-3\_62},
doi = {10.1007/978-3-319-69923-3\_62},
timestamp = {Tue, 04 Oct 2022 18:09:04 +0200},
biburl = {https://dblp.org/rec/conf/ccbr/LiuLFZD17.bib},
bibsource = {dblp computer science bibliography, https://dblp.org}
}
@inproceedings{DBLP:conf/ciss/MendatWRNA17,
author = {Daniel R. Mendat and
James E. West and
Sudarshan Ramenahalli and
Ernst Niebur and
Andreas G. Andreou},
title = {Audio-Visual beamforming with the Eigenmike microphone array an omni-camera
and cognitive auditory features},
booktitle = {51st Annual Conference on Information Sciences and Systems, {CISS}
2017, Baltimore, MD, USA, March 22-24, 2017},
pages = {1--4},
publisher = {{IEEE}},
year = {2017},
url = {https://doi.org/10.1109/CISS.2017.7926180},
doi = {10.1109/CISS.2017.7926180},
timestamp = {Sun, 25 Jul 2021 01:00:00 +0200},
biburl = {https://dblp.org/rec/conf/ciss/MendatWRNA17.bib},
bibsource = {dblp computer science bibliography, https://dblp.org}
}
@inproceedings{DBLP:conf/vcip/BokshiTBH17,
author = {Mangona Bokshi and
Fei Tao and
Carlos Busso and
John H. L. Hansen},
title = {Assessment and classification of singing quality based on audio-visual
features},
booktitle = {2017 {IEEE} Visual Communications and Image Processing, {VCIP} 2017,
St. Petersburg, FL, USA, December 10-13, 2017},
pages = {1--4},
publisher = {{IEEE}},
year = {2017},
url = {https://doi.org/10.1109/VCIP.2017.8305078},
doi = {10.1109/VCIP.2017.8305078},
timestamp = {Thu, 14 Oct 2021 01:00:00 +0200},
biburl = {https://dblp.org/rec/conf/vcip/BokshiTBH17.bib},
bibsource = {dblp computer science bibliography, https://dblp.org}
}
@article{DBLP:journals/ijst/BiswasSC16,
author = {Astik Biswas and
Prakash Kumar Sahu and
Mahesh Chandra},
title = {Multiple cameras audio visual speech recognition using active appearance
model visual features in car environment},
journal = {Int. J. Speech Technol.},
volume = {19},
number = {1},
pages = {159--171},
year = {2016},
url = {https://doi.org/10.1007/s10772-016-9332-x},
doi = {10.1007/S10772-016-9332-X},
timestamp = {Mon, 26 Oct 2020 00:00:00 +0100},
biburl = {https://dblp.org/rec/journals/ijst/BiswasSC16.bib},
bibsource = {dblp computer science bibliography, https://dblp.org}
}
@inproceedings{DBLP:conf/eccv/SubramaniamPMBM16,
author = {Arulkumar Subramaniam and
Vismay Patel and
Ashish Mishra and
Prashanth Balasubramanian and
Anurag Mittal},
editor = {Gang Hua and
Herv{\'{e}} J{\'{e}}gou},
title = {Bi-modal First Impressions Recognition Using Temporally Ordered Deep
Audio and Stochastic Visual Features},
booktitle = {Computer Vision - {ECCV} 2016 Workshops - Amsterdam, The Netherlands,
October 8-10 and 15-16, 2016, Proceedings, Part {III}},
series = {Lecture Notes in Computer Science},
volume = {9915},
pages = {337--348},
year = {2016},
url = {https://doi.org/10.1007/978-3-319-49409-8\_27},
doi = {10.1007/978-3-319-49409-8\_27},
timestamp = {Sun, 02 Jun 2019 21:17:49 +0200},
biburl = {https://dblp.org/rec/conf/eccv/SubramaniamPMBM16.bib},
bibsource = {dblp computer science bibliography, https://dblp.org}
}
@inproceedings{DBLP:conf/icwsm/PereiraPPBD16,
author = {Mois{\'{e}}s Henrique Ramos Pereira and
Fl{\'{a}}vio Luis Cardeal P{\'{a}}dua and
Adriano C{\'{e}}sar Machado Pereira and
Fabr{\'{\i}}cio Benevenuto and
Daniel Hasan Dalip},
title = {Fusing Audio, Textual, and Visual Features for Sentiment Analysis
of News Videos},
booktitle = {Proceedings of the Tenth International Conference on Web and Social
Media, Cologne, Germany, May 17-20, 2016},
pages = {659--662},
publisher = {{AAAI} Press},
year = {2016},
url = {http://www.aaai.org/ocs/index.php/ICWSM/ICWSM16/paper/view/13144},
timestamp = {Fri, 05 Feb 2021 11:07:46 +0100},
biburl = {https://dblp.org/rec/conf/icwsm/PereiraPPBD16.bib},
bibsource = {dblp computer science bibliography, https://dblp.org}
}
@inproceedings{DBLP:conf/interspeech/Heckmann16,
author = {Martin Heckmann},
editor = {Nelson Morgan},
title = {Feature-Level Decision Fusion for Audio-Visual Word Prominence Detection},
booktitle = {Interspeech 2016, 17th Annual Conference of the International Speech
Communication Association, San Francisco, CA, USA, September 8-12,
2016},
pages = {575--579},
publisher = {{ISCA}},
year = {2016},
url = {https://doi.org/10.21437/Interspeech.2016-163},
doi = {10.21437/INTERSPEECH.2016-163},
timestamp = {Mon, 26 Jun 2023 16:43:56 +0200},
biburl = {https://dblp.org/rec/conf/interspeech/Heckmann16.bib},
bibsource = {dblp computer science bibliography, https://dblp.org}
}
@inproceedings{DBLP:conf/interspeech/TakashimaATAMON16,
author = {Yuki Takashima and
Ryo Aihara and
Tetsuya Takiguchi and
Yasuo Ariki and
Nobuyuki Mitani and
Kiyohiro Omori and
Kaoru Nakazono},
editor = {Nelson Morgan},
title = {Audio-Visual Speech Recognition Using Bimodal-Trained Bottleneck Features
for a Person with Severe Hearing Loss},
booktitle = {Interspeech 2016, 17th Annual Conference of the International Speech
Communication Association, San Francisco, CA, USA, September 8-12,
2016},
pages = {277--281},
publisher = {{ISCA}},
year = {2016},
url = {https://doi.org/10.21437/Interspeech.2016-721},
doi = {10.21437/INTERSPEECH.2016-721},
timestamp = {Fri, 29 Jan 2021 00:00:00 +0100},
biburl = {https://dblp.org/rec/conf/interspeech/TakashimaATAMON16.bib},
bibsource = {dblp computer science bibliography, https://dblp.org}
}
@inproceedings{DBLP:conf/mldm/MuhammadD16,
author = {Atta Muhammad and
Sher Muhammad Daudpota},
editor = {Petra Perner},
title = {Content Based Identification of Talk Show Videos Using Audio Visual
Features},
booktitle = {Machine Learning and Data Mining in Pattern Recognition - 12th International
Conference, {MLDM} 2016, New York, NY, USA, July 16-21, 2016, Proceedings},
series = {Lecture Notes in Computer Science},
volume = {9729},
pages = {267--283},
publisher = {Springer},
year = {2016},
url = {https://doi.org/10.1007/978-3-319-41920-6\_20},
doi = {10.1007/978-3-319-41920-6\_20},
timestamp = {Wed, 07 Dec 2022 00:00:00 +0100},
biburl = {https://dblp.org/rec/conf/mldm/MuhammadD16.bib},
bibsource = {dblp computer science bibliography, https://dblp.org}
}
@inproceedings{DBLP:conf/sccc/LucioMC16,
author = {Diego Rafael Lucio and
Yandre Maldonado e Gomes da Costa},
editor = {Claudio Cubillos and
Hern{\'{a}}n Astudillo},
title = {Bird species classification using visual and acoustic features extracted
from audio signal},
booktitle = {35th International Conference of the Chilean Computer Science Society,
{SCCC} 2016, Valpara{\'{\i}}so, Chile, October 10-14, 2016},
pages = {1--12},
publisher = {{IEEE}},
year = {2016},
url = {https://doi.org/10.1109/SCCC.2016.7836063},
doi = {10.1109/SCCC.2016.7836063},
timestamp = {Wed, 16 Oct 2019 14:14:56 +0200},
biburl = {https://dblp.org/rec/conf/sccc/LucioMC16.bib},
bibsource = {dblp computer science bibliography, https://dblp.org}
}
@inproceedings{DBLP:conf/sigcse/DokeP16,
author = {Abhay Doke and
Niranjan Pedanekar},
editor = {Carl Alphonce and
Jodi L. Tims and
Michael E. Caspersen and
Stephen H. Edwards},
title = {Lights, Camera, but No Action: Exploring Affective Audio-Visual Features
of Educational Videos (Abstract Only)},
booktitle = {Proceedings of the 47th {ACM} Technical Symposium on Computing Science
Education, {SIGCSE} 2016, Memphis, TN, USA, March 02 - 05, 2016},
pages = {686},
publisher = {{ACM}},
year = {2016},
url = {https://doi.org/10.1145/2839509.2850535},
doi = {10.1145/2839509.2850535},
timestamp = {Mon, 13 Dec 2021 09:32:31 +0100},
biburl = {https://dblp.org/rec/conf/sigcse/DokeP16.bib},
bibsource = {dblp computer science bibliography, https://dblp.org}
}
@inproceedings{DBLP:conf/tsp/PalecekC16,
author = {Karel Palecek and
Josef Chaloupka},
title = {Depth-based features in audio-visual speech recognition},
booktitle = {39th International Conference on Telecommunications and Signal Processing,
{TSP} 2016, Vienna, Austria, June 27-29, 2016},
pages = {303--306},
publisher = {{IEEE}},
year = {2016},
url = {https://doi.org/10.1109/TSP.2016.7760884},
doi = {10.1109/TSP.2016.7760884},
timestamp = {Mon, 05 Feb 2024 00:00:00 +0100},
biburl = {https://dblp.org/rec/conf/tsp/PalecekC16.bib},
bibsource = {dblp computer science bibliography, https://dblp.org}
}
@article{DBLP:journals/corr/PereiraPPBD16,
author = {Mois{\'{e}}s H. R. Pereira and
Fl{\'{a}}vio L. C. P{\'{a}}dua and
Adriano C. M. Pereira and
Fabr{\'{\i}}cio Benevenuto and
Daniel Hasan Dalip},
title = {Fusing Audio, Textual and Visual Features for Sentiment Analysis of
News Videos},
journal = {CoRR},
volume = {abs/1604.02612},
year = {2016},
url = {http://arxiv.org/abs/1604.02612},
eprinttype = {arXiv},
eprint = {1604.02612},
timestamp = {Mon, 12 Aug 2019 01:00:00 +0200},
biburl = {https://dblp.org/rec/journals/corr/PereiraPPBD16.bib},
bibsource = {dblp computer science bibliography, https://dblp.org}
}
@article{DBLP:journals/corr/SubramaniamPMBM16,
author = {Arulkumar Subramaniam and
Vismay Patel and
Ashish Mishra and
Prashanth Balasubramanian and
Anurag Mittal},
title = {Bi-modal First Impressions Recognition using Temporally Ordered Deep
Audio and Stochastic Visual Features},
journal = {CoRR},
volume = {abs/1610.10048},
year = {2016},
url = {http://arxiv.org/abs/1610.10048},
eprinttype = {arXiv},
eprint = {1610.10048},
timestamp = {Mon, 13 Aug 2018 01:00:00 +0200},
biburl = {https://dblp.org/rec/journals/corr/SubramaniamPMBM16.bib},
bibsource = {dblp computer science bibliography, https://dblp.org}
}
@article{DBLP:journals/ijst/BordeVMY15,
author = {Prashant L. Borde and
Amarsinh Varpe and
Ramesh R. Manza and
Pravin L. Yannawar},
title = {Recognition of isolated words using Zernike and {MFCC} features for
audio visual speech recognition},
journal = {Int. J. Speech Technol.},
volume = {18},
number = {2},
pages = {167--175},
year = {2015},
url = {https://doi.org/10.1007/s10772-014-9257-1},
doi = {10.1007/S10772-014-9257-1},
timestamp = {Mon, 08 Jun 2020 01:00:00 +0200},
biburl = {https://dblp.org/rec/journals/ijst/BordeVMY15.bib},
bibsource = {dblp computer science bibliography, https://dblp.org}
}
@article{DBLP:journals/taffco/HanJH0L15,
author = {Junwei Han and
Xiang Ji and
Xintao Hu and
Lei Guo and
Tianming Liu},
title = {Arousal Recognition Using Audio-Visual Features and FMRI-Based Brain
Response},
journal = {{IEEE} Trans. Affect. Comput.},
volume = {6},
number = {4},
pages = {337--347},
year = {2015},
url = {https://doi.org/10.1109/TAFFC.2015.2411280},
doi = {10.1109/TAFFC.2015.2411280},
timestamp = {Mon, 19 Feb 2024 00:00:00 +0100},
biburl = {https://dblp.org/rec/journals/taffco/HanJH0L15.bib},
bibsource = {dblp computer science bibliography, https://dblp.org}
}
@inproceedings{DBLP:conf/apsipa/TamuraNKOITH15,
author = {Satoshi Tamura and
Hiroshi Ninomiya and
Norihide Kitaoka and
Shin Osuga and
Yurie Iribe and
Kazuya Takeda and
Satoru Hayamizu},
title = {Audio-visual speech recognition using deep bottleneck features and
high-performance lipreading},
booktitle = {Asia-Pacific Signal and Information Processing Association Annual
Summit and Conference, {APSIPA} 2015, Hong Kong, December 16-19, 2015},
pages = {575--582},
publisher = {{IEEE}},
year = {2015},
url = {https://doi.org/10.1109/APSIPA.2015.7415335},
doi = {10.1109/APSIPA.2015.7415335},
timestamp = {Wed, 16 Oct 2019 14:14:55 +0200},
biburl = {https://dblp.org/rec/conf/apsipa/TamuraNKOITH15.bib},
bibsource = {dblp computer science bibliography, https://dblp.org}
}
@inproceedings{DBLP:conf/caip/CastroMG15,
author = {Francisco M. Castro and
Manuel J. Mar{\'{\i}}n{-}Jim{\'{e}}nez and
Nicol{\'{a}}s Guil},
editor = {George Azzopardi and
Nicolai Petkov},
title = {Empirical Study of Audio-Visual Features Fusion for Gait Recognition},
booktitle = {Computer Analysis of Images and Patterns - 16th International Conference,
{CAIP} 2015, Valletta, Malta, September 2-4, 2015 Proceedings, Part
{I}},
series = {Lecture Notes in Computer Science},
volume = {9256},
pages = {727--739},
publisher = {Springer},
year = {2015},
url = {https://doi.org/10.1007/978-3-319-23192-1\_61},
doi = {10.1007/978-3-319-23192-1\_61},
timestamp = {Tue, 14 May 2019 10:00:53 +0200},
biburl = {https://dblp.org/rec/conf/caip/CastroMG15.bib},
bibsource = {dblp computer science bibliography, https://dblp.org}
}
@inproceedings{DBLP:conf/cores/ForczmanskiM15,
author = {Pawel Forczmanski and
Tomasz Maka},
editor = {Robert Burduk and
Konrad Jackowski and
Marek Kurzynski and
Michal Wozniak and
Andrzej Zolnierek},
title = {Investigating Combinations of Visual Audio Features and Distance Metrics
in the Problem of Audio Classification},
booktitle = {Proceedings of the 9th International Conference on Computer Recognition
Systems {CORES} 2015, Wroclaw, Poland, 25-27 May 2015},
series = {Advances in Intelligent Systems and Computing},
volume = {403},
pages = {733--744},
publisher = {Springer},
year = {2015},
url = {https://doi.org/10.1007/978-3-319-26227-7\_69},
doi = {10.1007/978-3-319-26227-7\_69},
timestamp = {Sat, 09 Apr 2022 01:00:00 +0200},
biburl = {https://dblp.org/rec/conf/cores/ForczmanskiM15.bib},
bibsource = {dblp computer science bibliography, https://dblp.org}
}
@inproceedings{DBLP:conf/ecir/SchindlerR15,
author = {Alexander Schindler and
Andreas Rauber},
editor = {Allan Hanbury and
Gabriella Kazai and
Andreas Rauber and
Norbert Fuhr},
title = {An Audio-Visual Approach to Music Genre Classification through Affective
Color Features},
booktitle = {Advances in Information Retrieval - 37th European Conference on {IR}
Research, {ECIR} 2015, Vienna, Austria, March 29 - April 2, 2015.
Proceedings},
series = {Lecture Notes in Computer Science},
volume = {9022},
pages = {61--67},
year = {2015},
url = {https://doi.org/10.1007/978-3-319-16354-3\_8},
doi = {10.1007/978-3-319-16354-3\_8},
timestamp = {Tue, 14 May 2019 10:00:37 +0200},
biburl = {https://dblp.org/rec/conf/ecir/SchindlerR15.bib},
bibsource = {dblp computer science bibliography, https://dblp.org}
}
@inproceedings{DBLP:conf/icdsp/TahirCMDDMT15,
author = {Yasir Tahir and
Debsubhra Chakraborty and
Tomasz Maszczyk and
Shoko Dauwels and
Justin Dauwels and
Nadia Magnenat{-}Thalmann and
Daniel Thalmann},
title = {Real-time sociometrics from audio-visual features for two-person dialogs},
booktitle = {2015 {IEEE} International Conference on Digital Signal Processing,
{DSP} 2015, Singapore, July 21-24, 2015},
pages = {823--827},
publisher = {{IEEE}},
year = {2015},
url = {https://doi.org/10.1109/ICDSP.2015.7251991},
doi = {10.1109/ICDSP.2015.7251991},
timestamp = {Sun, 02 Oct 2022 01:00:00 +0200},
biburl = {https://dblp.org/rec/conf/icdsp/TahirCMDDMT15.bib},
bibsource = {dblp computer science bibliography, https://dblp.org}
}
@inproceedings{DBLP:conf/icinco/SidorovSIM15,
author = {Maxim Sidorov and
Evgenii Sopov and
Ilia Ivanov and
Wolfgang Minker},
editor = {Joaquim Filipe and
Kurosh Madani and
Oleg Yu. Gusikhin and
Jurek Z. Sasiadek},
title = {Feature and Decision Level Audio-visual Data Fusion in Emotion Recognition
Problem},
booktitle = {{ICINCO} 2015 - Proceedings of the 12th International Conference on
Informatics in Control, Automation and Robotics, Volume 2, Colmar,
Alsace, France, 21-23 July, 2015},
pages = {246--251},
publisher = {SciTePress},
year = {2015},
url = {https://doi.org/10.5220/0005527002460251},
doi = {10.5220/0005527002460251},
timestamp = {Mon, 09 Aug 2021 17:01:45 +0200},
biburl = {https://dblp.org/rec/conf/icinco/SidorovSIM15.bib},
bibsource = {dblp computer science bibliography, https://dblp.org}
}
@inproceedings{DBLP:conf/interspeech/CornuM15,
author = {Thomas Le Cornu and
Ben Milner},
title = {Reconstructing intelligible audio speech from visual speech features},
booktitle = {{INTERSPEECH} 2015, 16th Annual Conference of the International Speech
Communication Association, Dresden, Germany, September 6-10, 2015},
pages = {3355--3359},
publisher = {{ISCA}},
year = {2015},
url = {https://doi.org/10.21437/Interspeech.2015-139},
doi = {10.21437/INTERSPEECH.2015-139},
timestamp = {Fri, 23 Jun 2023 01:00:00 +0200},
biburl = {https://dblp.org/rec/conf/interspeech/CornuM15.bib},
bibsource = {dblp computer science bibliography, https://dblp.org}
}
@inproceedings{DBLP:conf/interspeech/NinomiyaKTIT15,
author = {Hiroshi Ninomiya and
Norihide Kitaoka and
Satoshi Tamura and
Yurie Iribe and
Kazuya Takeda},
title = {Integration of deep bottleneck features for audio-visual speech recognition},
booktitle = {{INTERSPEECH} 2015, 16th Annual Conference of the International Speech
Communication Association, Dresden, Germany, September 6-10, 2015},
pages = {563--567},
publisher = {{ISCA}},
year = {2015},
url = {https://doi.org/10.21437/Interspeech.2015-204},
doi = {10.21437/INTERSPEECH.2015-204},
timestamp = {Fri, 23 Jun 2023 01:00:00 +0200},
biburl = {https://dblp.org/rec/conf/interspeech/NinomiyaKTIT15.bib},
bibsource = {dblp computer science bibliography, https://dblp.org}
}
@inproceedings{DBLP:conf/mediaeval/NishiIS15,
author = {Fumito Nishi and
Nakamasa Inoue and
Koichi Shinoda},
editor = {Martha A. Larson and
Bogdan Ionescu and
Mats Sj{\"{o}}berg and
Xavier Anguera and
Johann Poignant and
Michael Riegler and
Maria Eskevich and
Claudia Hauff and
Richard F. E. Sutcliffe and
Gareth J. F. Jones and
Yi{-}Hsuan Yang and
Mohammad Soleymani and
Symeon Papadopoulos},
title = {Combining Audio Features and Visual I-Vector @ MediaEval 2015 Multimodal
Person Discovery in Broadcast {TV}},
booktitle = {Working Notes Proceedings of the MediaEval 2015 Workshop, Wurzen,
Germany, September 14-15, 2015},
series = {{CEUR} Workshop Proceedings},
volume = {1436},
publisher = {CEUR-WS.org},
year = {2015},
url = {https://ceur-ws.org/Vol-1436/Paper39.pdf},
timestamp = {Fri, 10 Mar 2023 16:22:12 +0100},
biburl = {https://dblp.org/rec/conf/mediaeval/NishiIS15.bib},
bibsource = {dblp computer science bibliography, https://dblp.org}
}
@inproceedings{DBLP:conf/retis/BiswasSBC15,
author = {Astik Biswas and
Prakash Kumar Sahu and
Anirban Bhowmick and
Mahesh Chandra},
title = {VidTIMIT audio visual phoneme recognition using {AAM} visual features
and human auditory motivated acoustic wavelet features},
booktitle = {2nd {IEEE} International Conference on Recent Trends in Information
Systems, ReTIS 2015, Kolkata, India, July 9-11, 2015},
pages = {428--433},
publisher = {{IEEE}},
year = {2015},
url = {https://doi.org/10.1109/ReTIS.2015.7232917},
doi = {10.1109/RETIS.2015.7232917},
timestamp = {Sun, 25 Oct 2020 01:00:00 +0200},
biburl = {https://dblp.org/rec/conf/retis/BiswasSBC15.bib},
bibsource = {dblp computer science bibliography, https://dblp.org}
}
@article{DBLP:journals/acisc/IslamS14,
author = {Md. Rabiul Islam and
Md. Abdus Sobhan},
title = {Feature Fusion Based Audio-Visual Speaker Identification Using Hidden
Markov Model under Different Lighting Variations},
journal = {Appl. Comput. Intell. Soft Comput.},
volume = {2014},
pages = {831830:1--831830:7},
year = {2014},
url = {https://doi.org/10.1155/2014/831830},
doi = {10.1155/2014/831830},
timestamp = {Wed, 22 Jul 2020 01:00:00 +0200},
biburl = {https://dblp.org/rec/journals/acisc/IslamS14.bib},
bibsource = {dblp computer science bibliography, https://dblp.org}
}
@article{DBLP:journals/fgcs/LiuYXT14,
author = {Yizhi Liu and
Ying Yang and
Hongtao Xie and
Sheng Tang},
title = {Fusing audio vocabulary with visual features for pornographic video
detection},
journal = {Future Gener. Comput. Syst.},
volume = {31},
pages = {69--76},
year = {2014},
url = {https://doi.org/10.1016/j.future.2012.08.012},
doi = {10.1016/J.FUTURE.2012.08.012},
timestamp = {Wed, 19 Feb 2020 00:00:00 +0100},
biburl = {https://dblp.org/rec/journals/fgcs/LiuYXT14.bib},
bibsource = {dblp computer science bibliography, https://dblp.org}
}
@article{DBLP:journals/isci/Rinaldi14,
author = {Antonio M. Rinaldi},
title = {A multimedia ontology model based on linguistic properties and audio-visual
features},
journal = {Inf. Sci.},
volume = {277},
pages = {234--246},
year = {2014},
url = {https://doi.org/10.1016/j.ins.2014.02.017},
doi = {10.1016/J.INS.2014.02.017},
timestamp = {Tue, 06 Jun 2017 01:00:00 +0200},
biburl = {https://dblp.org/rec/journals/isci/Rinaldi14.bib},
bibsource = {dblp computer science bibliography, https://dblp.org}
}
@inproceedings{DBLP:conf/cse/LiXLZB14,
author = {Chen Li and
Yuxiang Xie and
Xidao Luan and
Kaichao Zhang and
Liang Bai},
editor = {Xingang Liu and
Didier El Baz and
Ching{-}Hsien Hsu and
Kai Kang and
Weifeng Chen},
title = {Automatic Movie Summarization Based on the Visual-Audio Features},
booktitle = {17th {IEEE} International Conference on Computational Science and
Engineering, {CSE} 2014, Chengdu, China, December 19-21, 2014},
pages = {1758--1761},
publisher = {{IEEE} Computer Society},
year = {2014},
url = {https://doi.org/10.1109/CSE.2014.322},
doi = {10.1109/CSE.2014.322},
timestamp = {Fri, 24 Mar 2023 00:00:00 +0100},
biburl = {https://dblp.org/rec/conf/cse/LiXLZB14.bib},
bibsource = {dblp computer science bibliography, https://dblp.org}
}
@inproceedings{DBLP:conf/euvip/MilaniCTTA14,
author = {Simone Milani and
Luca Cuccovillo and
Marco Tagliasacchi and
Stefano Tubaro and
Patrick Aichroth},
title = {Video camera identification using audio-visual features},
booktitle = {5th European Workshop on Visual Information Processing, {EUVIP} 2014,
Villetaneuse, Paris, France, December 10-12, 2014},
pages = {1--6},
publisher = {{IEEE}},
year = {2014},
url = {https://doi.org/10.1109/EUVIP.2014.7018382},
doi = {10.1109/EUVIP.2014.7018382},
timestamp = {Sun, 02 Oct 2022 01:00:00 +0200},
biburl = {https://dblp.org/rec/conf/euvip/MilaniCTTA14.bib},
bibsource = {dblp computer science bibliography, https://dblp.org}
}
@inproceedings{DBLP:conf/icassp/SawadaTTH14,
author = {Kohei Sawada and
Masanori Takehara and
Satoshi Tamura and
Satoru Hayamizu},
title = {Audio-visual voice conversion using noise-robust features},
booktitle = {{IEEE} International Conference on Acoustics, Speech and Signal Processing,
{ICASSP} 2014, Florence, Italy, May 4-9, 2014},
pages = {7899--7903},
publisher = {{IEEE}},
year = {2014},
url = {https://doi.org/10.1109/ICASSP.2014.6855138},
doi = {10.1109/ICASSP.2014.6855138},
timestamp = {Wed, 16 Oct 2019 14:14:52 +0200},
biburl = {https://dblp.org/rec/conf/icassp/SawadaTTH14.bib},
bibsource = {dblp computer science bibliography, https://dblp.org}
}
@inproceedings{DBLP:conf/icpram/KacheleGZMS14,
author = {Markus K{\"{a}}chele and
Michael Glodek and
Dimitri Zharkov and
Sascha Meudt and
Friedhelm Schwenker},
editor = {Maria De Marsico and
Antoine Tabbone and
Ana L. N. Fred},
title = {Fusion of Audio-visual Features using Hierarchical Classifier Systems
for the Recognition of Affective States and the State of Depression},
booktitle = {{ICPRAM} 2014 - Proceedings of the 3rd International Conference on
Pattern Recognition Applications and Methods, ESEO, Angers, Loire
Valley, France, 6-8 March, 2014},
pages = {671--678},
publisher = {SciTePress},
year = {2014},
url = {https://doi.org/10.5220/0004828606710678},
doi = {10.5220/0004828606710678},
timestamp = {Tue, 23 May 2017 01:00:00 +0200},
biburl = {https://dblp.org/rec/conf/icpram/KacheleGZMS14.bib},
bibsource = {dblp computer science bibliography, https://dblp.org}
}
@inproceedings{DBLP:conf/intcompsymp/ZengC14,
author = {Yi{-}Chong Zeng and
Wen{-}Tsung Chang},
editor = {William Cheng{-}Chung Chu and
Han{-}Chieh Chao and
Stephen Jenn{-}Hwa Yang},
title = {Fast Seriation of Multiple Homogeneous-content Videos Using Audio-visual
Features},
booktitle = {Intelligent Systems and Applications - Proceedings of the International
Computer Symposium {(ICS)} held at Taichung, Taiwan, December 12-14,
2014},
series = {Frontiers in Artificial Intelligence and Applications},
volume = {274},
pages = {1157--1166},
publisher = {{IOS} Press},
year = {2014},
url = {https://doi.org/10.3233/978-1-61499-484-8-1157},
doi = {10.3233/978-1-61499-484-8-1157},
timestamp = {Sun, 21 May 2017 01:00:00 +0200},
biburl = {https://dblp.org/rec/conf/intcompsymp/ZengC14.bib},
bibsource = {dblp computer science bibliography, https://dblp.org}
}
@inproceedings{DBLP:conf/interspeech/Fernandez-Martinez14,
author = {Fernando Fern{\'{a}}ndez Mart{\'{\i}}nez and
Alejandro Hern{\'{a}}ndez{-}Garc{\'{\i}}a and
Ascensi{\'{o}}n Gallardo{-}Antol{\'{\i}}n and
Fernando D{\'{\i}}az{-}de{-}Mar{\'{\i}}a},
title = {Combining audio-visual features for viewers' perception classification
of Youtube car commercials},
booktitle = {2nd International Workshop on Speech, Language and Audio in Multimedia,
{SLAM} 2014, Penang, Malaysia, September 11-12, 2014},
pages = {14--18},
publisher = {{ISCA}},
year = {2014},
url = {http://www.isca-speech.org/archive/slam\_2014/slm4\_014.html},
timestamp = {Tue, 11 Jul 2023 11:45:03 +0200},
biburl = {https://dblp.org/rec/conf/interspeech/Fernandez-Martinez14.bib},
bibsource = {dblp computer science bibliography, https://dblp.org}
}
@inproceedings{DBLP:conf/isccsp/IbrahimM14,
author = {Mohd Zamri Ibrahim and
David J. Mulvaney},
title = {A lip geometry approach for feature-fusion based audio-visual speech
recognition},
booktitle = {6th International Symposium on Communications, Control and Signal
Processing, {ISCCSP} 2014, Athens, Greece, May 21-23, 2014},
pages = {644--647},
publisher = {{IEEE}},
year = {2014},
url = {https://doi.org/10.1109/ISCCSP.2014.6877957},
doi = {10.1109/ISCCSP.2014.6877957},
timestamp = {Sun, 17 Sep 2023 01:00:00 +0200},
biburl = {https://dblp.org/rec/conf/isccsp/IbrahimM14.bib},
bibsource = {dblp computer science bibliography, https://dblp.org}
}
@inproceedings{DBLP:conf/mm/EspinosaEPMAR14,
author = {Humberto P{\'{e}}rez Espinosa and
Hugo Jair Escalante and
Luis Villase{\~{n}}or Pineda and
Manuel Montes{-}y{-}G{\'{o}}mez and
David Pinto Avenda{\~{n}}o and
Ver{\'{o}}nica Reyes{-}Meza},
editor = {Michel F. Valstar and
Bj{\"{o}}rn W. Schuller and
Jarek Krajewski and
Roddy Cowie and
Maja Pantic},
title = {Fusing Affective Dimensions and Audio-Visual Features from Segmented
Video for Depression Recognition: INAOE-BUAP's Participation at AVEC'14
Challenge},
booktitle = {Proceedings of the 4th International Workshop on Audio/Visual Emotion
Challenge, {AVEC} '14, Orlando, Florida, USA, November 7, 2014},
pages = {49--55},
publisher = {{ACM}},
year = {2014},
url = {https://doi.org/10.1145/2661806.2661815},
doi = {10.1145/2661806.2661815},
timestamp = {Sat, 09 Apr 2022 01:00:00 +0200},
biburl = {https://dblp.org/rec/conf/mm/EspinosaEPMAR14.bib},
bibsource = {dblp computer science bibliography, https://dblp.org}
}
@inproceedings{DBLP:conf/nime/Tsiros14,
author = {Augoustinos Tsiros},
editor = {Baptiste Caramiaux and
Koray Tahiroglu and
Rebecca Fiebrink and
Atau Tanaka},
title = {Evaluating the Perceived Similarity Between Audio-Visual Features
Using Corpus-Based Concatenative Synthesis},
booktitle = {14th International Conference on New Interfaces for Musical Expression,
{NIME} 2014, London, United Kingdom, June 30 - July 4, 2014},
pages = {421--426},
publisher = {nime.org},
year = {2014},
url = {https://doi.org/10.5281/zenodo.1178965},
doi = {10.5281/ZENODO.1178965},
timestamp = {Tue, 04 Apr 2023 16:52:05 +0200},
biburl = {https://dblp.org/rec/conf/nime/Tsiros14.bib},
bibsource = {dblp computer science bibliography, https://dblp.org}
}
@inproceedings{DBLP:conf/noms/RainerT14,
author = {Benjamin Rainer and
Christian Timmerer},
title = {A subjective evaluation using crowdsourcing of Adaptive Media Playout
utilizing audio-visual content features},
booktitle = {2014 {IEEE} Network Operations and Management Symposium, {NOMS} 2014,
Krakow, Poland, May 5-9, 2014},
pages = {1--7},
publisher = {{IEEE}},
year = {2014},
url = {https://doi.org/10.1109/NOMS.2014.6838406},
doi = {10.1109/NOMS.2014.6838406},
timestamp = {Wed, 16 Oct 2019 14:14:54 +0200},
biburl = {https://dblp.org/rec/conf/noms/RainerT14.bib},
bibsource = {dblp computer science bibliography, https://dblp.org}
}
@article{DBLP:journals/corr/BordeaVMY14,
author = {Prashant L. Borde and
Amarsinh Varpe and
Ramesh R. Manza and
Pravin L. Yannawar},
title = {Recognition of Isolated Words using Zernike and {MFCC} features for
Audio Visual Speech Recognition},
journal = {CoRR},
volume = {abs/1407.1165},
year = {2014},
url = {http://arxiv.org/abs/1407.1165},
eprinttype = {arXiv},
eprint = {1407.1165},
timestamp = {Mon, 13 Aug 2018 01:00:00 +0200},
biburl = {https://dblp.org/rec/journals/corr/BordeaVMY14.bib},
bibsource = {dblp computer science bibliography, https://dblp.org}
}
@inproceedings{DBLP:conf/avsp/BarbulescuHBR13,
author = {Adela Barbulescu and
Thomas Hueber and
G{\'{e}}rard Bailly and
R{\'{e}}mi Ronfard},
editor = {Slim Ouni and
Fr{\'{e}}d{\'{e}}ric Berthommier and
Alexandra Jesse},
title = {Audio-visual speaker conversion using prosody features},
booktitle = {Auditory-Visual Speech Processing, {AVSP} 2013, Annecy, France, August
29 - September 1, 2013},
pages = {11--16},
publisher = {{ISCA}},
year = {2013},
url = {http://www.isca-speech.org/archive/avsp13/av13\_011.html},
timestamp = {Tue, 16 Nov 2021 11:36:14 +0100},
biburl = {https://dblp.org/rec/conf/avsp/BarbulescuHBR13.bib},
bibsource = {dblp computer science bibliography, https://dblp.org}
}
@inproceedings{DBLP:conf/avsp/ShenTH13,
author = {Peng Shen and
Satoshi Tamura and
Satoru Hayamizu},
editor = {Slim Ouni and
Fr{\'{e}}d{\'{e}}ric Berthommier and
Alexandra Jesse},
title = {Audio-visual interaction in sparse representation features for noise
robust audio-visual speech recognition},
booktitle = {Auditory-Visual Speech Processing, {AVSP} 2013, Annecy, France, August
29 - September 1, 2013},
pages = {43--48},
publisher = {{ISCA}},
year = {2013},
url = {http://www.isca-speech.org/archive/avsp13/av13\_043.html},
timestamp = {Tue, 16 Nov 2021 00:00:00 +0100},
biburl = {https://dblp.org/rec/conf/avsp/ShenTH13.bib},
bibsource = {dblp computer science bibliography, https://dblp.org}
}
@inproceedings{DBLP:conf/cvpr/WangZH13,
author = {Tao Wang and
Zhigang Zhu and
Riad I. Hammoud},
title = {Audio-Visual Feature Fusion for Vehicles Classification in a Surveillance
System},
booktitle = {{IEEE} Conference on Computer Vision and Pattern Recognition, {CVPR}
Workshops 2013, Portland, OR, USA, June 23-28, 2013},
pages = {381--386},
publisher = {{IEEE} Computer Society},
year = {2013},
url = {https://doi.org/10.1109/CVPRW.2013.64},
doi = {10.1109/CVPRW.2013.64},
timestamp = {Fri, 24 Mar 2023 00:00:00 +0100},
biburl = {https://dblp.org/rec/conf/cvpr/WangZH13.bib},
bibsource = {dblp computer science bibliography, https://dblp.org}
}
@inproceedings{DBLP:conf/dev/FirminoT13,
author = {Emiliano Firmino and
Mauro Te{\'{o}}filo},
editor = {William D. Tucker and
Antoine B. Bagula and
Margaret Martonosi and
Bhaskaran Raman},
title = {Visually impaired navigation assistant for emerging market using tactile
floor, feature phone and audio descriptions},
booktitle = {Annual Symposium on Computing for Development, {ACM} DEV-4, Cape Town,
South Africa - December 06 - 07, 2013},
pages = {20:1--20:2},
publisher = {{ACM}},
year = {2013},
url = {https://doi.org/10.1145/2537052.2537072},
doi = {10.1145/2537052.2537072},
timestamp = {Tue, 06 Nov 2018 00:00:00 +0100},
biburl = {https://dblp.org/rec/conf/dev/FirminoT13.bib},
bibsource = {dblp computer science bibliography, https://dblp.org}
}
@inproceedings{DBLP:conf/icmcs/SayedelahlAK13,
author = {Aya Sayedelahl and
Rodrigo Araujo and
Mohamed S. Kamel},
title = {Audio-visual feature-decision level fusion for spontaneous emotion
estimation in speech conversations},
booktitle = {2013 {IEEE} International Conference on Multimedia and Expo Workshops,
San Jose, CA, USA, July 15-19, 2013},
pages = {1--6},
publisher = {{IEEE} Computer Society},
year = {2013},
url = {https://doi.org/10.1109/ICMEW.2013.6618372},
doi = {10.1109/ICMEW.2013.6618372},
timestamp = {Fri, 24 Mar 2023 00:00:00 +0100},
biburl = {https://dblp.org/rec/conf/icmcs/SayedelahlAK13.bib},
bibsource = {dblp computer science bibliography, https://dblp.org}
}
@inproceedings{DBLP:conf/interspeech/KhanM13,
author = {Faheem Khan and
Ben Milner},
editor = {Fr{\'{e}}d{\'{e}}ric Bimbot and
Christophe Cerisara and
C{\'{e}}cile Fougeron and
Guillaume Gravier and
Lori Lamel and
Fran{\c{c}}ois Pellegrino and
Pascal Perrier},
title = {Speaker separation using visual speech features and single-channel
audio},
booktitle = {{INTERSPEECH} 2013, 14th Annual Conference of the International Speech
Communication Association, Lyon, France, August 25-29, 2013},
pages = {3264--3268},
publisher = {{ISCA}},
year = {2013},
url = {https://doi.org/10.21437/Interspeech.2013-723},
doi = {10.21437/INTERSPEECH.2013-723},
timestamp = {Fri, 23 Jun 2023 01:00:00 +0200},
biburl = {https://dblp.org/rec/conf/interspeech/KhanM13.bib},
bibsource = {dblp computer science bibliography, https://dblp.org}
}
@inproceedings{DBLP:conf/interspeech/TiippanaTVV13,
author = {Kaisa Tiippana and
Mikko Tiainen and
Lari Vainio and
Martti Vainio},
editor = {Fr{\'{e}}d{\'{e}}ric Bimbot and
Christophe Cerisara and
C{\'{e}}cile Fougeron and
Guillaume Gravier and
Lori Lamel and
Fran{\c{c}}ois Pellegrino and
Pascal Perrier},
title = {Acoustic and visual phonetic features in the mcgurk effect - an audiovisual
speech illusion},
booktitle = {{INTERSPEECH} 2013, 14th Annual Conference of the International Speech
Communication Association, Lyon, France, August 25-29, 2013},
pages = {1634--1638},
publisher = {{ISCA}},
year = {2013},
url = {https://doi.org/10.21437/Interspeech.2013-424},
doi = {10.21437/INTERSPEECH.2013-424},
timestamp = {Fri, 23 Jun 2023 01:00:00 +0200},
biburl = {https://dblp.org/rec/conf/interspeech/TiippanaTVV13.bib},
bibsource = {dblp computer science bibliography, https://dblp.org}
}
@inproceedings{DBLP:conf/iscas/ZhangZX13,
author = {Bo Zhang and
Jiancheng Zou and
Bo Xu},
title = {Context-dependent audio-visual and temporal features fusion for {TV}
commercial detection},
booktitle = {2013 {IEEE} International Symposium on Circuits and Systems (ISCAS2013),
Beijing, China, May 19-23, 2013},
pages = {5--8},
publisher = {{IEEE}},
year = {2013},
url = {https://doi.org/10.1109/ISCAS.2013.6571768},
doi = {10.1109/ISCAS.2013.6571768},
timestamp = {Wed, 16 Oct 2019 14:14:49 +0200},
biburl = {https://dblp.org/rec/conf/iscas/ZhangZX13.bib},
bibsource = {dblp computer science bibliography, https://dblp.org}
}
@inproceedings{DBLP:conf/mir/GodinNW13,
author = {Fr{\'{e}}deric Godin and
Wesley De Neve and
Rik Van de Walle},
editor = {Ramesh C. Jain and
Balakrishnan Prabhakaran and
Marcel Worring and
John R. Smith and
Tat{-}Seng Chua},
title = {Towards fusion of collective knowledge and audio-visual content features
for annotating broadcast video},
booktitle = {International Conference on Multimedia Retrieval, ICMR'13, Dallas,
TX, USA, April 16-19, 2013},
pages = {329--332},
publisher = {{ACM}},
year = {2013},
url = {https://doi.org/10.1145/2461466.2461530},
doi = {10.1145/2461466.2461530},
timestamp = {Mon, 22 Apr 2024 21:24:20 +0200},
biburl = {https://dblp.org/rec/conf/mir/GodinNW13.bib},
bibsource = {dblp computer science bibliography, https://dblp.org}
}
@inproceedings{DBLP:conf/mm/RudovicPP13,
author = {Ognjen Rudovic and
Stavros Petridis and
Maja Pantic},
editor = {Alejandro Jaimes and
Nicu Sebe and
Nozha Boujemaa and
Daniel Gatica{-}Perez and
David A. Shamma and
Marcel Worring and
Roger Zimmermann},
title = {Bimodal log-linear regression for fusion of audio and visual features},
booktitle = {{ACM} Multimedia Conference, {MM} '13, Barcelona, Spain, October 21-25,
2013},
pages = {789--792},
publisher = {{ACM}},
year = {2013},
url = {https://doi.org/10.1145/2502081.2502207},
doi = {10.1145/2502081.2502207},
timestamp = {Tue, 06 Nov 2018 00:00:00 +0100},
biburl = {https://dblp.org/rec/conf/mm/RudovicPP13.bib},
bibsource = {dblp computer science bibliography, https://dblp.org}
}
@inproceedings{DBLP:conf/mmm/ZhangFX13,
author = {Bo Zhang and
Bailan Feng and
Bo Xu},
editor = {Shipeng Li and
Abdulmotaleb El{-}Saddik and
Meng Wang and
Tao Mei and
Nicu Sebe and
Shuicheng Yan and
Richang Hong and
Cathal Gurrin},
title = {Fusion of Audio-Visual Features and Statistical Property for Commercial
Segmentation},
booktitle = {Advances in Multimedia Modeling, 19th International Conference, {MMM}
2013, Huangshan, China, January 7-9, 2013, Proceedings, Part {I}},
series = {Lecture Notes in Computer Science},
volume = {7732},
pages = {250--260},
publisher = {Springer},
year = {2013},
url = {https://doi.org/10.1007/978-3-642-35725-1\_23},
doi = {10.1007/978-3-642-35725-1\_23},
timestamp = {Mon, 23 Nov 2020 15:58:17 +0100},
biburl = {https://dblp.org/rec/conf/mmm/ZhangFX13.bib},
bibsource = {dblp computer science bibliography, https://dblp.org}
}
@article{DBLP:journals/taslp/NewmanC12,
author = {Jacob L. Newman and
Stephen J. Cox},
title = {Language Identification Using Visual Features},
journal = {{IEEE} Trans. Speech Audio Process.},
volume = {20},
number = {7},
pages = {1936--1947},
year = {2012},
url = {https://doi.org/10.1109/TASL.2012.2191956},
doi = {10.1109/TASL.2012.2191956},
timestamp = {Sun, 17 May 2020 01:00:00 +0200},
biburl = {https://dblp.org/rec/journals/taslp/NewmanC12.bib},
bibsource = {dblp computer science bibliography, https://dblp.org}
}
@inproceedings{DBLP:conf/acssc/SuiTHB12,
author = {Chao Sui and
Roberto Togneri and
Serajul Haque and
Mohammed Bennamoun},
editor = {Michael B. Matthews},
title = {Discrimination comparison between audio and visual features},
booktitle = {Conference Record of the Forty Sixth Asilomar Conference on Signals,
Systems and Computers, {ACSCC} 2012, Pacific Grove, CA, USA, November
4-7, 2012},
pages = {1609--1612},
publisher = {{IEEE}},
year = {2012},
url = {https://doi.org/10.1109/ACSSC.2012.6489302},
doi = {10.1109/ACSSC.2012.6489302},
timestamp = {Sat, 19 Oct 2019 01:00:00 +0200},
biburl = {https://dblp.org/rec/conf/acssc/SuiTHB12.bib},
bibsource = {dblp computer science bibliography, https://dblp.org}
}
@inproceedings{DBLP:conf/apsipa/ShenTH12,
author = {Peng Shen and
Satoshi Tamura and
Satoru Hayamizu},
title = {Feature reconstruction using sparse imputation for noise robust audio-visual
speech recognition},
booktitle = {Asia-Pacific Signal and Information Processing Association Annual
Summit and Conference, {APSIPA} 2012, Hollywood, CA, USA, December
3-6, 2012},
pages = {1--4},
publisher = {{IEEE}},
year = {2012},
url = {https://ieeexplore.ieee.org/document/6411773/},
timestamp = {Sun, 08 Aug 2021 01:00:00 +0200},
biburl = {https://dblp.org/rec/conf/apsipa/ShenTH12.bib},
bibsource = {dblp computer science bibliography, https://dblp.org}
}
@inproceedings{DBLP:conf/iconip/AlmaadeedAA12,
author = {Noor Almaadeed and
Amar Aggoun and
Abbes Amira},
editor = {Tingwen Huang and
Zhigang Zeng and
Chuandong Li and
Chi{-}Sing Leung},
title = {Audio-Visual Feature Fusion for Speaker Identification},
booktitle = {Neural Information Processing - 19th International Conference, {ICONIP}
2012, Doha, Qatar, November 12-15, 2012, Proceedings, Part {I}},
series = {Lecture Notes in Computer Science},
volume = {7663},
pages = {56--67},
publisher = {Springer},
year = {2012},
url = {https://doi.org/10.1007/978-3-642-34475-6\_8},
doi = {10.1007/978-3-642-34475-6\_8},
timestamp = {Tue, 30 Jun 2020 11:04:50 +0200},
biburl = {https://dblp.org/rec/conf/iconip/AlmaadeedAA12.bib},
bibsource = {dblp computer science bibliography, https://dblp.org}
}
@inproceedings{DBLP:conf/slt/KashiwagiSMH12,
author = {Yosuke Kashiwagi and
Masayuki Suzuki and
Nobuaki Minematsu and
Keikichi Hirose},
title = {Audio-visual feature integration based on piecewise linear transformation
for noise robust automatic speech recognition},
booktitle = {2012 {IEEE} Spoken Language Technology Workshop (SLT), Miami, FL,
USA, December 2-5, 2012},
pages = {149--152},
publisher = {{IEEE}},
year = {2012},
url = {https://doi.org/10.1109/SLT.2012.6424213},
doi = {10.1109/SLT.2012.6424213},
timestamp = {Wed, 16 Oct 2019 14:14:53 +0200},
biburl = {https://dblp.org/rec/conf/slt/KashiwagiSMH12.bib},
bibsource = {dblp computer science bibliography, https://dblp.org}
}
@inproceedings{DBLP:conf/centeris/OliveiraAA11,
author = {Rita Oliveira and
Jorge Ferraz de Abreu and
Ana Margarida Pisco Almeida},
editor = {Maria Manuela Cruz{-}Cunha and
Jo{\~{a}}o Varaj{\~{a}}o and
Philip Powell and
Ricardo Martinho},
title = {An iTV Audio Description Service: Suggesting Requirements and Features
for Visually Impaired Users},
booktitle = {ENTERprise Information Systems - International Conference, {CENTERIS}
2011, Vilamoura, Portugal, October 5-7, 2011, Proceedings, Part {III}},
series = {Communications in Computer and Information Science},
volume = {221},
pages = {59--68},
publisher = {Springer},
year = {2011},
url = {https://doi.org/10.1007/978-3-642-24352-3\_7},
doi = {10.1007/978-3-642-24352-3\_7},
timestamp = {Tue, 23 Apr 2024 23:18:35 +0200},
biburl = {https://dblp.org/rec/conf/centeris/OliveiraAA11.bib},
bibsource = {dblp computer science bibliography, https://dblp.org}
}
@inproceedings{DBLP:conf/cikm/IslamABR11,
author = {Muhammad Asiful Islam and
Faisal Ahmed and
Yevgen Borodin and
I. V. Ramakrishnan},
editor = {Craig Macdonald and
Iadh Ounis and
Ian Ruthven},
title = {Tightly coupling visual and linguistic features for enriching audio-based
web browsing experience},
booktitle = {Proceedings of the 20th {ACM} Conference on Information and Knowledge
Management, {CIKM} 2011, Glasgow, United Kingdom, October 24-28, 2011},
pages = {2085--2088},
publisher = {{ACM}},
year = {2011},
url = {https://doi.org/10.1145/2063576.2063896},
doi = {10.1145/2063576.2063896},
timestamp = {Tue, 06 Nov 2018 00:00:00 +0100},
biburl = {https://dblp.org/rec/conf/cikm/IslamABR11.bib},
bibsource = {dblp computer science bibliography, https://dblp.org}
}
@inproceedings{DBLP:conf/eusipco/LiuNWJC11,
author = {Qingju Liu and
Syed Mohsen Naqvi and
Wenwu Wang and
Philip J. B. Jackson and
Jonathon A. Chambers},
title = {Robust feature selection for scaling ambiguity reduction in audio-visual
convolutive {BSS}},
booktitle = {Proceedings of the 19th European Signal Processing Conference, {EUSIPCO}
2011, Barcelona, Spain, August 29 - Sept. 2, 2011},
pages = {1060--1064},
publisher = {{IEEE}},
year = {2011},
url = {https://ieeexplore.ieee.org/document/7074127/},
timestamp = {Thu, 05 Jan 2023 00:00:00 +0100},
biburl = {https://dblp.org/rec/conf/eusipco/LiuNWJC11.bib},
bibsource = {dblp computer science bibliography, https://dblp.org}
}
@inproceedings{DBLP:conf/icassp/ChandrasekharSR11,
author = {Vijay Chandrasekhar and
Mehmet Emre Sargin and
David A. Ross},
title = {Automatic Language Identification in music videos with low level audio
and visual features},
booktitle = {Proceedings of the {IEEE} International Conference on Acoustics, Speech,
and Signal Processing, {ICASSP} 2011, May 22-27, 2011, Prague Congress
Center, Prague, Czech Republic},
pages = {5724--5727},
publisher = {{IEEE}},
year = {2011},
url = {https://doi.org/10.1109/ICASSP.2011.5947660},
doi = {10.1109/ICASSP.2011.5947660},
timestamp = {Tue, 23 Jul 2019 01:00:00 +0200},
biburl = {https://dblp.org/rec/conf/icassp/ChandrasekharSR11.bib},
bibsource = {dblp computer science bibliography, https://dblp.org}
}
@inproceedings{DBLP:conf/maics/SchlittenhartWSI11,
author = {Isaac Schlittenhart and
Jason Winters and
Kyle Springer and
Atsushi Inoue},
editor = {Sofia Visa and
Atsushi Inoue and
Anca L. Ralescu},
title = {Toward Robust Features for Remote Audio-Visual Classroom},
booktitle = {Proceedings of The 22nd Midwest Artificial Intelligence and Cognitive
Science Conference 2011, Cincinnati, Ohio, USA, April 16-17, 2011},
series = {{CEUR} Workshop Proceedings},
volume = {710},
pages = {202--207},
publisher = {CEUR-WS.org},
year = {2011},
url = {https://ceur-ws.org/Vol-710/paper38.pdf},
timestamp = {Fri, 10 Mar 2023 16:22:19 +0100},
biburl = {https://dblp.org/rec/conf/maics/SchlittenhartWSI11.bib},
bibsource = {dblp computer science bibliography, https://dblp.org}
}
@inproceedings{DBLP:conf/mediaeval/AcarSA11,
author = {Esra Acar and
Stephan Spiegel and
Sahin Albayrak},
editor = {Martha A. Larson and
Adam Rae and
Claire{-}H{\'{e}}l{\`{e}}ne Demarty and
Christoph Kofler and
Florian Metze and
Rapha{\"{e}}l Troncy and
Vasileios Mezaris and
Gareth J. F. Jones},
title = {MediaEval 2011 Affect Task: Violent Scene Detection combining audio
and visual Features with {SVM}},
booktitle = {Working Notes Proceedings of the MediaEval 2011 Workshop, Santa Croce
in Fossabanda, Pisa, Italy, September 1-2, 2011},
series = {{CEUR} Workshop Proceedings},
volume = {807},
publisher = {CEUR-WS.org},
year = {2011},
url = {https://ceur-ws.org/Vol-807/acar\_TUB\_Violence\_me11wn.pdf},
timestamp = {Fri, 10 Mar 2023 16:22:12 +0100},
biburl = {https://dblp.org/rec/conf/mediaeval/AcarSA11.bib},
bibsource = {dblp computer science bibliography, https://dblp.org}
}
@inproceedings{DBLP:conf/psivt/KomaiAT11,
author = {Yuto Komai and
Yasuo Ariki and
Tetsuya Takiguchi},
editor = {Yo{-}Sung Ho},
title = {Audio-Visual Speech Recognition Based on {AAM} Parameter and Phoneme
Analysis of Visual Feature},
booktitle = {Advances in Image and Video Technology - 5th Pacific Rim Symposium,
{PSIVT} 2011, Gwangju, South Korea, November 20-23, 2011, Proceedings,
Part {I}},
series = {Lecture Notes in Computer Science},
volume = {7087},
pages = {97--108},
publisher = {Springer},
year = {2011},
url = {https://doi.org/10.1007/978-3-642-25367-6\_9},
doi = {10.1007/978-3-642-25367-6\_9},
timestamp = {Tue, 14 May 2019 10:00:47 +0200},
biburl = {https://dblp.org/rec/conf/psivt/KomaiAT11.bib},
bibsource = {dblp computer science bibliography, https://dblp.org}
}
@inproceedings{DBLP:conf/trecvid/PereraOLKBLMLMH11,
author = {A. G. Amitha Perera and
Sangmin Oh and
Matthew J. Leotta and
Ilseo Kim and
Byungki Byun and
Chin{-}Hui Lee and
Scott McCloskey and
Jingchen Liu and
Ben Miller and
Zhi Feng Huang and
Arash Vahdat and
Weilong Yang and
Greg Mori and
Kevin Tang and
Daphne Koller and
Li Fei{-}Fei and
Kang Li and
Gang Chen and
Jason J. Corso and
Yun Fu and
Rohini K. Srihari},
editor = {Paul Over and
George Awad and
Jonathan G. Fiscus and
Brian Antonishek and
Martial Michel and
Alan F. Smeaton and
Wessel Kraaij and
Georges Qu{\'{e}}not},
title = {{GENIE} {TRECVID} 2011 Multimedia Event Detection: Late-Fusion Approaches
to Combine Multiple Audio-Visual features},
booktitle = {2011 {TREC} Video Retrieval Evaluation, {TRECVID} 2011, Gaithersburg,
MD, USA, December 5-7, 2011},
publisher = {National Institute of Standards and Technology {(NIST)}},
year = {2011},
url = {https://www-nlpir.nist.gov/projects/tvpubs/tv11.papers/genie.pdf},
timestamp = {Tue, 10 Jan 2023 00:00:00 +0100},
biburl = {https://dblp.org/rec/conf/trecvid/PereraOLKBLMLMH11.bib},
bibsource = {dblp computer science bibliography, https://dblp.org}
}
@inproceedings{DBLP:conf/trustcom/LiuWZT11,
author = {Yizhi Liu and
Xiangdong Wang and
Yongdong Zhang and
Sheng Tang},
title = {Fusing Audio-Words with Visual Features for Pornographic Video Detection},
booktitle = {{IEEE} 10th International Conference on Trust, Security and Privacy
in Computing and Communications, TrustCom 2011, Changsha, China, 16-18
November, 2011},
pages = {1488--1493},
publisher = {{IEEE} Computer Society},
year = {2011},
url = {https://doi.org/10.1109/TrustCom.2011.205},
doi = {10.1109/TRUSTCOM.2011.205},
timestamp = {Fri, 24 Mar 2023 00:00:00 +0100},
biburl = {https://dblp.org/rec/conf/trustcom/LiuWZT11.bib},
bibsource = {dblp computer science bibliography, https://dblp.org}
}
@article{DBLP:journals/csl/DeanS10,
author = {David Dean and
Sridha Sridharan},
title = {Dynamic visual features for audio-visual speaker verification},
journal = {Comput. Speech Lang.},
volume = {24},
number = {2},
pages = {136--149},
year = {2010},
url = {https://doi.org/10.1016/j.csl.2009.03.007},
doi = {10.1016/J.CSL.2009.03.007},
timestamp = {Thu, 20 Feb 2020 00:00:00 +0100},
biburl = {https://dblp.org/rec/journals/csl/DeanS10.bib},
bibsource = {dblp computer science bibliography, https://dblp.org}
}
@article{DBLP:journals/ijsc/ShahHN10,
author = {Dhaval Shah and
Kyu Jeong Han and
Shrikanth S. Narayanan},
title = {Robust Multimodal Person Recognition Using Low-Complexity Audio-Visual
Feature Fusion Approaches},
journal = {Int. J. Semantic Comput.},
volume = {4},
number = {2},
pages = {155--179},
year = {2010},
url = {https://doi.org/10.1142/S1793351X10000985},
doi = {10.1142/S1793351X10000985},
timestamp = {Fri, 03 Jul 2020 01:00:00 +0200},
biburl = {https://dblp.org/rec/journals/ijsc/ShahHN10.bib},
bibsource = {dblp computer science bibliography, https://dblp.org}
}
@article{DBLP:journals/tmm/ShresthaBWS10,
author = {Prarthana Shrestha and
Mauro Barbieri and
Hans Weda and
Dragan Sekulovski},
title = {Synchronization of Multiple Camera Videos Using Audio-Visual Features},
journal = {{IEEE} Trans. Multim.},
volume = {12},
number = {1},
pages = {79--92},
year = {2010},
url = {https://doi.org/10.1109/TMM.2009.2036285},
doi = {10.1109/TMM.2009.2036285},
timestamp = {Thu, 01 Oct 2020 01:00:00 +0200},
biburl = {https://dblp.org/rec/journals/tmm/ShresthaBWS10.bib},
bibsource = {dblp computer science bibliography, https://dblp.org}
}
@article{DBLP:journals/vlsisp/MuneesawangGA10,
author = {Paisarn Muneesawang and
Ling Guan and
Tahir Amin},
title = {A New Learning Algorithm for the Fusion of Adaptive Audio-Visual Features
for the Retrieval and Classification of Movie Clips},
journal = {J. Signal Process. Syst.},
volume = {59},
number = {2},
pages = {177--188},
year = {2010},
url = {https://doi.org/10.1007/s11265-008-0290-7},
doi = {10.1007/S11265-008-0290-7},
timestamp = {Thu, 12 Mar 2020 00:00:00 +0100},
biburl = {https://dblp.org/rec/journals/vlsisp/MuneesawangGA10.bib},
bibsource = {dblp computer science bibliography, https://dblp.org}
}
@inproceedings{DBLP:conf/icassp/PetridisAP10,
author = {Stavros Petridis and
Ali Asghar and
Maja Pantic},
title = {Classifying laughter and speech using audio-visual feature prediction},
booktitle = {Proceedings of the {IEEE} International Conference on Acoustics, Speech,
and Signal Processing, {ICASSP} 2010, 14-19 March 2010, Sheraton Dallas
Hotel, Dallas, Texas, {USA}},
pages = {5254--5257},
publisher = {{IEEE}},
year = {2010},
url = {https://doi.org/10.1109/ICASSP.2010.5494992},
doi = {10.1109/ICASSP.2010.5494992},
timestamp = {Fri, 19 May 2017 01:00:00 +0200},
biburl = {https://dblp.org/rec/conf/icassp/PetridisAP10.bib},
bibsource = {dblp computer science bibliography, https://dblp.org}
}
@inproceedings{DBLP:conf/icmcs/BoyarAASCA10,
author = {Mujdat Boyar and
{\"{O}}zg{\"{u}}r Alan and
Samet Akpinar and
Orkunt Sabuncu and
Nihan K. {\c{C}}i{\c{c}}ekli and
Ferda Nur Alpaslan},
title = {Event boundary detection using audio-visual features and web-casting
texts with imprecise time information},
booktitle = {Proceedings of the 2010 {IEEE} International Conference on Multimedia
and Expo, {ICME} 2010, 19-23 July 2010, Singapore},
pages = {578--583},
publisher = {{IEEE} Computer Society},
year = {2010},
url = {https://doi.org/10.1109/ICME.2010.5583864},
doi = {10.1109/ICME.2010.5583864},
timestamp = {Fri, 24 Mar 2023 00:00:00 +0100},
biburl = {https://dblp.org/rec/conf/icmcs/BoyarAASCA10.bib},
bibsource = {dblp computer science bibliography, https://dblp.org}
}
@inproceedings{DBLP:conf/interspeech/ButkoN10,
author = {Taras Butko and
Climent Nadeu},
editor = {Takao Kobayashi and
Keikichi Hirose and
Satoshi Nakamura},
title = {A fast one-pass-training feature selection technique for GMM-based
acoustic event detection with audio-visual data},
booktitle = {{INTERSPEECH} 2010, 11th Annual Conference of the International Speech
Communication Association, Makuhari, Chiba, Japan, September 26-30,
2010},
pages = {2338--2341},
publisher = {{ISCA}},
year = {2010},
url = {https://doi.org/10.21437/Interspeech.2010-640},
doi = {10.21437/INTERSPEECH.2010-640},
timestamp = {Fri, 23 Jun 2023 01:00:00 +0200},
biburl = {https://dblp.org/rec/conf/interspeech/ButkoN10.bib},
bibsource = {dblp computer science bibliography, https://dblp.org}
}
@inproceedings{DBLP:conf/iscslp/JiangWWSV10,
author = {Dongmei Jiang and
Peng Wu and
Fengna Wang and
Hichem Sahli and
Werner Verhelst},
title = {Audio visual speech recognition based on multi-stream {DBN} models
with Articulatory Features},
booktitle = {7th International Symposium on Chinese Spoken Language Processing,
{ISCSLP} 2010, November 29 2010-December 3, 2010, Tainan {\&}
Sun Moon Lake, Taiwan},
pages = {190--193},
publisher = {{IEEE}},
year = {2010},
url = {https://doi.org/10.1109/ISCSLP.2010.5684915},
doi = {10.1109/ISCSLP.2010.5684915},
timestamp = {Wed, 16 Oct 2019 14:14:48 +0200},
biburl = {https://dblp.org/rec/conf/iscslp/JiangWWSV10.bib},
bibsource = {dblp computer science bibliography, https://dblp.org}
}
@inproceedings{DBLP:conf/sac/RoyM10,
author = {Anindya Roy and
S{\'{e}}bastien Marcel},
editor = {Sung Y. Shin and
Sascha Ossowski and
Michael Schumacher and
Mathew J. Palakal and
Chih{-}Cheng Hung},
title = {Visual processing-inspired fern-audio features for noise-robust speaker
verification},
booktitle = {Proceedings of the 2010 {ACM} Symposium on Applied Computing (SAC),
Sierre, Switzerland, March 22-26, 2010},
pages = {1491--1495},
publisher = {{ACM}},
year = {2010},
url = {https://doi.org/10.1145/1774088.1774407},
doi = {10.1145/1774088.1774407},
timestamp = {Sun, 02 Jun 2019 21:18:37 +0200},
biburl = {https://dblp.org/rec/conf/sac/RoyM10.bib},
bibsource = {dblp computer science bibliography, https://dblp.org}
}
@phdthesis{DBLP:phd/ch/Gurban09,
author = {Mihai Gurban},
title = {Multimodal feature extraction and fusion for audio-visual speech recognition},
school = {EPFL, Switzerland},
year = {2009},
url = {https://doi.org/10.5075/epfl-thesis-4292},
doi = {10.5075/EPFL-THESIS-4292},
timestamp = {Fri, 29 Jul 2022 01:00:00 +0200},
biburl = {https://dblp.org/rec/phd/ch/Gurban09.bib},
bibsource = {dblp computer science bibliography, https://dblp.org}
}
@article{DBLP:journals/tsp/GurbanT09,
author = {Mihai Gurban and
Jean{-}Philippe Thiran},
title = {Information theoretic feature extraction for audio-visual speech recognition},
journal = {{IEEE} Trans. Signal Process.},
volume = {57},
number = {12},
pages = {4765--4776},
year = {2009},
url = {https://doi.org/10.1109/TSP.2009.2026513},
doi = {10.1109/TSP.2009.2026513},
timestamp = {Tue, 10 Mar 2020 00:00:00 +0100},
biburl = {https://dblp.org/rec/journals/tsp/GurbanT09.bib},
bibsource = {dblp computer science bibliography, https://dblp.org}
}
@inproceedings{DBLP:conf/icig/JiangLRSV09,
author = {Dongmei Jiang and
Peizhen Liu and
Ilse Ravyse and
Hichem Sahli and
Werner Verhelst},
title = {Video Realistic Mouth Animation Based on an Audio Visual {DBN} Model
with Articulatory Features and Constrained Asynchrony},
booktitle = {Proceedings of the Fifth International Conference on Image and Graphics,
{ICIG} 2009, Xi'an, Shanxi, China, 20-23 September 2009},
pages = {658--662},
publisher = {{IEEE} Computer Society},
year = {2009},
url = {https://doi.org/10.1109/ICIG.2009.51},
doi = {10.1109/ICIG.2009.51},
timestamp = {Fri, 24 Mar 2023 00:00:00 +0100},
biburl = {https://dblp.org/rec/conf/icig/JiangLRSV09.bib},
bibsource = {dblp computer science bibliography, https://dblp.org}
}
@inproceedings{DBLP:conf/icig/ZhuYL09,
author = {Songhao Zhu and
Junchi Yan and
Yuncai Liu},
title = {Improving Semantic Scene Categorization by Exploiting Audio-Visual
Features},
booktitle = {Proceedings of the Fifth International Conference on Image and Graphics,
{ICIG} 2009, Xi'an, Shanxi, China, 20-23 September 2009},
pages = {435--440},
publisher = {{IEEE} Computer Society},
year = {2009},
url = {https://doi.org/10.1109/ICIG.2009.17},
doi = {10.1109/ICIG.2009.17},
timestamp = {Fri, 24 Mar 2023 00:00:00 +0100},
biburl = {https://dblp.org/rec/conf/icig/ZhuYL09.bib},
bibsource = {dblp computer science bibliography, https://dblp.org}
}
@inproceedings{DBLP:conf/icip/WuZX09,
author = {Guanyong Wu and
Jie Zhu and
Haihua Xu},
title = {A hybrid visual feature extraction method for audio-visual speech
recognition},
booktitle = {Proceedings of the International Conference on Image Processing, {ICIP}
2009, 7-10 November 2009, Cairo, Egypt},
pages = {1829--1832},
publisher = {{IEEE}},
year = {2009},
url = {https://doi.org/10.1109/ICIP.2009.5413573},
doi = {10.1109/ICIP.2009.5413573},
timestamp = {Thu, 19 Dec 2019 00:00:00 +0100},
biburl = {https://dblp.org/rec/conf/icip/WuZX09.bib},
bibsource = {dblp computer science bibliography, https://dblp.org}
}
@inproceedings{DBLP:conf/interspeech/AlmajaiM09,
author = {Ibrahim Almajai and
Ben Milner},
title = {Enhancing audio speech using visual speech features},
booktitle = {{INTERSPEECH} 2009, 10th Annual Conference of the International Speech
Communication Association, Brighton, United Kingdom, September 6-10,
2009},
pages = {1959--1962},
publisher = {{ISCA}},
year = {2009},
url = {https://doi.org/10.21437/Interspeech.2009-576},
doi = {10.21437/INTERSPEECH.2009-576},
timestamp = {Fri, 23 Jun 2023 01:00:00 +0200},
biburl = {https://dblp.org/rec/conf/interspeech/AlmajaiM09.bib},
bibsource = {dblp computer science bibliography, https://dblp.org}
}
@inproceedings{DBLP:conf/mmsp/DasB09,
author = {Amitava Das and
Vaibhav Bedia},
title = {Audio-visual person authentication with multiple face-profiles and
compressed-feature-dynamics signatures of spoken passwords},
booktitle = {2009 {IEEE} International Workshop on Multimedia Signal Processing,
{MMSP} '09, Rio de Janeiro, Brazil, October 5-7, 2009},
pages = {1--6},
publisher = {{IEEE}},
year = {2009},
url = {https://doi.org/10.1109/MMSP.2009.5293273},
doi = {10.1109/MMSP.2009.5293273},
timestamp = {Wed, 16 Oct 2019 14:14:49 +0200},
biburl = {https://dblp.org/rec/conf/mmsp/DasB09.bib},
bibsource = {dblp computer science bibliography, https://dblp.org}
}
@inproceedings{DBLP:conf/smc/PaoLWL09,
author = {Tsang{-}Long Pao and
Wen{-}Yuan Liao and
Tsan{-}Nung Wu and
Ching{-}Yi Lin},
title = {Automatic Visual Feature Extraction for Mandarin Audio-Visual Speech
Recognition},
booktitle = {Proceedings of the {IEEE} International Conference on Systems, Man
and Cybernetics, San Antonio, TX, USA, 11-14 October 2009},
pages = {2936--2940},
publisher = {{IEEE}},
year = {2009},
url = {https://doi.org/10.1109/ICSMC.2009.5346011},
doi = {10.1109/ICSMC.2009.5346011},
timestamp = {Wed, 16 Oct 2019 14:14:51 +0200},
biburl = {https://dblp.org/rec/conf/smc/PaoLWL09.bib},
bibsource = {dblp computer science bibliography, https://dblp.org}
}
@article{DBLP:journals/ieicet/DendaNY08,
author = {Yuki Denda and
Takanobu Nishiura and
Yoichi Yamashita},
title = {Omnidirectional Audio-Visual Talker Localization Based on Dynamic
Fusion of Audio-Visual Features Using Validity and Reliability Criteria},
journal = {{IEICE} Trans. Inf. Syst.},
volume = {91-D},
number = {3},
pages = {598--606},
year = {2008},
url = {https://doi.org/10.1093/ietisy/e91-d.3.598},
doi = {10.1093/IETISY/E91-D.3.598},
timestamp = {Sat, 11 Apr 2020 01:00:00 +0200},
biburl = {https://dblp.org/rec/journals/ieicet/DendaNY08.bib},
bibsource = {dblp computer science bibliography, https://dblp.org}
}
@inproceedings{DBLP:conf/avsp/HaqJE08,
author = {Sanaul Haq and
Philip J. B. Jackson and
James D. Edge},
editor = {Roland G{\"{o}}cke and
Patrick Lucey and
Simon Lucey},
title = {Audio-visual feature selection and reduction for emotion classification},
booktitle = {International Conference on Auditory-Visual Speech Processing 2008,
Moreton Island, Queensland, Australia, September 26-29, 2008},
pages = {185--190},
publisher = {{ISCA}},
year = {2008},
url = {http://www.isca-speech.org/archive\_open/avsp08/av08\_185.html},
timestamp = {Wed, 10 Feb 2021 22:00:47 +0100},
biburl = {https://dblp.org/rec/conf/avsp/HaqJE08.bib},
bibsource = {dblp computer science bibliography, https://dblp.org}
}
@inproceedings{DBLP:conf/eusipco/AlmajaiM08,
author = {Ibrahim Almajai and
Ben P. Milner},
title = {Using audio-visual features for robust voice activity detection in
clean and noisy speech},
booktitle = {2008 16th European Signal Processing Conference, {EUSIPCO} 2008, Lausanne,
Switzerland, August 25-29, 2008},
pages = {1--5},
publisher = {{IEEE}},
year = {2008},
url = {https://ieeexplore.ieee.org/document/7080692/},
timestamp = {Mon, 09 Aug 2021 01:00:00 +0200},
biburl = {https://dblp.org/rec/conf/eusipco/AlmajaiM08.bib},
bibsource = {dblp computer science bibliography, https://dblp.org}
}
@inproceedings{DBLP:conf/eusipco/DemirEYT08,
author = {Yasemin Demir and
Engin Erzin and
Y{\"{u}}cel Yemez and
A. Murat Tekalp},
title = {Evaluation of audio features for audio-visual analysis of dance figures},
booktitle = {2008 16th European Signal Processing Conference, {EUSIPCO} 2008, Lausanne,
Switzerland, August 25-29, 2008},
pages = {1--4},
publisher = {{IEEE}},
year = {2008},
url = {https://ieeexplore.ieee.org/document/7080401/},
timestamp = {Mon, 09 Aug 2021 01:00:00 +0200},
biburl = {https://dblp.org/rec/conf/eusipco/DemirEYT08.bib},
bibsource = {dblp computer science bibliography, https://dblp.org}
}
@inproceedings{DBLP:conf/icip/TerrySK08,
author = {Louis H. Terry and
Derek J. Shiell and
Aggelos K. Katsaggelos},
title = {Feature space video stream consistency estimation for dynamic stream
weighting in audio-visual speech recognition},
booktitle = {Proceedings of the International Conference on Image Processing, {ICIP}
2008, October 12-15, 2008, San Diego, California, {USA}},
pages = {1316--1319},
publisher = {{IEEE}},
year = {2008},
url = {https://doi.org/10.1109/ICIP.2008.4712005},
doi = {10.1109/ICIP.2008.4712005},
timestamp = {Tue, 21 Mar 2023 00:00:00 +0100},
biburl = {https://dblp.org/rec/conf/icip/TerrySK08.bib},
bibsource = {dblp computer science bibliography, https://dblp.org}
}
@inproceedings{DBLP:conf/icvgip/DasMT08,
author = {Amitava Das and
Ohil K. Manyam and
Makarand Tapaswi},
title = {Audio-Visual Person Authentication with Multiple Visualized-Speech
Features and Multiple Face Profiles},
booktitle = {Sixth Indian Conference on Computer Vision, Graphics {\&} Image
Processing, {ICVGIP} 2008, Bhubaneswar, India, 16-19 December 2008},
pages = {39--46},
publisher = {{IEEE} Computer Society},
year = {2008},
url = {https://doi.org/10.1109/ICVGIP.2008.106},
doi = {10.1109/ICVGIP.2008.106},
timestamp = {Fri, 24 Mar 2023 00:00:00 +0100},
biburl = {https://dblp.org/rec/conf/icvgip/DasMT08.bib},
bibsource = {dblp computer science bibliography, https://dblp.org}
}
@inproceedings{DBLP:conf/ism/MowerMN08,
author = {Emily Mower and
Maja J. Mataric and
Shrikanth S. Narayanan},
title = {Selection of Emotionally Salient Audio-Visual Features for Modeling
Human Evaluations of Synthetic Character Emotion Displays},
booktitle = {Tenth {IEEE} International Symposium on Multimedia (ISM2008), December
15-17, 2008, Berkeley, California, {USA}},
pages = {190--195},
publisher = {{IEEE} Computer Society},
year = {2008},
url = {https://doi.org/10.1109/ISM.2008.78},
doi = {10.1109/ISM.2008.78},
timestamp = {Fri, 24 Mar 2023 00:00:00 +0100},
biburl = {https://dblp.org/rec/conf/ism/MowerMN08.bib},
bibsource = {dblp computer science bibliography, https://dblp.org}
}
@incollection{DBLP:series/asc/Chaloupka08,
author = {Josef Chaloupka},
editor = {Marek Kurzynski and
Edward Puchala and
Michal Wozniak and
Andrzej Zolnierek},
title = {Extraction of the Visual Features from the Audio-Visual Speech Signal
and the Utilization of These Features for the Speaker Identification},
booktitle = {Computer Recognition Systems 2},
series = {Advances in Soft Computing},
volume = {45},
pages = {413--420},
publisher = {Springer},
year = {2008},
url = {https://doi.org/10.1007/978-3-540-75175-5\_52},
doi = {10.1007/978-3-540-75175-5\_52},
timestamp = {Thu, 07 Nov 2019 15:14:22 +0100},
biburl = {https://dblp.org/rec/series/asc/Chaloupka08.bib},
bibsource = {dblp computer science bibliography, https://dblp.org}
}
@article{DBLP:journals/jmui/ChituRWW07,
author = {Alin Gavril Chitu and
L{\'{e}}on J. M. Rothkrantz and
Pascal Wiggers and
Jacek C. Wojdel},
title = {Comparison between different feature extraction techniques for audio-visual
speech recognition},
journal = {J. Multimodal User Interfaces},
volume = {1},
number = {1},
pages = {7--20},
year = {2007},
url = {https://doi.org/10.1007/BF02884428},
doi = {10.1007/BF02884428},
timestamp = {Sun, 28 May 2017 01:00:00 +0200},
biburl = {https://dblp.org/rec/journals/jmui/ChituRWW07.bib},
bibsource = {dblp computer science bibliography, https://dblp.org}
}
@article{DBLP:journals/tce/OtsukaSKD07,
author = {Isao Otsuka and
Hidetsugu Suginohara and
Yoshiaki Kusunoki and
Ajay Divakaran},
title = {Detection of music segment boundaries using audio-visual features
for a personal video recorder},
journal = {{IEEE} Trans. Consumer Electron.},
volume = {53},
number = {1},
pages = {150--154},
year = {2007},
url = {https://doi.org/10.1109/TCE.2007.339517},
doi = {10.1109/TCE.2007.339517},
timestamp = {Thu, 09 Jul 2020 01:00:00 +0200},
biburl = {https://dblp.org/rec/journals/tce/OtsukaSKD07.bib},
bibsource = {dblp computer science bibliography, https://dblp.org}
}
@inproceedings{DBLP:conf/aiprf/HuangZM07,
author = {Lin Huang and
Hanqi Zhuang and
Salvatore D. Morgera},
editor = {Dimitris A. Karras and
Chunping Li and
Zoran Majkic and
S. R. Mahadeva Prasanna},
title = {Audio-visual Based Person Recognition with Fusion at Feature Level},
booktitle = {International Conference on Artificial Intelligence and Pattern Recognition,
AIPR-07, Orlando, Florida, USA, July 9-12, 2007},
pages = {249--254},
publisher = {{ISRST}},
year = {2007},
timestamp = {Wed, 07 Aug 2019 01:00:00 +0200},
biburl = {https://dblp.org/rec/conf/aiprf/HuangZM07.bib},
bibsource = {dblp computer science bibliography, https://dblp.org}
}
@inproceedings{DBLP:conf/avsp/GanMY07,
author = {Tian Gan and
Wolfgang Menzel and
Shiqiang Yang},
editor = {Jean Vroomen and
Marc Swerts and
Emiel Krahmer},
title = {An audio-visual speech recognition framework based on articulatory
features},
booktitle = {Auditory-Visual Speech Processing 2007, {AVSP} 2007, Hilvarenbeek,
The Netherlands, August 31 - September 3, 2007},
pages = {1},
publisher = {{ISCA}},
year = {2007},
url = {http://www.isca-speech.org/archive\_open/avsp07/av07\_P01.html},
timestamp = {Wed, 10 Feb 2021 22:00:49 +0100},
biburl = {https://dblp.org/rec/conf/avsp/GanMY07.bib},
bibsource = {dblp computer science bibliography, https://dblp.org}
}
@inproceedings{DBLP:conf/avss/KlausnerTLER07,
author = {Andreas Klausner and
Allan Tengg and
Christian Leistner and
Stefan Erb and
Bernhard Rinner},
title = {An audio-visual sensor fusion approach for feature based vehicle identification},
booktitle = {Fourth {IEEE} International Conference on Advanced Video and Signal
Based Surveillance, {AVSS} 2007, 5-7 September, 2007, Queen Mary,
University of London, London, United Kingdom},
pages = {111--116},
publisher = {{IEEE} Computer Society},
year = {2007},
url = {https://doi.org/10.1109/AVSS.2007.4425295},
doi = {10.1109/AVSS.2007.4425295},
timestamp = {Thu, 23 Mar 2023 00:00:00 +0100},
biburl = {https://dblp.org/rec/conf/avss/KlausnerTLER07.bib},
bibsource = {dblp computer science bibliography, https://dblp.org}
}
@inproceedings{DBLP:conf/clear/BernardinGS07,
author = {Keni Bernardin and
Tobias Gehrig and
Rainer Stiefelhagen},
editor = {Rainer Stiefelhagen and
Rachel Bowers and
Jonathan G. Fiscus},
title = {Multi-level Particle Filter Fusion of Features and Cues for Audio-Visual
Person Tracking},
booktitle = {Multimodal Technologies for Perception of Humans, International Evaluation
Workshops {CLEAR} 2007 and {RT} 2007, Baltimore, MD, USA, May 8-11,
2007, Revised Selected Papers},
series = {Lecture Notes in Computer Science},
volume = {4625},
pages = {70--81},
publisher = {Springer},
year = {2007},
url = {https://doi.org/10.1007/978-3-540-68585-2\_5},
doi = {10.1007/978-3-540-68585-2\_5},
timestamp = {Tue, 14 May 2019 10:00:42 +0200},
biburl = {https://dblp.org/rec/conf/clear/BernardinGS07.bib},
bibsource = {dblp computer science bibliography, https://dblp.org}
}
@inproceedings{DBLP:conf/eusipco/CarbonerasGT07,
author = {Andres Valles Carboneras and
Mihai Gurban and
Jean{-}Philippe Thiran},
title = {Low-dimensional motion features for audio-visual speech recognition},
booktitle = {15th European Signal Processing Conference, {EUSIPCO} 2007, Poznan,
Poland, September 3-7, 2007},
pages = {297--301},
publisher = {{IEEE}},
year = {2007},
url = {https://ieeexplore.ieee.org/document/7098812/},
timestamp = {Mon, 09 Aug 2021 01:00:00 +0200},
biburl = {https://dblp.org/rec/conf/eusipco/CarbonerasGT07.bib},
bibsource = {dblp computer science bibliography, https://dblp.org}
}
@inproceedings{DBLP:conf/icassp/LivescuCHKBBKLYBDWFMS07,
author = {Karen Livescu and
{\"{O}}zg{\"{u}}r {\c{C}}etin and
Mark Hasegawa{-}Johnson and
Simon King and
Chris D. Bartels and
Nash M. Borges and
Arthur Kantor and
Partha Lal and
Lisa Yung and
Ari Bezman and
Stephen Dawson{-}Haggerty and
Bronwyn Woods and
Joe Frankel and
Mathew Magimai{-}Doss and
Kate Saenko},
title = {Articulatory Feature-Based Methods for Acoustic and Audio-Visual Speech
Recognition: Summary from the 2006 {JHU} Summer workshop},
booktitle = {Proceedings of the {IEEE} International Conference on Acoustics, Speech,
and Signal Processing, {ICASSP} 2007, Honolulu, Hawaii, USA, April
15-20, 2007},
pages = {621--624},
publisher = {{IEEE}},
year = {2007},
url = {https://doi.org/10.1109/ICASSP.2007.366989},
doi = {10.1109/ICASSP.2007.366989},
timestamp = {Mon, 29 Jan 2024 00:00:00 +0100},
biburl = {https://dblp.org/rec/conf/icassp/LivescuCHKBBKLYBDWFMS07.bib},
bibsource = {dblp computer science bibliography, https://dblp.org}
}
@inproceedings{DBLP:conf/interspeech/DendaNY07,
author = {Yuki Denda and
Takanobu Nishiura and
Yoichi Yamashita},
title = {Omnidirectional audio-visual talker localizer with dynamic feature
fusion based on validity and reliability criteria},
booktitle = {{INTERSPEECH} 2007, 8th Annual Conference of the International Speech
Communication Association, Antwerp, Belgium, August 27-31, 2007},
pages = {726--729},
publisher = {{ISCA}},
year = {2007},
url = {https://doi.org/10.21437/Interspeech.2007-300},
doi = {10.21437/INTERSPEECH.2007-300},
timestamp = {Fri, 23 Jun 2023 01:00:00 +0200},
biburl = {https://dblp.org/rec/conf/interspeech/DendaNY07.bib},
bibsource = {dblp computer science bibliography, https://dblp.org}
}
@inproceedings{DBLP:conf/interspeech/WuZ07,
author = {Guanyong Wu and
Jie Zhu},
title = {An extension 2DPCA based visual feature extraction method for audio-visual
speech recognition},
booktitle = {{INTERSPEECH} 2007, 8th Annual Conference of the International Speech
Communication Association, Antwerp, Belgium, August 27-31, 2007},
pages = {714--717},
publisher = {{ISCA}},
year = {2007},
url = {https://doi.org/10.21437/Interspeech.2007-297},
doi = {10.21437/INTERSPEECH.2007-297},
timestamp = {Fri, 23 Jun 2023 01:00:00 +0200},
biburl = {https://dblp.org/rec/conf/interspeech/WuZ07.bib},
bibsource = {dblp computer science bibliography, https://dblp.org}
}
@inproceedings{DBLP:conf/iros/KoiwaNI07,
author = {Tomoaki Koiwa and
Kazuhiro Nakadai and
Jun{-}ichi Imura},
title = {Coarse speech recognition by audio-visual integration based on missing
feature theory},
booktitle = {2007 {IEEE/RSJ} International Conference on Intelligent Robots and
Systems, October 29 - November 2, 2007, Sheraton Hotel and Marina,
San Diego, California, {USA}},
pages = {1751--1756},
publisher = {{IEEE}},
year = {2007},
url = {https://doi.org/10.1109/IROS.2007.4399300},
doi = {10.1109/IROS.2007.4399300},
timestamp = {Fri, 27 Mar 2020 00:00:00 +0100},
biburl = {https://dblp.org/rec/conf/iros/KoiwaNI07.bib},
bibsource = {dblp computer science bibliography, https://dblp.org}
}
@inproceedings{DBLP:conf/mmsp/DrugmanGT07,
author = {Thomas Drugman and
Mihai Gurban and
Jean{-}Philippe Thiran},
title = {Relevant Feature Selection for Audio-Visual Speech Recognition},
booktitle = {{IEEE} 9th Workshop on Multimedia Signal Processing, {MMSP} 2007,
Chania, Crete, Greece, October 1-3, 2007},
pages = {179--182},
publisher = {{IEEE}},
year = {2007},
url = {https://doi.org/10.1109/MMSP.2007.4412847},
doi = {10.1109/MMSP.2007.4412847},
timestamp = {Wed, 16 Oct 2019 14:14:49 +0200},
biburl = {https://dblp.org/rec/conf/mmsp/DrugmanGT07.bib},
bibsource = {dblp computer science bibliography, https://dblp.org}
}
@inproceedings{DBLP:conf/premi/ChettyW07,
author = {Girija Chetty and
Michael Wagner},
editor = {Ashish Ghosh and
Rajat K. De and
Sankar K. Pal},
title = {Audio Visual Speaker Verification Based on Hybrid Fusion of Cross
Modal Features},
booktitle = {Pattern Recognition and Machine Intelligence, Second International
Conference, PReMI 2007, Kolkata, India, December 18-22, 2007, Proceedings},
series = {Lecture Notes in Computer Science},
volume = {4815},
pages = {469--478},
publisher = {Springer},
year = {2007},
url = {https://doi.org/10.1007/978-3-540-77046-6\_58},
doi = {10.1007/978-3-540-77046-6\_58},
timestamp = {Tue, 14 May 2019 10:00:41 +0200},
biburl = {https://dblp.org/rec/conf/premi/ChettyW07.bib},
bibsource = {dblp computer science bibliography, https://dblp.org}
}
@inproceedings{DBLP:conf/icb/WuCM06,
author = {Zhiyong Wu and
Lianhong Cai and
Helen M. Meng},
editor = {David Zhang and
Anil K. Jain},
title = {Multi-level Fusion of Audio and Visual Features for Speaker Identification},
booktitle = {Advances in Biometrics, International Conference, {ICB} 2006, Hong
Kong, China, January 5-7, 2006, Proceedings},
series = {Lecture Notes in Computer Science},
volume = {3832},
pages = {493--499},
publisher = {Springer},
year = {2006},
url = {https://doi.org/10.1007/11608288\_66},
doi = {10.1007/11608288\_66},
timestamp = {Sat, 08 May 2021 01:00:00 +0200},
biburl = {https://dblp.org/rec/conf/icb/WuCM06.bib},
bibsource = {dblp computer science bibliography, https://dblp.org}
}
@inproceedings{DBLP:conf/interspeech/AlmajaiMD06,
author = {Ibrahim Almajai and
Ben Milner and
Jonathan Darch},
title = {Analysis of correlation between audio and visual speech features for
clean audio feature prediction in noise},
booktitle = {{INTERSPEECH} 2006 - ICSLP, Ninth International Conference on Spoken
Language Processing, Pittsburgh, PA, USA, September 17-21, 2006},
publisher = {{ISCA}},
year = {2006},
url = {https://doi.org/10.21437/Interspeech.2006-619},
doi = {10.21437/INTERSPEECH.2006-619},
timestamp = {Thu, 22 Jun 2023 16:42:16 +0200},
biburl = {https://dblp.org/rec/conf/interspeech/AlmajaiMD06.bib},
bibsource = {dblp computer science bibliography, https://dblp.org}
}
@inproceedings{DBLP:conf/mlmi/Al-HamesHSR06,
author = {Marc A. Al{-}Hames and
Benedikt H{\"{o}}rnler and
Christoph Scheuermann and
Gerhard Rigoll},
editor = {Steve Renals and
Samy Bengio and
Jonathan G. Fiscus},
title = {Using Audio, Visual, and Lexical Features in a Multi-modal Virtual
Meeting Director},
booktitle = {Machine Learning for Multimodal Interaction, Third International Workshop,
{MLMI} 2006, Bethesda, MD, USA, May 1-4, 2006, Revised Selected Papers},
series = {Lecture Notes in Computer Science},
volume = {4299},
pages = {63--74},
publisher = {Springer},
year = {2006},
url = {https://doi.org/10.1007/11965152\_6},
doi = {10.1007/11965152\_6},
timestamp = {Tue, 31 Aug 2021 01:00:00 +0200},
biburl = {https://dblp.org/rec/conf/mlmi/Al-HamesHSR06.bib},
bibsource = {dblp computer science bibliography, https://dblp.org}
}
@inproceedings{DBLP:conf/mmsp/KepesiNPGGJ06,
author = {Mari{\'{a}}n K{\'{e}}pesi and
Michael Neffe and
Tuan Van Pham and
Michael Grabner and
Helmut Grabner and
Andreas Juffinger},
title = {Audio-Visual Feature Extraction for Semi-Automatic Annotation of Meetings},
booktitle = {{IEEE} 8th Workshop on Multimedia Signal Processing, {MMSP} 2006,
Victoria, BC, Canada, October 3-6, 2006},
pages = {207--211},
publisher = {{IEEE}},
year = {2006},
url = {https://doi.org/10.1109/MMSP.2006.285298},
doi = {10.1109/MMSP.2006.285298},
timestamp = {Wed, 16 Oct 2019 14:14:49 +0200},
biburl = {https://dblp.org/rec/conf/mmsp/KepesiNPGGJ06.bib},
bibsource = {dblp computer science bibliography, https://dblp.org}
}
@article{DBLP:journals/tcsv/SadlierO05,
author = {David A. Sadlier and
Noel E. O'Connor},
title = {Event detection in field sports video using audio-visual features
and a support vector Machine},
journal = {{IEEE} Trans. Circuits Syst. Video Technol.},
volume = {15},
number = {10},
pages = {1225--1233},
year = {2005},
url = {https://doi.org/10.1109/TCSVT.2005.854237},
doi = {10.1109/TCSVT.2005.854237},
timestamp = {Tue, 25 Aug 2020 01:00:00 +0200},
biburl = {https://dblp.org/rec/journals/tcsv/SadlierO05.bib},
bibsource = {dblp computer science bibliography, https://dblp.org}
}
@inproceedings{DBLP:conf/eusipco/SarginEYT05,
author = {Mehmet Emre Sargin and
Engin Erzin and
Y{\"{u}}cel Yemez and
A. Murat Tekalp},
title = {Lip feature extraction based on audio-visual correlation},
booktitle = {13th European Signal Processing Conference, {EUSIPCO} 2005, Antalya,
Turkey, September 4-8, 2005},
pages = {1--4},
publisher = {{IEEE}},
year = {2005},
url = {https://ieeexplore.ieee.org/document/7077967/},
timestamp = {Mon, 09 Aug 2021 01:00:00 +0200},
biburl = {https://dblp.org/rec/conf/eusipco/SarginEYT05.bib},
bibsource = {dblp computer science bibliography, https://dblp.org}
}
@inproceedings{DBLP:conf/icassp/ChangMC05,
author = {Shih{-}Fu Chang and
R. Manmatha and
Tat{-}Seng Chua},
title = {Combining text and audio-visual features in video indexing},
booktitle = {2005 {IEEE} International Conference on Acoustics, Speech, and Signal
Processing, {ICASSP} '05, Philadelphia, Pennsylvania, USA, March 18-23,
2005},
pages = {1005--1008},
publisher = {{IEEE}},
year = {2005},
url = {https://doi.org/10.1109/ICASSP.2005.1416476},
doi = {10.1109/ICASSP.2005.1416476},
timestamp = {Mon, 22 Jun 2020 01:00:00 +0200},
biburl = {https://dblp.org/rec/conf/icassp/ChangMC05.bib},
bibsource = {dblp computer science bibliography, https://dblp.org}
}
@inproceedings{DBLP:conf/icmcs/HuangMV05,
author = {Jing Huang and
Etienne Marcheret and
Karthik Visweswariah},
title = {Rapid Feature Space Speaker Adaptation for Multi-Stream HMM-Based
Audio-Visual Speech Recognition},
booktitle = {Proceedings of the 2005 {IEEE} International Conference on Multimedia
and Expo, {ICME} 2005, July 6-9, 2005, Amsterdam, The Netherlands},
pages = {338--341},
publisher = {{IEEE} Computer Society},
year = {2005},
url = {https://doi.org/10.1109/ICME.2005.1521429},
doi = {10.1109/ICME.2005.1521429},
timestamp = {Fri, 24 Mar 2023 00:00:00 +0100},
biburl = {https://dblp.org/rec/conf/icmcs/HuangMV05.bib},
bibsource = {dblp computer science bibliography, https://dblp.org}
}
@inproceedings{DBLP:conf/icnc/KimRK05,
author = {Myung{-}Won Kim and
Joung Woo Ryu and
Eun Ju Kim},
editor = {Lipo Wang and
Ke Chen and
Yew{-}Soon Ong},
title = {Speech Recognition by Integrating Audio, Visual and Contextual Features
Based on Neural Networks},
booktitle = {Advances in Natural Computation, First International Conference, {ICNC}
2005, Changsha, China, August 27-29, 2005, Proceedings, Part {II}},
series = {Lecture Notes in Computer Science},
volume = {3611},
pages = {155--164},
publisher = {Springer},
year = {2005},
url = {https://doi.org/10.1007/11539117\_25},
doi = {10.1007/11539117\_25},
timestamp = {Sun, 02 Jun 2019 21:14:27 +0200},
biburl = {https://dblp.org/rec/conf/icnc/KimRK05.bib},
bibsource = {dblp computer science bibliography, https://dblp.org}
}
@inproceedings{DBLP:conf/interspeech/HuangP05,
author = {Jing Huang and
Daniel Povey},
title = {Discriminatively trained features using fMPE for multi-stream audio-visual
speech recognition},
booktitle = {{INTERSPEECH} 2005 - Eurospeech, 9th European Conference on Speech
Communication and Technology, Lisbon, Portugal, September 4-8, 2005},
pages = {777--780},
publisher = {{ISCA}},
year = {2005},
url = {https://doi.org/10.21437/Interspeech.2005-361},
doi = {10.21437/INTERSPEECH.2005-361},
timestamp = {Thu, 22 Jun 2023 16:42:16 +0200},
biburl = {https://dblp.org/rec/conf/interspeech/HuangP05.bib},
bibsource = {dblp computer science bibliography, https://dblp.org}
}
@inproceedings{DBLP:conf/interspeech/HuangV05,
author = {Jing Huang and
Karthik Visweswariah},
title = {Improving lip-reading with feature space transforms for multi-stream
audio-visual speech recognition},
booktitle = {{INTERSPEECH} 2005 - Eurospeech, 9th European Conference on Speech
Communication and Technology, Lisbon, Portugal, September 4-8, 2005},
pages = {1221--1224},
publisher = {{ISCA}},
year = {2005},
url = {https://doi.org/10.21437/Interspeech.2005-373},
doi = {10.21437/INTERSPEECH.2005-373},
timestamp = {Thu, 22 Jun 2023 01:00:00 +0200},
biburl = {https://dblp.org/rec/conf/interspeech/HuangV05.bib},
bibsource = {dblp computer science bibliography, https://dblp.org}
}
@inproceedings{DBLP:conf/isspa/LewisP05,
author = {Trent W. Lewis and
David M. W. Powers},
title = {Distinctive feature fusion for improved audio-visual phoneme recognition},
booktitle = {Proceedings of the Eighth International Symposium on Signal Processing
and Its Applications, {ISSPA} 2005, 28-31 August 2005, Sydney, Australia},
pages = {62--65},
publisher = {{IEEE}},
year = {2005},
url = {https://doi.org/10.1109/ISSPA.2005.1580196},
doi = {10.1109/ISSPA.2005.1580196},
timestamp = {Wed, 16 Oct 2019 14:14:56 +0200},
biburl = {https://dblp.org/rec/conf/isspa/LewisP05.bib},
bibsource = {dblp computer science bibliography, https://dblp.org}
}
@article{DBLP:journals/tsmc/KaynakZCSJC04,
author = {Mustafa Nazmi Kaynak and
Qi Zhi and
Adrian David Cheok and
Kuntal Sengupta and
Jian Zhang and
Chi Chung Ko},
title = {Analysis of lip geometric features for audio-visual speech recognition},
journal = {{IEEE} Trans. Syst. Man Cybern. Part {A}},
volume = {34},
number = {4},
pages = {564--570},
year = {2004},
url = {https://doi.org/10.1109/TSMCA.2004.826274},
doi = {10.1109/TSMCA.2004.826274},
timestamp = {Mon, 25 May 2020 01:00:00 +0200},
biburl = {https://dblp.org/rec/journals/tsmc/KaynakZCSJC04.bib},
bibsource = {dblp computer science bibliography, https://dblp.org}
}
@inproceedings{DBLP:conf/icassp/AleksicK04,
author = {Petar S. Aleksic and
Aggelos K. Katsaggelos},
title = {Comparison of low- and high-level visual features for audio-visual
continuous automatic speech recognition},
booktitle = {2004 {IEEE} International Conference on Acoustics, Speech, and Signal
Processing, {ICASSP} 2004, Montreal, Quebec, Canada, May 17-21, 2004},
pages = {917--920},
publisher = {{IEEE}},
year = {2004},
url = {https://doi.org/10.1109/ICASSP.2004.1327261},
doi = {10.1109/ICASSP.2004.1327261},
timestamp = {Mon, 22 Jun 2020 01:00:00 +0200},
biburl = {https://dblp.org/rec/conf/icassp/AleksicK04.bib},
bibsource = {dblp computer science bibliography, https://dblp.org}
}
@inproceedings{DBLP:conf/icassp/JiangPNIN04,
author = {Jintao Jiang and
Gerasimos Potamianos and
Harriet J. Nock and
Giridharan Iyengar and
Chalapathy Neti},
title = {Improved face and feature finding for audio-visual speech recognition
in visually challenging environments},
booktitle = {2004 {IEEE} International Conference on Acoustics, Speech, and Signal
Processing, {ICASSP} 2004, Montreal, Quebec, Canada, May 17-21, 2004},
pages = {873--876},
publisher = {{IEEE}},
year = {2004},
url = {https://doi.org/10.1109/ICASSP.2004.1327250},
doi = {10.1109/ICASSP.2004.1327250},
timestamp = {Mon, 22 Jun 2020 01:00:00 +0200},
biburl = {https://dblp.org/rec/conf/icassp/JiangPNIN04.bib},
bibsource = {dblp computer science bibliography, https://dblp.org}
}
@inproceedings{DBLP:conf/mir/XuC04,
author = {Huaxin Xu and
Tat{-}Seng Chua},
editor = {Michael S. Lew and
Nicu Sebe and
Chabane Djeraba},
title = {The fusion of audio-visual features and external knowledge for event
detection in team sports video},
booktitle = {Proceedings of the 6th {ACM} {SIGMM} International Workshop on Multimedia
Information Retrieval, {MIR} 2004, October 15-16, 2004, New York,
NY, {USA}},
pages = {127--134},
publisher = {{ACM}},
year = {2004},
url = {https://doi.org/10.1145/1026711.1026733},
doi = {10.1145/1026711.1026733},
timestamp = {Tue, 06 Nov 2018 00:00:00 +0100},
biburl = {https://dblp.org/rec/conf/mir/XuC04.bib},
bibsource = {dblp computer science bibliography, https://dblp.org}
}
@inproceedings{DBLP:conf/webi/Liu04,
author = {Huayong Liu},
title = {Content-Based {TV} Sports Video Retrieval Based on Audio-Visual Features
and Text Information},
booktitle = {2004 {IEEE/WIC/ACM} International Conference on Web Intelligence {(WI}
2004), 20-24 September 2004, Beijing, China},
pages = {481--484},
publisher = {{IEEE} Computer Society},
year = {2004},
url = {https://doi.org/10.1109/WI.2004.10107},
doi = {10.1109/WI.2004.10107},
timestamp = {Thu, 23 Mar 2023 14:30:18 +0100},
biburl = {https://dblp.org/rec/conf/webi/Liu04.bib},
bibsource = {dblp computer science bibliography, https://dblp.org}
}
@article{DBLP:journals/jvcir/WangDVCS03,
author = {Hualu Wang and
Ajay Divakaran and
Anthony Vetro and
Shih{-}Fu Chang and
Huifang Sun},
title = {Survey of compressed-domain features used in audio-visual indexing
and analysis},
journal = {J. Vis. Commun. Image Represent.},
volume = {14},
number = {2},
pages = {150--183},
year = {2003},
url = {https://doi.org/10.1016/S1047-3203(03)00019-1},
doi = {10.1016/S1047-3203(03)00019-1},
timestamp = {Sat, 22 Feb 2020 00:00:00 +0100},
biburl = {https://dblp.org/rec/journals/jvcir/WangDVCS03.bib},
bibsource = {dblp computer science bibliography, https://dblp.org}
}
@inproceedings{DBLP:conf/avbpa/FoxR03,
author = {Niall A. Fox and
Richard B. Reilly},
editor = {Josef Kittler and
Mark S. Nixon},
title = {Audio-Visual Speaker Identification Based on the Use of Dynamic Audio
and Visual Features},
booktitle = {Audio-and Video-Based Biometrie Person Authentication, 4th International
Conference, {AVBPA} 2003, Guildford, UK, June 9-11, 2003 Proceedings},
series = {Lecture Notes in Computer Science},
volume = {2688},
pages = {743--751},
publisher = {Springer},
year = {2003},
url = {https://doi.org/10.1007/3-540-44887-X\_86},
doi = {10.1007/3-540-44887-X\_86},
timestamp = {Mon, 15 Jun 2020 01:00:00 +0200},
biburl = {https://dblp.org/rec/conf/avbpa/FoxR03.bib},
bibsource = {dblp computer science bibliography, https://dblp.org}
}
@inproceedings{DBLP:conf/icip/SuganoINY03,
author = {Masaru Sugano and
Roger Isaksson and
Yasuyuki Nakajima and
Hiromasa Yanagihara},
title = {Shot genre classification using compressed audio-visual features},
booktitle = {Proceedings of the 2003 International Conference on Image Processing,
{ICIP} 2003, Barcelona, Catalonia, Spain, September 14-18, 2003},
pages = {17--20},
publisher = {{IEEE}},
year = {2003},
url = {https://doi.org/10.1109/ICIP.2003.1246605},
doi = {10.1109/ICIP.2003.1246605},
timestamp = {Tue, 02 Jan 2024 00:00:00 +0100},
biburl = {https://dblp.org/rec/conf/icip/SuganoINY03.bib},
bibsource = {dblp computer science bibliography, https://dblp.org}
}
@inproceedings{DBLP:conf/spieVIP/LeeYK03,
author = {Shih{-}Hung Lee and
Chia{-}Hung Yeh and
C.{-}C. Jay Kuo},
editor = {Zia{-}ur Rahman and
Robert A. Schowengerdt and
Stephen E. Reichenbach},
title = {Robust {TV} commercial detection based on audiovisual features},
booktitle = {Visual Information Processing XII, Orlando, FL, USA, April 21, 2003},
series = {{SPIE} Proceedings},
volume = {5108},
pages = {147--158},
publisher = {{SPIE}},
year = {2003},
url = {https://doi.org/10.1117/12.486775},
doi = {10.1117/12.486775},
timestamp = {Fri, 06 May 2022 13:45:23 +0200},
biburl = {https://dblp.org/rec/conf/spieVIP/LeeYK03.bib},
bibsource = {dblp computer science bibliography, https://dblp.org}
}
@article{DBLP:journals/ejasp/AleksicWWK02,
author = {Petar S. Aleksic and
Jay J. Williams and
Zhilin Wu and
Aggelos K. Katsaggelos},
title = {Audio-Visual Speech Recognition Using {MPEG-4} Compliant Visual Features},
journal = {{EURASIP} J. Adv. Signal Process.},
volume = {2002},
number = {11},
pages = {1213--1227},
year = {2002},
url = {https://doi.org/10.1155/S1110865702206162},
doi = {10.1155/S1110865702206162},
timestamp = {Tue, 21 Mar 2023 00:00:00 +0100},
biburl = {https://dblp.org/rec/journals/ejasp/AleksicWWK02.bib},
bibsource = {dblp computer science bibliography, https://dblp.org}
}
@inproceedings{DBLP:conf/civr/KimCKK02,
author = {Kyungsu Kim and
Junho Choi and
Namjung Kim and
Pankoo Kim},
editor = {Michael S. Lew and
Nicu Sebe and
John P. Eakins},
title = {Extracting Semantic Information from Basketball Video Based on Audio-Visual
Features},
booktitle = {Image and Video Retrieval, International Conference, {CIVR} 2002,
London, UK, July 18-19, 2002, Proceedings},
series = {Lecture Notes in Computer Science},
volume = {2383},
pages = {278--288},
publisher = {Springer},
year = {2002},
url = {https://doi.org/10.1007/3-540-45479-9\_30},
doi = {10.1007/3-540-45479-9\_30},
timestamp = {Wed, 16 Jun 2021 01:00:00 +0200},
biburl = {https://dblp.org/rec/conf/civr/KimCKK02.bib},
bibsource = {dblp computer science bibliography, https://dblp.org}
}
@inproceedings{DBLP:conf/icassp/GoeckePN02,
author = {Roland Goecke and
Gerasimos Potamianos and
Chalapathy Neti},
title = {Noisy audio feature enhancement using audio-visual speech data},
booktitle = {Proceedings of the {IEEE} International Conference on Acoustics, Speech,
and Signal Processing, {ICASSP} 2002, May 13-17 2002, Orlando, Florida,
{USA}},
pages = {2025--2028},
publisher = {{IEEE}},
year = {2002},
url = {https://doi.org/10.1109/ICASSP.2002.5745030},
doi = {10.1109/ICASSP.2002.5745030},
timestamp = {Wed, 16 Oct 2019 14:14:52 +0200},
biburl = {https://dblp.org/rec/conf/icassp/GoeckePN02.bib},
bibsource = {dblp computer science bibliography, https://dblp.org}
}
@inproceedings{DBLP:conf/icip/AleksicWWK02,
author = {Petar S. Aleksic and
Jay J. Williams and
Zhilin Wu and
Aggelos K. Katsaggelos},
title = {Audio-visual continuous speech recognition using {MPEG-4} compliant
visual features},
booktitle = {Proceedings of the 2002 International Conference on Image Processing,
{ICIP} 2002, Rochester, New York, USA, September 22-25, 2002},
pages = {960--963},
publisher = {{IEEE}},
year = {2002},
url = {https://doi.org/10.1109/ICIP.2002.1038187},
doi = {10.1109/ICIP.2002.1038187},
timestamp = {Wed, 16 Oct 2019 14:14:52 +0200},
biburl = {https://dblp.org/rec/conf/icip/AleksicWWK02.bib},
bibsource = {dblp computer science bibliography, https://dblp.org}
}
@inproceedings{DBLP:conf/icpr/RasheedS02,
author = {Zeeshan Rasheed and
Mubarak Shah},
title = {Movie Genre Classification By Exploiting Audio-Visual Features Of
Previews},
booktitle = {16th International Conference on Pattern Recognition, {ICPR} 2002,
Quebec, Canada, August 11-15, 2002},
pages = {1086--1089},
publisher = {{IEEE} Computer Society},
year = {2002},
url = {https://doi.org/10.1109/ICPR.2002.1048494},
doi = {10.1109/ICPR.2002.1048494},
timestamp = {Fri, 24 Mar 2023 00:00:00 +0100},
biburl = {https://dblp.org/rec/conf/icpr/RasheedS02.bib},
bibsource = {dblp computer science bibliography, https://dblp.org}
}
@inproceedings{DBLP:conf/interspeech/HeckmannKSB02,
author = {Martin Heckmann and
Kristian Kroschel and
Christophe Savariaux and
Fr{\'{e}}d{\'{e}}ric Berthommier},
editor = {John H. L. Hansen and
Bryan L. Pellom},
title = {DCT-based video features for audio-visual speech recognition},
booktitle = {7th International Conference on Spoken Language Processing, {ICSLP2002}
- {INTERSPEECH} 2002, Denver, Colorado, USA, September 16-20, 2002},
pages = {1925--1928},
publisher = {{ISCA}},
year = {2002},
url = {https://doi.org/10.21437/ICSLP.2002-434},
doi = {10.21437/ICSLP.2002-434},
timestamp = {Thu, 22 Jun 2023 16:42:18 +0200},
biburl = {https://dblp.org/rec/conf/interspeech/HeckmannKSB02.bib},
bibsource = {dblp computer science bibliography, https://dblp.org}
}
@phdthesis{DBLP:phd/us/Naphade01,
author = {Milind R. Naphade},
title = {A Probablistic Framework for Mapping Audio-Visual Features to High-Level
Semantics in Terms of Concepts and Context},
school = {University of Illinois Urbana-Champaign, {USA}},
year = {2001},
url = {https://hdl.handle.net/2142/80716},
timestamp = {Thu, 07 Sep 2023 01:00:00 +0200},
biburl = {https://dblp.org/rec/phd/us/Naphade01.bib},
bibsource = {dblp computer science bibliography, https://dblp.org}
}
@inproceedings{DBLP:conf/icassp/PotamianosLN01,
author = {Gerasimos Potamianos and
Juergen Luettin and
Chalapathy Neti},
title = {Hierarchical discriminant features for audio-visual {LVCSR}},
booktitle = {{IEEE} International Conference on Acoustics, Speech, and Signal Processing,
{ICASSP} 2001, 7-11 May, 2001, Salt Palace Convention Center, Salt
Lake City, Utah, USA, Proceedings},
pages = {165--168},
publisher = {{IEEE}},
year = {2001},
url = {https://doi.org/10.1109/ICASSP.2001.940793},
doi = {10.1109/ICASSP.2001.940793},
timestamp = {Thu, 23 Mar 2023 00:00:00 +0100},
biburl = {https://dblp.org/rec/conf/icassp/PotamianosLN01.bib},
bibsource = {dblp computer science bibliography, https://dblp.org}
}
@inproceedings{DBLP:conf/icmcs/MatthewsPNL01,
author = {Iain A. Matthews and
Gerasimos Potamianos and
Chalapathy Neti and
Juergen Luettin},
title = {A Comparison Of Model And Transform-Based Visual Features For Audio-Visual
{LVCSR}},
booktitle = {Proceedings of the 2001 {IEEE} International Conference on Multimedia
and Expo, {ICME} 2001, August 22-25, 2001, Tokyo, Japan},
publisher = {{IEEE} Computer Society},
year = {2001},
url = {https://doi.org/10.1109/ICME.2001.1237849},
doi = {10.1109/ICME.2001.1237849},
timestamp = {Fri, 24 Mar 2023 00:00:00 +0100},
biburl = {https://dblp.org/rec/conf/icmcs/MatthewsPNL01.bib},
bibsource = {dblp computer science bibliography, https://dblp.org}
}
@inproceedings{DBLP:conf/icmcs/YoshitakaM01,
author = {Atsuo Yoshitaka and
Masato Miyake},
title = {Scene Detection by Audio-Visual Features},
booktitle = {Proceedings of the 2001 {IEEE} International Conference on Multimedia
and Expo, {ICME} 2001, August 22-25, 2001, Tokyo, Japan},
publisher = {{IEEE} Computer Society},
year = {2001},
url = {https://doi.org/10.1109/ICME.2001.1237652},
doi = {10.1109/ICME.2001.1237652},
timestamp = {Fri, 24 Mar 2023 00:00:00 +0100},
biburl = {https://dblp.org/rec/conf/icmcs/YoshitakaM01.bib},
bibsource = {dblp computer science bibliography, https://dblp.org}
}
@inproceedings{DBLP:conf/mmsp/Chan01,
author = {Michael T. Chan},
editor = {Jean{-}Luc Dugelay and
Kenneth Rose},
title = {HMM-based audio-visual speech recognition integrating geometric and
appearance-based visual features},
booktitle = {Fourth {IEEE} Workshop on Multimedia Signal Processing, {MMSP} 2001,
Cannes, France, October 3-5, 2001},
pages = {9--14},
publisher = {{IEEE}},
year = {2001},
url = {https://doi.org/10.1109/MMSP.2001.962703},
doi = {10.1109/MMSP.2001.962703},
timestamp = {Wed, 16 Oct 2019 14:14:49 +0200},
biburl = {https://dblp.org/rec/conf/mmsp/Chan01.bib},
bibsource = {dblp computer science bibliography, https://dblp.org}
}
@inproceedings{DBLP:conf/spieSR/LiWSD01,
author = {Dongge Li and
Gang Wei and
Ishwar K. Sethi and
Nevenka Dimitrova},
editor = {Minerva M. Yeung and
Chung{-}Sheng Li and
Rainer Lienhart},
title = {Fusion of visual and audio features for person identification in real
video},
booktitle = {Storage and Retrieval for Media Databases 2001, San Jose, CA, USA,
January 24, 2001},
series = {{SPIE} Proceedings},
volume = {4315},
pages = {180--187},
publisher = {{SPIE}},
year = {2001},
url = {https://doi.org/10.1117/12.410926},
doi = {10.1117/12.410926},
timestamp = {Sun, 02 Oct 2022 01:00:00 +0200},
biburl = {https://dblp.org/rec/conf/spieSR/LiWSD01.bib},
bibsource = {dblp computer science bibliography, https://dblp.org}
}
@article{DBLP:journals/taslp/WatanabeTN00,
author = {Akira Watanabe and
Shingo Tomishige and
Masahiro Nakatake},
title = {Speech visualization by integrating features for the hearing impaired},
journal = {{IEEE} Trans. Speech Audio Process.},
volume = {8},
number = {4},
pages = {454--466},
year = {2000},
url = {https://doi.org/10.1109/89.848226},
doi = {10.1109/89.848226},
timestamp = {Sun, 17 May 2020 01:00:00 +0200},
biburl = {https://dblp.org/rec/journals/taslp/WatanabeTN00.bib},
bibsource = {dblp computer science bibliography, https://dblp.org}
}
@inproceedings{DBLP:conf/icip/PanLH00,
author = {Hao Pan and
Zhi{-}Pei Liang and
Thomas S. Huang},
title = {Fusing Audio and Visual Features of Speech},
booktitle = {Proceedings of the 2000 International Conference on Image Processing,
{ICIP} 2000, Vancouver, BC, Canada, September 10-13, 2000},
pages = {214--217},
publisher = {{IEEE}},
year = {2000},
url = {https://doi.org/10.1109/ICIP.2000.899333},
doi = {10.1109/ICIP.2000.899333},
timestamp = {Fri, 12 Jan 2024 00:00:00 +0100},
biburl = {https://dblp.org/rec/conf/icip/PanLH00.bib},
bibsource = {dblp computer science bibliography, https://dblp.org}
}
@inproceedings{DBLP:conf/icmcs/PanLH00,
author = {Hao Pan and
Zhi{-}Pei Liang and
Thomas S. Huang},
title = {A New Approach to Integrate Audio and Visual Features of Speech},
booktitle = {2000 {IEEE} International Conference on Multimedia and Expo, {ICME}
2000, New York, NY, USA, July 30 - August 2, 2000},
pages = {1093--1096},
publisher = {{IEEE} Computer Society},
year = {2000},
url = {https://doi.org/10.1109/ICME.2000.871551},
doi = {10.1109/ICME.2000.871551},
timestamp = {Fri, 12 Jan 2024 00:00:00 +0100},
biburl = {https://dblp.org/rec/conf/icmcs/PanLH00.bib},
bibsource = {dblp computer science bibliography, https://dblp.org}
}
@inproceedings{DBLP:conf/avsp/NiyogiPZ99,
author = {Partha Niyogi and
Eric Petajan and
Jialin Zhong},
editor = {Dominic W. Massaro},
title = {Feature based representation for audio-visual speech recognition},
booktitle = {Auditory-Visual Speech Processing, {AVSP} '99, Santa Cruz, CA, USA,
August 7-10, 1999},
pages = {16},
publisher = {{ISCA}},
year = {1999},
url = {http://www.isca-speech.org/archive\_open/avsp99/av99\_016.html},
timestamp = {Wed, 10 Feb 2021 22:00:51 +0100},
biburl = {https://dblp.org/rec/conf/avsp/NiyogiPZ99.bib},
bibsource = {dblp computer science bibliography, https://dblp.org}
}
@inproceedings{DBLP:conf/icip/Pavlovic98,
author = {Vladimir Pavlovic},
title = {Multimodal Tracking and Classification of Audio-Visual Features},
booktitle = {Proceedings of the 1998 {IEEE} International Conference on Image Processing,
ICIP-98, Chicago, Illinois, USA, October 4-7, 1998},
pages = {343--347},
publisher = {{IEEE} Computer Society},
year = {1998},
url = {https://doi.org/10.1109/ICIP.1998.723492},
doi = {10.1109/ICIP.1998.723492},
timestamp = {Fri, 24 Mar 2023 00:00:00 +0100},
biburl = {https://dblp.org/rec/conf/icip/Pavlovic98.bib},
bibsource = {dblp computer science bibliography, https://dblp.org}
}
a service of 
manage site settings
To protect your privacy, all features that rely on external API calls from your browser are turned off by default. You need to opt-in for them to become active. All settings here will be stored as cookies with your web browser. For more information see our F.A.Q.
retrieved on 2024-05-15 12:54 CEST from data curated by the dblp team
all metadata released as open data under CC0 1.0 license
see also: Terms of Use | Privacy Policy | Imprint
dblp was originally created in 1993 at:
since 2018, dblp has been operated and maintained by:
the dblp computer science bibliography is funded and supported by:
