![](https://dblp.uni-trier.de/img/logo.ua.320x120.png)
![](https://dblp.uni-trier.de/img/dropdown.dark.16x16.png)
![](https://dblp.uni-trier.de/img/peace.dark.16x16.png)
Остановите войну!
for scientists:
![search dblp search dblp](https://dblp.uni-trier.de/img/search.dark.16x16.png)
![search dblp](https://dblp.uni-trier.de/img/search.dark.16x16.png)
default search action
Search dblp for Publications
export results for "toc:db/conf/slt/slt2021.bht:"
@inproceedings{DBLP:conf/slt/0001KDZA21, author = {Shang{-}Wen Li and Jason Krone and Shuyan Dong and Yi Zhang and Yaser Al{-}Onaizan}, title = {Meta Learning to Classify Intent and Slot Labels with Noisy Few Shot Examples}, booktitle = {{IEEE} Spoken Language Technology Workshop, {SLT} 2021, Shenzhen, China, January 19-22, 2021}, pages = {1004--1011}, publisher = {{IEEE}}, year = {2021}, url = {https://doi.org/10.1109/SLT48900.2021.9383489}, doi = {10.1109/SLT48900.2021.9383489}, timestamp = {Mon, 05 Jun 2023 01:00:00 +0200}, biburl = {https://dblp.org/rec/conf/slt/0001KDZA21.bib}, bibsource = {dblp computer science bibliography, https://dblp.org} }
@inproceedings{DBLP:conf/slt/0002DLTL21, author = {Li Chai and Jun Du and Diyuan Liu and Yanhui Tu and Chin{-}Hui Lee}, title = {Acoustic Modeling for Multi-Array Conversational Speech Recognition in the Chime-6 Challenge}, booktitle = {{IEEE} Spoken Language Technology Workshop, {SLT} 2021, Shenzhen, China, January 19-22, 2021}, pages = {912--918}, publisher = {{IEEE}}, year = {2021}, url = {https://doi.org/10.1109/SLT48900.2021.9383628}, doi = {10.1109/SLT48900.2021.9383628}, timestamp = {Thu, 14 Sep 2023 01:00:00 +0200}, biburl = {https://dblp.org/rec/conf/slt/0002DLTL21.bib}, bibsource = {dblp computer science bibliography, https://dblp.org} }
@inproceedings{DBLP:conf/slt/0004HM21, author = {Yi Luo and Cong Han and Nima Mesgarani}, title = {Distortion-Controlled Training for end-to-end Reverberant Speech Separation with Auxiliary Autoencoding Loss}, booktitle = {{IEEE} Spoken Language Technology Workshop, {SLT} 2021, Shenzhen, China, January 19-22, 2021}, pages = {825--832}, publisher = {{IEEE}}, year = {2021}, url = {https://doi.org/10.1109/SLT48900.2021.9383494}, doi = {10.1109/SLT48900.2021.9383494}, timestamp = {Thu, 08 Apr 2021 01:00:00 +0200}, biburl = {https://dblp.org/rec/conf/slt/0004HM21.bib}, bibsource = {dblp computer science bibliography, https://dblp.org} }
@inproceedings{DBLP:conf/slt/0007KGLAG21, author = {Manoj Kumar and Varun Kumar and Hadrien Glaude and Cyprien de Lichy and Aman Alok and Rahul Gupta}, title = {Protoda: Efficient Transfer Learning for Few-Shot Intent Classification}, booktitle = {{IEEE} Spoken Language Technology Workshop, {SLT} 2021, Shenzhen, China, January 19-22, 2021}, pages = {966--972}, publisher = {{IEEE}}, year = {2021}, url = {https://doi.org/10.1109/SLT48900.2021.9383495}, doi = {10.1109/SLT48900.2021.9383495}, timestamp = {Thu, 06 Oct 2022 01:00:00 +0200}, biburl = {https://dblp.org/rec/conf/slt/0007KGLAG21.bib}, bibsource = {dblp computer science bibliography, https://dblp.org} }
@inproceedings{DBLP:conf/slt/AiLWYL21, author = {Yang Ai and Haoyu Li and Xin Wang and Junichi Yamagishi and Zhen{-}Hua Ling}, title = {Denoising-and-Dereverberation Hierarchical Neural Vocoder for Robust Waveform Generation}, booktitle = {{IEEE} Spoken Language Technology Workshop, {SLT} 2021, Shenzhen, China, January 19-22, 2021}, pages = {477--484}, publisher = {{IEEE}}, year = {2021}, url = {https://doi.org/10.1109/SLT48900.2021.9383611}, doi = {10.1109/SLT48900.2021.9383611}, timestamp = {Mon, 26 Jun 2023 01:00:00 +0200}, biburl = {https://dblp.org/rec/conf/slt/AiLWYL21.bib}, bibsource = {dblp computer science bibliography, https://dblp.org} }
@inproceedings{DBLP:conf/slt/BaharBN21, author = {Parnia Bahar and Christopher Brix and Hermann Ney}, title = {Two-Way Neural Machine Translation: {A} Proof of Concept for Bidirectional Translation Modeling Using a Two-Dimensional Grid}, booktitle = {{IEEE} Spoken Language Technology Workshop, {SLT} 2021, Shenzhen, China, January 19-22, 2021}, pages = {1065--1070}, publisher = {{IEEE}}, year = {2021}, url = {https://doi.org/10.1109/SLT48900.2021.9383589}, doi = {10.1109/SLT48900.2021.9383589}, timestamp = {Thu, 08 Apr 2021 01:00:00 +0200}, biburl = {https://dblp.org/rec/conf/slt/BaharBN21.bib}, bibsource = {dblp computer science bibliography, https://dblp.org} }
@inproceedings{DBLP:conf/slt/BaharBSN21, author = {Parnia Bahar and Tobias Bieschke and Ralf Schl{\"{u}}ter and Hermann Ney}, title = {Tight Integrated End-to-End Training for Cascaded Speech Translation}, booktitle = {{IEEE} Spoken Language Technology Workshop, {SLT} 2021, Shenzhen, China, January 19-22, 2021}, pages = {950--957}, publisher = {{IEEE}}, year = {2021}, url = {https://doi.org/10.1109/SLT48900.2021.9383462}, doi = {10.1109/SLT48900.2021.9383462}, timestamp = {Wed, 07 Dec 2022 00:00:00 +0100}, biburl = {https://dblp.org/rec/conf/slt/BaharBSN21.bib}, bibsource = {dblp computer science bibliography, https://dblp.org} }
@inproceedings{DBLP:conf/slt/BairdAMS21, author = {Alice Baird and Shahin Amiriparian and Manuel Milling and Bj{\"{o}}rn W. Schuller}, title = {Emotion Recognition in Public Speaking Scenarios Utilising An {LSTM-RNN} Approach with Attention}, booktitle = {{IEEE} Spoken Language Technology Workshop, {SLT} 2021, Shenzhen, China, January 19-22, 2021}, pages = {397--402}, publisher = {{IEEE}}, year = {2021}, url = {https://doi.org/10.1109/SLT48900.2021.9383542}, doi = {10.1109/SLT48900.2021.9383542}, timestamp = {Thu, 08 Apr 2021 01:00:00 +0200}, biburl = {https://dblp.org/rec/conf/slt/BairdAMS21.bib}, bibsource = {dblp computer science bibliography, https://dblp.org} }
@inproceedings{DBLP:conf/slt/CaiL21, author = {Danwei Cai and Ming Li}, title = {Embedding Aggregation for Far-Field Speaker Verification with Distributed Microphone Arrays}, booktitle = {{IEEE} Spoken Language Technology Workshop, {SLT} 2021, Shenzhen, China, January 19-22, 2021}, pages = {308--315}, publisher = {{IEEE}}, year = {2021}, url = {https://doi.org/10.1109/SLT48900.2021.9383501}, doi = {10.1109/SLT48900.2021.9383501}, timestamp = {Wed, 12 Oct 2022 01:00:00 +0200}, biburl = {https://dblp.org/rec/conf/slt/CaiL21.bib}, bibsource = {dblp computer science bibliography, https://dblp.org} }
@inproceedings{DBLP:conf/slt/CaoZFM21, author = {Songjun Cao and Yike Zhang and Xiaobing Feng and Long Ma}, title = {Improving Speech Recognition Accuracy of Local {POI} Using Geographical Models}, booktitle = {{IEEE} Spoken Language Technology Workshop, {SLT} 2021, Shenzhen, China, January 19-22, 2021}, pages = {180--185}, publisher = {{IEEE}}, year = {2021}, url = {https://doi.org/10.1109/SLT48900.2021.9383538}, doi = {10.1109/SLT48900.2021.9383538}, timestamp = {Thu, 08 Apr 2021 01:00:00 +0200}, biburl = {https://dblp.org/rec/conf/slt/CaoZFM21.bib}, bibsource = {dblp computer science bibliography, https://dblp.org} }
@inproceedings{DBLP:conf/slt/ChangL0HZH21, author = {Ting{-}Yun Chang and Yang Liu and Karthik Gopalakrishnan and Behnam Hedayatnia and Pei Zhou and Dilek Hakkani{-}T{\"{u}}r}, title = {Go Beyond Plain Fine-Tuning: Improving Pretrained Models for Social Commonsense}, booktitle = {{IEEE} Spoken Language Technology Workshop, {SLT} 2021, Shenzhen, China, January 19-22, 2021}, pages = {1028--1035}, publisher = {{IEEE}}, year = {2021}, url = {https://doi.org/10.1109/SLT48900.2021.9383453}, doi = {10.1109/SLT48900.2021.9383453}, timestamp = {Thu, 04 Nov 2021 00:00:00 +0100}, biburl = {https://dblp.org/rec/conf/slt/ChangL0HZH21.bib}, bibsource = {dblp computer science bibliography, https://dblp.org} }
@inproceedings{DBLP:conf/slt/ChangLLL21, author = {Heng{-}Jui Chang and Alexander H. Liu and Hung{-}yi Lee and Lin{-}Shan Lee}, title = {End-to-End Whispered Speech Recognition with Frequency-Weighted Approaches and Pseudo Whisper Pre-training}, booktitle = {{IEEE} Spoken Language Technology Workshop, {SLT} 2021, Shenzhen, China, January 19-22, 2021}, pages = {186--193}, publisher = {{IEEE}}, year = {2021}, url = {https://doi.org/10.1109/SLT48900.2021.9383595}, doi = {10.1109/SLT48900.2021.9383595}, timestamp = {Sat, 30 Sep 2023 01:00:00 +0200}, biburl = {https://dblp.org/rec/conf/slt/ChangLLL21.bib}, bibsource = {dblp computer science bibliography, https://dblp.org} }
@inproceedings{DBLP:conf/slt/ChenK21, author = {Tianxiang Chen and Elie Khoury}, title = {Spoofprint: {A} New Paradigm for Spoofing Attacks Detection}, booktitle = {{IEEE} Spoken Language Technology Workshop, {SLT} 2021, Shenzhen, China, January 19-22, 2021}, pages = {538--543}, publisher = {{IEEE}}, year = {2021}, url = {https://doi.org/10.1109/SLT48900.2021.9383572}, doi = {10.1109/SLT48900.2021.9383572}, timestamp = {Thu, 15 Jul 2021 01:00:00 +0200}, biburl = {https://dblp.org/rec/conf/slt/ChenK21.bib}, bibsource = {dblp computer science bibliography, https://dblp.org} }
@inproceedings{DBLP:conf/slt/ChenLL21, author = {Huan{-}Yu Chen and Yun{-}Shao Lin and Chi{-}Chun Lee}, title = {Through the Words of Viewers: Using Comment-Content Entangled Network for Humor Impression Recognition}, booktitle = {{IEEE} Spoken Language Technology Workshop, {SLT} 2021, Shenzhen, China, January 19-22, 2021}, pages = {1058--1064}, publisher = {{IEEE}}, year = {2021}, url = {https://doi.org/10.1109/SLT48900.2021.9383564}, doi = {10.1109/SLT48900.2021.9383564}, timestamp = {Mon, 05 Feb 2024 00:00:00 +0100}, biburl = {https://dblp.org/rec/conf/slt/ChenLL21.bib}, bibsource = {dblp computer science bibliography, https://dblp.org} }
@inproceedings{DBLP:conf/slt/ChiCWHC0L21, author = {Po{-}Han Chi and Pei{-}Hung Chung and Tsung{-}Han Wu and Chun{-}Cheng Hsieh and Yen{-}Hao Chen and Shang{-}Wen Li and Hung{-}yi Lee}, title = {Audio Albert: {A} Lite Bert for Self-Supervised Learning of Audio Representation}, booktitle = {{IEEE} Spoken Language Technology Workshop, {SLT} 2021, Shenzhen, China, January 19-22, 2021}, pages = {344--350}, publisher = {{IEEE}}, year = {2021}, url = {https://doi.org/10.1109/SLT48900.2021.9383575}, doi = {10.1109/SLT48900.2021.9383575}, timestamp = {Mon, 05 Feb 2024 00:00:00 +0100}, biburl = {https://dblp.org/rec/conf/slt/ChiCWHC0L21.bib}, bibsource = {dblp computer science bibliography, https://dblp.org} }
@inproceedings{DBLP:conf/slt/ChienL21, author = {Chung{-}Ming Chien and Hung{-}yi Lee}, title = {Hierarchical Prosody Modeling for Non-Autoregressive Speech Synthesis}, booktitle = {{IEEE} Spoken Language Technology Workshop, {SLT} 2021, Shenzhen, China, January 19-22, 2021}, pages = {446--453}, publisher = {{IEEE}}, year = {2021}, url = {https://doi.org/10.1109/SLT48900.2021.9383629}, doi = {10.1109/SLT48900.2021.9383629}, timestamp = {Thu, 08 Apr 2021 01:00:00 +0200}, biburl = {https://dblp.org/rec/conf/slt/ChienL21.bib}, bibsource = {dblp computer science bibliography, https://dblp.org} }
@inproceedings{DBLP:conf/slt/ChiuC21, author = {Shih{-}Hsuan Chiu and Berlin Chen}, title = {Innovative Bert-Based Reranking Language Models for Speech Recognition}, booktitle = {{IEEE} Spoken Language Technology Workshop, {SLT} 2021, Shenzhen, China, January 19-22, 2021}, pages = {266--271}, publisher = {{IEEE}}, year = {2021}, url = {https://doi.org/10.1109/SLT48900.2021.9383557}, doi = {10.1109/SLT48900.2021.9383557}, timestamp = {Thu, 08 Apr 2021 01:00:00 +0200}, biburl = {https://dblp.org/rec/conf/slt/ChiuC21.bib}, bibsource = {dblp computer science bibliography, https://dblp.org} }
@inproceedings{DBLP:conf/slt/ChiuNHPZJPSNCW21, author = {Chung{-}Cheng Chiu and Arun Narayanan and Wei Han and Rohit Prabhavalkar and Yu Zhang and Navdeep Jaitly and Ruoming Pang and Tara N. Sainath and Patrick Nguyen and Liangliang Cao and Yonghui Wu}, title = {{RNN-T} Models Fail to Generalize to Out-of-Domain Audio: Causes and Solutions}, booktitle = {{IEEE} Spoken Language Technology Workshop, {SLT} 2021, Shenzhen, China, January 19-22, 2021}, pages = {873--880}, publisher = {{IEEE}}, year = {2021}, url = {https://doi.org/10.1109/SLT48900.2021.9383518}, doi = {10.1109/SLT48900.2021.9383518}, timestamp = {Fri, 07 May 2021 01:00:00 +0200}, biburl = {https://dblp.org/rec/conf/slt/ChiuNHPZJPSNCW21.bib}, bibsource = {dblp computer science bibliography, https://dblp.org} }
@inproceedings{DBLP:conf/slt/ChoiJK21, author = {Yeunju Choi and Youngmoon Jung and Hoirin Kim}, title = {Neural {MOS} Prediction for Synthesized Speech Using Multi-Task Learning with Spoofing Detection and Spoofing Type Classification}, booktitle = {{IEEE} Spoken Language Technology Workshop, {SLT} 2021, Shenzhen, China, January 19-22, 2021}, pages = {462--469}, publisher = {{IEEE}}, year = {2021}, url = {https://doi.org/10.1109/SLT48900.2021.9383533}, doi = {10.1109/SLT48900.2021.9383533}, timestamp = {Thu, 08 Apr 2021 01:00:00 +0200}, biburl = {https://dblp.org/rec/conf/slt/ChoiJK21.bib}, bibsource = {dblp computer science bibliography, https://dblp.org} }
@inproceedings{DBLP:conf/slt/DuLLWQ21, author = {Chenpeng Du and Hao Li and Yizhou Lu and Lan Wang and Yanmin Qian}, title = {Data Augmentation for end-to-end Code-Switching Speech Recognition}, booktitle = {{IEEE} Spoken Language Technology Workshop, {SLT} 2021, Shenzhen, China, January 19-22, 2021}, pages = {194--200}, publisher = {{IEEE}}, year = {2021}, url = {https://doi.org/10.1109/SLT48900.2021.9383620}, doi = {10.1109/SLT48900.2021.9383620}, timestamp = {Thu, 14 Oct 2021 01:00:00 +0200}, biburl = {https://dblp.org/rec/conf/slt/DuLLWQ21.bib}, bibsource = {dblp computer science bibliography, https://dblp.org} }
@inproceedings{DBLP:conf/slt/DuTX021, author = {Hongqiang Du and Xiaohai Tian and Lei Xie and Haizhou Li}, title = {Optimizing Voice Conversion Network with Cycle Consistency Loss of Speaker Identity}, booktitle = {{IEEE} Spoken Language Technology Workshop, {SLT} 2021, Shenzhen, China, January 19-22, 2021}, pages = {507--513}, publisher = {{IEEE}}, year = {2021}, url = {https://doi.org/10.1109/SLT48900.2021.9383567}, doi = {10.1109/SLT48900.2021.9383567}, timestamp = {Fri, 14 May 2021 01:00:00 +0200}, biburl = {https://dblp.org/rec/conf/slt/DuTX021.bib}, bibsource = {dblp computer science bibliography, https://dblp.org} }
@inproceedings{DBLP:conf/slt/EppsUK21, author = {Maya Epps and Juan Uribe and Mandy Korpusik}, title = {A New Dataset for Natural Language Understanding of Exercise Logs in a Food and Fitness Spoken Dialogue System}, booktitle = {{IEEE} Spoken Language Technology Workshop, {SLT} 2021, Shenzhen, China, January 19-22, 2021}, pages = {1071--1078}, publisher = {{IEEE}}, year = {2021}, url = {https://doi.org/10.1109/SLT48900.2021.9383508}, doi = {10.1109/SLT48900.2021.9383508}, timestamp = {Thu, 08 Apr 2021 01:00:00 +0200}, biburl = {https://dblp.org/rec/conf/slt/EppsUK21.bib}, bibsource = {dblp computer science bibliography, https://dblp.org} }
@inproceedings{DBLP:conf/slt/FengBE21, author = {Yulan Feng and Alan W. Black and Maxine Esk{\'{e}}nazi}, title = {Towards Automatic Route Description Unification in Spoken Dialog Systems}, booktitle = {{IEEE} Spoken Language Technology Workshop, {SLT} 2021, Shenzhen, China, January 19-22, 2021}, pages = {685--692}, publisher = {{IEEE}}, year = {2021}, url = {https://doi.org/10.1109/SLT48900.2021.9383465}, doi = {10.1109/SLT48900.2021.9383465}, timestamp = {Thu, 08 Apr 2021 01:00:00 +0200}, biburl = {https://dblp.org/rec/conf/slt/FengBE21.bib}, bibsource = {dblp computer science bibliography, https://dblp.org} }
@inproceedings{DBLP:conf/slt/FuWHXX21, author = {Yihui Fu and Jian Wu and Yanxin Hu and Mengtao Xing and Lei Xie}, title = {DESNet: {A} Multi-Channel Network for Simultaneous Speech Dereverberation, Enhancement and Separation}, booktitle = {{IEEE} Spoken Language Technology Workshop, {SLT} 2021, Shenzhen, China, January 19-22, 2021}, pages = {857--864}, publisher = {{IEEE}}, year = {2021}, url = {https://doi.org/10.1109/SLT48900.2021.9383604}, doi = {10.1109/SLT48900.2021.9383604}, timestamp = {Sat, 18 Feb 2023 00:00:00 +0100}, biburl = {https://dblp.org/rec/conf/slt/FuWHXX21.bib}, bibsource = {dblp computer science bibliography, https://dblp.org} }
@inproceedings{DBLP:conf/slt/FuYHWWYZXHBMO21, author = {Yihui Fu and Zhuoyuan Yao and Weipeng He and Jian Wu and Xiong Wang and Zhanheng Yang and Shimin Zhang and Lei Xie and Dongyan Huang and Hui Bu and Petr Motl{\'{\i}}cek and Jean{-}Marc Odobez}, title = {{IEEE} {SLT} 2021 Alpha-Mini Speech Challenge: Open Datasets, Tracks, Rules and Baselines}, booktitle = {{IEEE} Spoken Language Technology Workshop, {SLT} 2021, Shenzhen, China, January 19-22, 2021}, pages = {1101--1108}, publisher = {{IEEE}}, year = {2021}, url = {https://doi.org/10.1109/SLT48900.2021.9383546}, doi = {10.1109/SLT48900.2021.9383546}, timestamp = {Tue, 07 May 2024 01:00:00 +0200}, biburl = {https://dblp.org/rec/conf/slt/FuYHWWYZXHBMO21.bib}, bibsource = {dblp computer science bibliography, https://dblp.org} }
@inproceedings{DBLP:conf/slt/GaoLRS21, author = {Yang Gao and Jiachen Lian and Bhiksha Raj and Rita Singh}, title = {Detection and Evaluation of Human and Machine Generated Speech in Spoofing Attacks on Automatic Speaker Verification Systems}, booktitle = {{IEEE} Spoken Language Technology Workshop, {SLT} 2021, Shenzhen, China, January 19-22, 2021}, pages = {544--551}, publisher = {{IEEE}}, year = {2021}, url = {https://doi.org/10.1109/SLT48900.2021.9383558}, doi = {10.1109/SLT48900.2021.9383558}, timestamp = {Thu, 08 Apr 2021 01:00:00 +0200}, biburl = {https://dblp.org/rec/conf/slt/GaoLRS21.bib}, bibsource = {dblp computer science bibliography, https://dblp.org} }
@inproceedings{DBLP:conf/slt/GeorgescuMOCB21, author = {Alexandru{-}Lucian Georgescu and Cristian Manolache and Dan Oneata and Horia Cucu and Corneliu Burileanu}, title = {Data-Filtering Methods for Self-Training of Automatic Speech Recognition Systems}, booktitle = {{IEEE} Spoken Language Technology Workshop, {SLT} 2021, Shenzhen, China, January 19-22, 2021}, pages = {141--147}, publisher = {{IEEE}}, year = {2021}, url = {https://doi.org/10.1109/SLT48900.2021.9383577}, doi = {10.1109/SLT48900.2021.9383577}, timestamp = {Thu, 14 Oct 2021 01:00:00 +0200}, biburl = {https://dblp.org/rec/conf/slt/GeorgescuMOCB21.bib}, bibsource = {dblp computer science bibliography, https://dblp.org} }
@inproceedings{DBLP:conf/slt/GhorbaniGSL21, author = {Shahram Ghorbani and Yashesh Gaur and Yu Shi and Jinyu Li}, title = {Listen, Look and Deliberate: Visual Context-Aware Speech Recognition Using Pre-Trained Text-Video Representations}, booktitle = {{IEEE} Spoken Language Technology Workshop, {SLT} 2021, Shenzhen, China, January 19-22, 2021}, pages = {621--628}, publisher = {{IEEE}}, year = {2021}, url = {https://doi.org/10.1109/SLT48900.2021.9383466}, doi = {10.1109/SLT48900.2021.9383466}, timestamp = {Tue, 21 Mar 2023 00:00:00 +0100}, biburl = {https://dblp.org/rec/conf/slt/GhorbaniGSL21.bib}, bibsource = {dblp computer science bibliography, https://dblp.org} }
@inproceedings{DBLP:conf/slt/GuoZSHX21, author = {Haohan Guo and Shaofei Zhang and Frank K. Soong and Lei He and Lei Xie}, title = {Conversational End-to-End {TTS} for Voice Agents}, booktitle = {{IEEE} Spoken Language Technology Workshop, {SLT} 2021, Shenzhen, China, January 19-22, 2021}, pages = {403--409}, publisher = {{IEEE}}, year = {2021}, url = {https://doi.org/10.1109/SLT48900.2021.9383460}, doi = {10.1109/SLT48900.2021.9383460}, timestamp = {Sun, 02 Oct 2022 01:00:00 +0200}, biburl = {https://dblp.org/rec/conf/slt/GuoZSHX21.bib}, bibsource = {dblp computer science bibliography, https://dblp.org} }
@inproceedings{DBLP:conf/slt/HGDR21, author = {Muralikrishna H and Shikha Gupta and Dileep Aroor Dinesh and Padmanabhan Rajan}, title = {Noise-Robust Spoken Language Identification Using Language Relevance Factor Based Embedding}, booktitle = {{IEEE} Spoken Language Technology Workshop, {SLT} 2021, Shenzhen, China, January 19-22, 2021}, pages = {644--651}, publisher = {{IEEE}}, year = {2021}, url = {https://doi.org/10.1109/SLT48900.2021.9383503}, doi = {10.1109/SLT48900.2021.9383503}, timestamp = {Thu, 08 Apr 2021 01:00:00 +0200}, biburl = {https://dblp.org/rec/conf/slt/HGDR21.bib}, bibsource = {dblp computer science bibliography, https://dblp.org} }
@inproceedings{DBLP:conf/slt/HoriguchiFN21, author = {Shota Horiguchi and Yusuke Fujita and Kenji Nagamatsu}, title = {Block-Online Guided Source Separation}, booktitle = {{IEEE} Spoken Language Technology Workshop, {SLT} 2021, Shenzhen, China, January 19-22, 2021}, pages = {236--242}, publisher = {{IEEE}}, year = {2021}, url = {https://doi.org/10.1109/SLT48900.2021.9383510}, doi = {10.1109/SLT48900.2021.9383510}, timestamp = {Thu, 08 Apr 2021 01:00:00 +0200}, biburl = {https://dblp.org/rec/conf/slt/HoriguchiFN21.bib}, bibsource = {dblp computer science bibliography, https://dblp.org} }
@inproceedings{DBLP:conf/slt/HossainS21, author = {Delowar Hossain and Yoshinao Sato}, title = {Efficient corpus design for wake-word detection}, booktitle = {{IEEE} Spoken Language Technology Workshop, {SLT} 2021, Shenzhen, China, January 19-22, 2021}, pages = {1094--1100}, publisher = {{IEEE}}, year = {2021}, url = {https://doi.org/10.1109/SLT48900.2021.9383569}, doi = {10.1109/SLT48900.2021.9383569}, timestamp = {Thu, 08 Apr 2021 01:00:00 +0200}, biburl = {https://dblp.org/rec/conf/slt/HossainS21.bib}, bibsource = {dblp computer science bibliography, https://dblp.org} }
@inproceedings{DBLP:conf/slt/Hsu0SH21, author = {Wei{-}Ning Hsu and Ann Lee and Gabriel Synnaeve and Awni Y. Hannun}, title = {Semi-Supervised end-to-end Speech Recognition via Local Prior Matching}, booktitle = {{IEEE} Spoken Language Technology Workshop, {SLT} 2021, Shenzhen, China, January 19-22, 2021}, pages = {125--132}, publisher = {{IEEE}}, year = {2021}, url = {https://doi.org/10.1109/SLT48900.2021.9383552}, doi = {10.1109/SLT48900.2021.9383552}, timestamp = {Tue, 05 Apr 2022 01:00:00 +0200}, biburl = {https://dblp.org/rec/conf/slt/Hsu0SH21.bib}, bibsource = {dblp computer science bibliography, https://dblp.org} }
@inproceedings{DBLP:conf/slt/HuBPRML21, author = {Qiong Hu and Tobias Bleisch and Petko Petkov and Tuomo Raitio and Erik Marchi and Varun Lakshminarasimhan}, title = {Whispered and Lombard Neural Speech Synthesis}, booktitle = {{IEEE} Spoken Language Technology Workshop, {SLT} 2021, Shenzhen, China, January 19-22, 2021}, pages = {454--461}, publisher = {{IEEE}}, year = {2021}, url = {https://doi.org/10.1109/SLT48900.2021.9383454}, doi = {10.1109/SLT48900.2021.9383454}, timestamp = {Thu, 08 Apr 2021 01:00:00 +0200}, biburl = {https://dblp.org/rec/conf/slt/HuBPRML21.bib}, bibsource = {dblp computer science bibliography, https://dblp.org} }
@inproceedings{DBLP:conf/slt/HuPSS21, author = {Ke Hu and Ruoming Pang and Tara N. Sainath and Trevor Strohman}, title = {Transformer Based Deliberation for Two-Pass Speech Recognition}, booktitle = {{IEEE} Spoken Language Technology Workshop, {SLT} 2021, Shenzhen, China, January 19-22, 2021}, pages = {68--74}, publisher = {{IEEE}}, year = {2021}, url = {https://doi.org/10.1109/SLT48900.2021.9383497}, doi = {10.1109/SLT48900.2021.9383497}, timestamp = {Thu, 08 Apr 2021 01:00:00 +0200}, biburl = {https://dblp.org/rec/conf/slt/HuPSS21.bib}, bibsource = {dblp computer science bibliography, https://dblp.org} }
@inproceedings{DBLP:conf/slt/HuSL21, author = {Yushi Hu and Shane Settle and Karen Livescu}, title = {Acoustic Span Embeddings for Multilingual Query-by-Example Search}, booktitle = {{IEEE} Spoken Language Technology Workshop, {SLT} 2021, Shenzhen, China, January 19-22, 2021}, pages = {935--942}, publisher = {{IEEE}}, year = {2021}, url = {https://doi.org/10.1109/SLT48900.2021.9383545}, doi = {10.1109/SLT48900.2021.9383545}, timestamp = {Thu, 08 Apr 2021 01:00:00 +0200}, biburl = {https://dblp.org/rec/conf/slt/HuSL21.bib}, bibsource = {dblp computer science bibliography, https://dblp.org} }
@inproceedings{DBLP:conf/slt/HuangCPW21, author = {Yiling Huang and Yutian Chen and Jason Pelecanos and Quan Wang}, title = {Synth2Aug: Cross-Domain Speaker Recognition with {TTS} Synthesized Speech}, booktitle = {{IEEE} Spoken Language Technology Workshop, {SLT} 2021, Shenzhen, China, January 19-22, 2021}, pages = {316--322}, publisher = {{IEEE}}, year = {2021}, url = {https://doi.org/10.1109/SLT48900.2021.9383525}, doi = {10.1109/SLT48900.2021.9383525}, timestamp = {Thu, 08 Apr 2021 01:00:00 +0200}, biburl = {https://dblp.org/rec/conf/slt/HuangCPW21.bib}, bibsource = {dblp computer science bibliography, https://dblp.org} }
@inproceedings{DBLP:conf/slt/HuangLL21, author = {Tzu{-}hsien Huang and Jheng{-}Hao Lin and Hung{-}yi Lee}, title = {How Far Are We from Robust Voice Conversion: {A} Survey}, booktitle = {{IEEE} Spoken Language Technology Workshop, {SLT} 2021, Shenzhen, China, January 19-22, 2021}, pages = {514--521}, publisher = {{IEEE}}, year = {2021}, url = {https://doi.org/10.1109/SLT48900.2021.9383498}, doi = {10.1109/SLT48900.2021.9383498}, timestamp = {Thu, 08 Apr 2021 01:00:00 +0200}, biburl = {https://dblp.org/rec/conf/slt/HuangLL21.bib}, bibsource = {dblp computer science bibliography, https://dblp.org} }
@inproceedings{DBLP:conf/slt/HuangLLL21, author = {Chien{-}yu Huang and Yist Y. Lin and Hung{-}yi Lee and Lin{-}Shan Lee}, title = {Defending Your Voice: Adversarial Attack on Voice Conversion}, booktitle = {{IEEE} Spoken Language Technology Workshop, {SLT} 2021, Shenzhen, China, January 19-22, 2021}, pages = {552--559}, publisher = {{IEEE}}, year = {2021}, url = {https://doi.org/10.1109/SLT48900.2021.9383529}, doi = {10.1109/SLT48900.2021.9383529}, timestamp = {Thu, 08 Apr 2021 01:00:00 +0200}, biburl = {https://dblp.org/rec/conf/slt/HuangLLL21.bib}, bibsource = {dblp computer science bibliography, https://dblp.org} }
@inproceedings{DBLP:conf/slt/HuhLHMC21, author = {Jaesung Huh and Minjae Lee and Heesoo Heo and Seongkyu Mun and Joon Son Chung}, title = {Metric Learning for Keyword Spotting}, booktitle = {{IEEE} Spoken Language Technology Workshop, {SLT} 2021, Shenzhen, China, January 19-22, 2021}, pages = {133--140}, publisher = {{IEEE}}, year = {2021}, url = {https://doi.org/10.1109/SLT48900.2021.9383571}, doi = {10.1109/SLT48900.2021.9383571}, timestamp = {Thu, 08 Apr 2021 01:00:00 +0200}, biburl = {https://dblp.org/rec/conf/slt/HuhLHMC21.bib}, bibsource = {dblp computer science bibliography, https://dblp.org} }
@inproceedings{DBLP:conf/slt/JacobsMK21, author = {Christiaan Jacobs and Yevgen Matusevych and Herman Kamper}, title = {Acoustic Word Embeddings for Zero-Resource Languages Using Self-Supervised Contrastive Learning and Multilingual Adaptation}, booktitle = {{IEEE} Spoken Language Technology Workshop, {SLT} 2021, Shenzhen, China, January 19-22, 2021}, pages = {919--926}, publisher = {{IEEE}}, year = {2021}, url = {https://doi.org/10.1109/SLT48900.2021.9383594}, doi = {10.1109/SLT48900.2021.9383594}, timestamp = {Thu, 14 Oct 2021 01:00:00 +0200}, biburl = {https://dblp.org/rec/conf/slt/JacobsMK21.bib}, bibsource = {dblp computer science bibliography, https://dblp.org} }
@inproceedings{DBLP:conf/slt/JayasimhaP21, author = {Aditya Jayasimha and Periyasamy Paramasivam}, title = {Personalizing Speech Start Point and End Point Detection in {ASR} Systems from Speaker Embeddings}, booktitle = {{IEEE} Spoken Language Technology Workshop, {SLT} 2021, Shenzhen, China, January 19-22, 2021}, pages = {771--777}, publisher = {{IEEE}}, year = {2021}, url = {https://doi.org/10.1109/SLT48900.2021.9383516}, doi = {10.1109/SLT48900.2021.9383516}, timestamp = {Thu, 08 Apr 2021 01:00:00 +0200}, biburl = {https://dblp.org/rec/conf/slt/JayasimhaP21.bib}, bibsource = {dblp computer science bibliography, https://dblp.org} }
@inproceedings{DBLP:conf/slt/KaiTSK21, author = {Hiroto Kai and Shinnosuke Takamichi and Sayaka Shiota and Hitoshi Kiya}, title = {Lightweight Voice Anonymization Based on Data-Driven Optimization of Cascaded Voice Modification Modules}, booktitle = {{IEEE} Spoken Language Technology Workshop, {SLT} 2021, Shenzhen, China, January 19-22, 2021}, pages = {560--566}, publisher = {{IEEE}}, year = {2021}, url = {https://doi.org/10.1109/SLT48900.2021.9383535}, doi = {10.1109/SLT48900.2021.9383535}, timestamp = {Thu, 08 Apr 2021 01:00:00 +0200}, biburl = {https://dblp.org/rec/conf/slt/KaiTSK21.bib}, bibsource = {dblp computer science bibliography, https://dblp.org} }
@inproceedings{DBLP:conf/slt/KandaCGWMCY21, author = {Naoyuki Kanda and Xuankai Chang and Yashesh Gaur and Xiaofei Wang and Zhong Meng and Zhuo Chen and Takuya Yoshioka}, title = {Investigation of End-to-End Speaker-Attributed {ASR} for Continuous Multi-Talker Recordings}, booktitle = {{IEEE} Spoken Language Technology Workshop, {SLT} 2021, Shenzhen, China, January 19-22, 2021}, pages = {809--816}, publisher = {{IEEE}}, year = {2021}, url = {https://doi.org/10.1109/SLT48900.2021.9383600}, doi = {10.1109/SLT48900.2021.9383600}, timestamp = {Wed, 19 Oct 2022 01:00:00 +0200}, biburl = {https://dblp.org/rec/conf/slt/KandaCGWMCY21.bib}, bibsource = {dblp computer science bibliography, https://dblp.org} }
@inproceedings{DBLP:conf/slt/KangY021, author = {Fang Kang and Feiran Yang and Jun Yang}, title = {Real-Time Independent Vector Analysis with a Deep-Learning-Based Source Model}, booktitle = {{IEEE} Spoken Language Technology Workshop, {SLT} 2021, Shenzhen, China, January 19-22, 2021}, pages = {665--669}, publisher = {{IEEE}}, year = {2021}, url = {https://doi.org/10.1109/SLT48900.2021.9383599}, doi = {10.1109/SLT48900.2021.9383599}, timestamp = {Thu, 08 Apr 2021 01:00:00 +0200}, biburl = {https://dblp.org/rec/conf/slt/KangY021.bib}, bibsource = {dblp computer science bibliography, https://dblp.org} }
@inproceedings{DBLP:conf/slt/KanoS021, author = {Takatomo Kano and Sakriani Sakti and Satoshi Nakamura}, title = {Transformer-Based Direct Speech-To-Speech Translation with Transcoder}, booktitle = {{IEEE} Spoken Language Technology Workshop, {SLT} 2021, Shenzhen, China, January 19-22, 2021}, pages = {958--965}, publisher = {{IEEE}}, year = {2021}, url = {https://doi.org/10.1109/SLT48900.2021.9383496}, doi = {10.1109/SLT48900.2021.9383496}, timestamp = {Thu, 08 Apr 2021 01:00:00 +0200}, biburl = {https://dblp.org/rec/conf/slt/KanoS021.bib}, bibsource = {dblp computer science bibliography, https://dblp.org} }
@inproceedings{DBLP:conf/slt/KhanalJB21, author = {Subash Khanal and Michael T. Johnson and Narjes Bozorg}, title = {Articulatory Comparison of {L1} and {L2} Speech for Mispronunciation Diagnosis}, booktitle = {{IEEE} Spoken Language Technology Workshop, {SLT} 2021, Shenzhen, China, January 19-22, 2021}, pages = {693--697}, publisher = {{IEEE}}, year = {2021}, url = {https://doi.org/10.1109/SLT48900.2021.9383574}, doi = {10.1109/SLT48900.2021.9383574}, timestamp = {Thu, 08 Apr 2021 01:00:00 +0200}, biburl = {https://dblp.org/rec/conf/slt/KhanalJB21.bib}, bibsource = {dblp computer science bibliography, https://dblp.org} }
@inproceedings{DBLP:conf/slt/KharePS21, author = {Aparna Khare and Srinivas Parthasarathy and Shiva Sundaram}, title = {Self-Supervised Learning with Cross-Modal Transformers for Emotion Recognition}, booktitle = {{IEEE} Spoken Language Technology Workshop, {SLT} 2021, Shenzhen, China, January 19-22, 2021}, pages = {381--388}, publisher = {{IEEE}}, year = {2021}, url = {https://doi.org/10.1109/SLT48900.2021.9383618}, doi = {10.1109/SLT48900.2021.9383618}, timestamp = {Sat, 30 Sep 2023 01:00:00 +0200}, biburl = {https://dblp.org/rec/conf/slt/KharePS21.bib}, bibsource = {dblp computer science bibliography, https://dblp.org} }
@inproceedings{DBLP:conf/slt/KharitonovRSWMD21, author = {Eugene Kharitonov and Morgane Rivi{\`{e}}re and Gabriel Synnaeve and Lior Wolf and Pierre{-}Emmanuel Mazar{\'{e}} and Matthijs Douze and Emmanuel Dupoux}, title = {Data Augmenting Contrastive Learning of Speech Representations in the Time Domain}, booktitle = {{IEEE} Spoken Language Technology Workshop, {SLT} 2021, Shenzhen, China, January 19-22, 2021}, pages = {215--222}, publisher = {{IEEE}}, year = {2021}, url = {https://doi.org/10.1109/SLT48900.2021.9383605}, doi = {10.1109/SLT48900.2021.9383605}, timestamp = {Thu, 08 Apr 2021 01:00:00 +0200}, biburl = {https://dblp.org/rec/conf/slt/KharitonovRSWMD21.bib}, bibsource = {dblp computer science bibliography, https://dblp.org} }
@inproceedings{DBLP:conf/slt/KimHCL21, author = {You Jin Kim and Hee Soo Heo and Soo{-}Whan Chung and Bong{-}Jin Lee}, title = {End-To-End Lip Synchronisation Based on Pattern Classification}, booktitle = {{IEEE} Spoken Language Technology Workshop, {SLT} 2021, Shenzhen, China, January 19-22, 2021}, pages = {598--605}, publisher = {{IEEE}}, year = {2021}, url = {https://doi.org/10.1109/SLT48900.2021.9383616}, doi = {10.1109/SLT48900.2021.9383616}, timestamp = {Thu, 08 Apr 2021 01:00:00 +0200}, biburl = {https://dblp.org/rec/conf/slt/KimHCL21.bib}, bibsource = {dblp computer science bibliography, https://dblp.org} }
@inproceedings{DBLP:conf/slt/KongWWGZWX21, author = {Yuxiang Kong and Jian Wu and Quandong Wang and Peng Gao and Weiji Zhuang and Yujun Wang and Lei Xie}, title = {Multi-Channel Automatic Speech Recognition Using Deep Complex Unet}, booktitle = {{IEEE} Spoken Language Technology Workshop, {SLT} 2021, Shenzhen, China, January 19-22, 2021}, pages = {104--110}, publisher = {{IEEE}}, year = {2021}, url = {https://doi.org/10.1109/SLT48900.2021.9383492}, doi = {10.1109/SLT48900.2021.9383492}, timestamp = {Sat, 20 May 2023 01:00:00 +0200}, biburl = {https://dblp.org/rec/conf/slt/KongWWGZWX21.bib}, bibsource = {dblp computer science bibliography, https://dblp.org} }
@inproceedings{DBLP:conf/slt/Krishnamachari021, author = {Suchitra Krishnamachari and Manoj Kumar and So Hyun Kim and Catherine Lord and Shrikanth Narayanan}, title = {Developing Neural Representations for Robust Child-Adult Diarization}, booktitle = {{IEEE} Spoken Language Technology Workshop, {SLT} 2021, Shenzhen, China, January 19-22, 2021}, pages = {590--597}, publisher = {{IEEE}}, year = {2021}, url = {https://doi.org/10.1109/SLT48900.2021.9383488}, doi = {10.1109/SLT48900.2021.9383488}, timestamp = {Sat, 30 Sep 2023 01:00:00 +0200}, biburl = {https://dblp.org/rec/conf/slt/Krishnamachari021.bib}, bibsource = {dblp computer science bibliography, https://dblp.org} }
@inproceedings{DBLP:conf/slt/KwonHHLC21, author = {Youngki Kwon and Hee Soo Heo and Jaesung Huh and Bong{-}Jin Lee and Joon Son Chung}, title = {Look Who's Not Talking}, booktitle = {{IEEE} Spoken Language Technology Workshop, {SLT} 2021, Shenzhen, China, January 19-22, 2021}, pages = {567--573}, publisher = {{IEEE}}, year = {2021}, url = {https://doi.org/10.1109/SLT48900.2021.9383502}, doi = {10.1109/SLT48900.2021.9383502}, timestamp = {Thu, 08 Apr 2021 01:00:00 +0200}, biburl = {https://dblp.org/rec/conf/slt/KwonHHLC21.bib}, bibsource = {dblp computer science bibliography, https://dblp.org} }
@inproceedings{DBLP:conf/slt/KyeCK21, author = {Seong Min Kye and Joon Son Chung and Hoirin Kim}, title = {Supervised Attention for Speaker Recognition}, booktitle = {{IEEE} Spoken Language Technology Workshop, {SLT} 2021, Shenzhen, China, January 19-22, 2021}, pages = {286--293}, publisher = {{IEEE}}, year = {2021}, url = {https://doi.org/10.1109/SLT48900.2021.9383579}, doi = {10.1109/SLT48900.2021.9383579}, timestamp = {Thu, 08 Apr 2021 01:00:00 +0200}, biburl = {https://dblp.org/rec/conf/slt/KyeCK21.bib}, bibsource = {dblp computer science bibliography, https://dblp.org} }
@inproceedings{DBLP:conf/slt/KyeKC21, author = {Seong Min Kye and Yoohwan Kwon and Joon Son Chung}, title = {Cross Attentive Pooling for Speaker Verification}, booktitle = {{IEEE} Spoken Language Technology Workshop, {SLT} 2021, Shenzhen, China, January 19-22, 2021}, pages = {294--300}, publisher = {{IEEE}}, year = {2021}, url = {https://doi.org/10.1109/SLT48900.2021.9383565}, doi = {10.1109/SLT48900.2021.9383565}, timestamp = {Thu, 08 Apr 2021 01:00:00 +0200}, biburl = {https://dblp.org/rec/conf/slt/KyeKC21.bib}, bibsource = {dblp computer science bibliography, https://dblp.org} }
@inproceedings{DBLP:conf/slt/LamWSY21, author = {Max W. Y. Lam and Jun Wang and Dan Su and Dong Yu}, title = {Effective Low-Cost Time-Domain Audio Separation Using Globally Attentive Locally Recurrent Networks}, booktitle = {{IEEE} Spoken Language Technology Workshop, {SLT} 2021, Shenzhen, China, January 19-22, 2021}, pages = {801--808}, publisher = {{IEEE}}, year = {2021}, url = {https://doi.org/10.1109/SLT48900.2021.9383464}, doi = {10.1109/SLT48900.2021.9383464}, timestamp = {Wed, 22 Dec 2021 00:00:00 +0100}, biburl = {https://dblp.org/rec/conf/slt/LamWSY21.bib}, bibsource = {dblp computer science bibliography, https://dblp.org} }
@inproceedings{DBLP:conf/slt/LeKCMFS21, author = {Duc Le and Gil Keren and Julian Chan and Jay Mahadeokar and Christian Fuegen and Michael L. Seltzer}, title = {Deep Shallow Fusion for {RNN-T} Personalization}, booktitle = {{IEEE} Spoken Language Technology Workshop, {SLT} 2021, Shenzhen, China, January 19-22, 2021}, pages = {251--257}, publisher = {{IEEE}}, year = {2021}, url = {https://doi.org/10.1109/SLT48900.2021.9383560}, doi = {10.1109/SLT48900.2021.9383560}, timestamp = {Thu, 08 Apr 2021 01:00:00 +0200}, biburl = {https://dblp.org/rec/conf/slt/LeKCMFS21.bib}, bibsource = {dblp computer science bibliography, https://dblp.org} }
@inproceedings{DBLP:conf/slt/Lee21, author = {Shi{-}wook Lee}, title = {Domain Generalization with Triplet Network for Cross-Corpus Speech Emotion Recognition}, booktitle = {{IEEE} Spoken Language Technology Workshop, {SLT} 2021, Shenzhen, China, January 19-22, 2021}, pages = {389--396}, publisher = {{IEEE}}, year = {2021}, url = {https://doi.org/10.1109/SLT48900.2021.9383534}, doi = {10.1109/SLT48900.2021.9383534}, timestamp = {Thu, 14 Oct 2021 01:00:00 +0200}, biburl = {https://dblp.org/rec/conf/slt/Lee21.bib}, bibsource = {dblp computer science bibliography, https://dblp.org} }
@inproceedings{DBLP:conf/slt/LeiYX21, author = {Yi Lei and Shan Yang and Lei Xie}, title = {Fine-Grained Emotion Strength Transfer, Control and Prediction for Emotional Speech Synthesis}, booktitle = {{IEEE} Spoken Language Technology Workshop, {SLT} 2021, Shenzhen, China, January 19-22, 2021}, pages = {423--430}, publisher = {{IEEE}}, year = {2021}, url = {https://doi.org/10.1109/SLT48900.2021.9383524}, doi = {10.1109/SLT48900.2021.9383524}, timestamp = {Fri, 05 Nov 2021 00:00:00 +0100}, biburl = {https://dblp.org/rec/conf/slt/LeiYX21.bib}, bibsource = {dblp computer science bibliography, https://dblp.org} }
@inproceedings{DBLP:conf/slt/Li0ZSCKHHBC021, author = {Chenda Li and Jing Shi and Wangyou Zhang and Aswin Shanmugam Subramanian and Xuankai Chang and Naoyuki Kamo and Moto Hira and Tomoki Hayashi and Christoph B{\"{o}}ddeker and Zhuo Chen and Shinji Watanabe}, title = {ESPnet-SE: End-To-End Speech Enhancement and Separation Toolkit Designed for {ASR} Integration}, booktitle = {{IEEE} Spoken Language Technology Workshop, {SLT} 2021, Shenzhen, China, January 19-22, 2021}, pages = {785--792}, publisher = {{IEEE}}, year = {2021}, url = {https://doi.org/10.1109/SLT48900.2021.9383615}, doi = {10.1109/SLT48900.2021.9383615}, timestamp = {Tue, 21 Mar 2023 00:00:00 +0100}, biburl = {https://dblp.org/rec/conf/slt/Li0ZSCKHHBC021.bib}, bibsource = {dblp computer science bibliography, https://dblp.org} }
@inproceedings{DBLP:conf/slt/LiAY21, author = {Haoyu Li and Yang Ai and Junichi Yamagishi}, title = {Enhancing Low-Quality Voice Recordings Using Disentangled Channel Factor and Neural Waveform Model}, booktitle = {{IEEE} Spoken Language Technology Workshop, {SLT} 2021, Shenzhen, China, January 19-22, 2021}, pages = {734--741}, publisher = {{IEEE}}, year = {2021}, url = {https://doi.org/10.1109/SLT48900.2021.9383507}, doi = {10.1109/SLT48900.2021.9383507}, timestamp = {Thu, 08 Apr 2021 01:00:00 +0200}, biburl = {https://dblp.org/rec/conf/slt/LiAY21.bib}, bibsource = {dblp computer science bibliography, https://dblp.org} }
@inproceedings{DBLP:conf/slt/LiK0W21, author = {Qiujia Li and Florian L. Kreyssig and Chao Zhang and Philip C. Woodland}, title = {Discriminative Neural Clustering for Speaker Diarisation}, booktitle = {{IEEE} Spoken Language Technology Workshop, {SLT} 2021, Shenzhen, China, January 19-22, 2021}, pages = {574--581}, publisher = {{IEEE}}, year = {2021}, url = {https://doi.org/10.1109/SLT48900.2021.9383617}, doi = {10.1109/SLT48900.2021.9383617}, timestamp = {Thu, 08 Apr 2021 01:00:00 +0200}, biburl = {https://dblp.org/rec/conf/slt/LiK0W21.bib}, bibsource = {dblp computer science bibliography, https://dblp.org} }
@inproceedings{DBLP:conf/slt/LiLHLYZDKBQ0C21, author = {Chenda Li and Yi Luo and Cong Han and Jinyu Li and Takuya Yoshioka and Tianyan Zhou and Marc Delcroix and Keisuke Kinoshita and Christoph B{\"{o}}ddeker and Yanmin Qian and Shinji Watanabe and Zhuo Chen}, title = {Dual-Path {RNN} for Long Recording Speech Separation}, booktitle = {{IEEE} Spoken Language Technology Workshop, {SLT} 2021, Shenzhen, China, January 19-22, 2021}, pages = {865--872}, publisher = {{IEEE}}, year = {2021}, url = {https://doi.org/10.1109/SLT48900.2021.9383514}, doi = {10.1109/SLT48900.2021.9383514}, timestamp = {Sun, 12 Nov 2023 00:00:00 +0100}, biburl = {https://dblp.org/rec/conf/slt/LiLHLYZDKBQ0C21.bib}, bibsource = {dblp computer science bibliography, https://dblp.org} }
@inproceedings{DBLP:conf/slt/LiOLH21, author = {Song Li and Beibei Ouyang and Lin Li and Qingyang Hong}, title = {Lightspeech: Lightweight Non-Autoregressive Multi-Speaker Text-To-Speech}, booktitle = {{IEEE} Spoken Language Technology Workshop, {SLT} 2021, Shenzhen, China, January 19-22, 2021}, pages = {499--506}, publisher = {{IEEE}}, year = {2021}, url = {https://doi.org/10.1109/SLT48900.2021.9383562}, doi = {10.1109/SLT48900.2021.9383562}, timestamp = {Mon, 26 Apr 2021 01:00:00 +0200}, biburl = {https://dblp.org/rec/conf/slt/LiOLH21.bib}, bibsource = {dblp computer science bibliography, https://dblp.org} }
@inproceedings{DBLP:conf/slt/LiSH21, author = {Ruizhi Li and Gregory Sell and Hynek Hermansky}, title = {Two-Stage Augmentation and Adaptive {CTC} Fusion for Improved Robustness of Multi-Stream end-to-end {ASR}}, booktitle = {{IEEE} Spoken Language Technology Workshop, {SLT} 2021, Shenzhen, China, January 19-22, 2021}, pages = {229--235}, publisher = {{IEEE}}, year = {2021}, url = {https://doi.org/10.1109/SLT48900.2021.9383621}, doi = {10.1109/SLT48900.2021.9383621}, timestamp = {Thu, 08 Apr 2021 01:00:00 +0200}, biburl = {https://dblp.org/rec/conf/slt/LiSH21.bib}, bibsource = {dblp computer science bibliography, https://dblp.org} }
@inproceedings{DBLP:conf/slt/LiZD21, author = {Mohan Li and Catalin Zorila and Rama Doddipatla}, title = {Transformer-Based Online Speech Recognition with Decoder-end Adaptive Computation Steps}, booktitle = {{IEEE} Spoken Language Technology Workshop, {SLT} 2021, Shenzhen, China, January 19-22, 2021}, pages = {1--7}, publisher = {{IEEE}}, year = {2021}, url = {https://doi.org/10.1109/SLT48900.2021.9383613}, doi = {10.1109/SLT48900.2021.9383613}, timestamp = {Thu, 08 Apr 2021 01:00:00 +0200}, biburl = {https://dblp.org/rec/conf/slt/LiZD21.bib}, bibsource = {dblp computer science bibliography, https://dblp.org} }
@inproceedings{DBLP:conf/slt/LiZLH21, author = {Zheng Li and Miao Zhao and Lin Li and Qingyang Hong}, title = {Multi-Feature Learning with Canonical Correlation Analysis Constraint for Text-Independent Speaker Verification}, booktitle = {{IEEE} Spoken Language Technology Workshop, {SLT} 2021, Shenzhen, China, January 19-22, 2021}, pages = {330--337}, publisher = {{IEEE}}, year = {2021}, url = {https://doi.org/10.1109/SLT48900.2021.9383541}, doi = {10.1109/SLT48900.2021.9383541}, timestamp = {Mon, 26 Apr 2021 01:00:00 +0200}, biburl = {https://dblp.org/rec/conf/slt/LiZLH21.bib}, bibsource = {dblp computer science bibliography, https://dblp.org} }
@inproceedings{DBLP:conf/slt/LiZZL21, author = {Xinwei Li and Yuanyuan Zhang and Xiaodan Zhuang and Daben Liu}, title = {Frame-Level Specaugment for Deep Convolutional Neural Networks in Hybrid {ASR} Systems}, booktitle = {{IEEE} Spoken Language Technology Workshop, {SLT} 2021, Shenzhen, China, January 19-22, 2021}, pages = {209--214}, publisher = {{IEEE}}, year = {2021}, url = {https://doi.org/10.1109/SLT48900.2021.9383626}, doi = {10.1109/SLT48900.2021.9383626}, timestamp = {Thu, 08 Apr 2021 01:00:00 +0200}, biburl = {https://dblp.org/rec/conf/slt/LiZZL21.bib}, bibsource = {dblp computer science bibliography, https://dblp.org} }
@inproceedings{DBLP:conf/slt/LinWDF21, author = {Binghuai Lin and Liyuan Wang and Hongwei Ding and Xiaoli Feng}, title = {Improving {L2} English Rhythm Evaluation with Automatic Sentence Stress Detection}, booktitle = {{IEEE} Spoken Language Technology Workshop, {SLT} 2021, Shenzhen, China, January 19-22, 2021}, pages = {713--719}, publisher = {{IEEE}}, year = {2021}, url = {https://doi.org/10.1109/SLT48900.2021.9383455}, doi = {10.1109/SLT48900.2021.9383455}, timestamp = {Thu, 08 Apr 2021 01:00:00 +0200}, biburl = {https://dblp.org/rec/conf/slt/LinWDF21.bib}, bibsource = {dblp computer science bibliography, https://dblp.org} }
@inproceedings{DBLP:conf/slt/Liu0LKSZ21, author = {Chunxi Liu and Frank Zhang and Duc Le and Suyoun Kim and Yatharth Saraf and Geoffrey Zweig}, title = {Improving {RNN} Transducer Based {ASR} with Auxiliary Tasks}, booktitle = {{IEEE} Spoken Language Technology Workshop, {SLT} 2021, Shenzhen, China, January 19-22, 2021}, pages = {172--179}, publisher = {{IEEE}}, year = {2021}, url = {https://doi.org/10.1109/SLT48900.2021.9383548}, doi = {10.1109/SLT48900.2021.9383548}, timestamp = {Thu, 08 Apr 2021 01:00:00 +0200}, biburl = {https://dblp.org/rec/conf/slt/Liu0LKSZ21.bib}, bibsource = {dblp computer science bibliography, https://dblp.org} }
@inproceedings{DBLP:conf/slt/LiuHWYY0M21, author = {Liangqi Liu and Jiankun Hu and Zhiyong Wu and Song Yang and Songfan Yang and Jia Jia and Helen Meng}, title = {Controllable Emphatic Speech Synthesis based on Forward Attention for Expressive Speech Synthesis}, booktitle = {{IEEE} Spoken Language Technology Workshop, {SLT} 2021, Shenzhen, China, January 19-22, 2021}, pages = {410--414}, publisher = {{IEEE}}, year = {2021}, url = {https://doi.org/10.1109/SLT48900.2021.9383537}, doi = {10.1109/SLT48900.2021.9383537}, timestamp = {Sat, 08 May 2021 01:00:00 +0200}, biburl = {https://dblp.org/rec/conf/slt/LiuHWYY0M21.bib}, bibsource = {dblp computer science bibliography, https://dblp.org} }
@inproceedings{DBLP:conf/slt/LiuYXWZC021, author = {Jianming Liu and Meng Yu and Yong Xu and Chao Weng and Shi{-}Xiong Zhang and Lianwu Chen and Dong Yu}, title = {Neural Mask based Multi-channel Convolutional Beamforming for Joint Dereverberation, Echo Cancellation and Denoising}, booktitle = {{IEEE} Spoken Language Technology Workshop, {SLT} 2021, Shenzhen, China, January 19-22, 2021}, pages = {766--770}, publisher = {{IEEE}}, year = {2021}, url = {https://doi.org/10.1109/SLT48900.2021.9383519}, doi = {10.1109/SLT48900.2021.9383519}, timestamp = {Mon, 26 Apr 2021 01:00:00 +0200}, biburl = {https://dblp.org/rec/conf/slt/LiuYXWZC021.bib}, bibsource = {dblp computer science bibliography, https://dblp.org} }
@inproceedings{DBLP:conf/slt/LuLZZ21, author = {Zexin Lu and Jing Li and Yingyi Zhang and Haisong Zhang}, title = {Getting Your Conversation on Track: Estimation of Residual Life for Conversations}, booktitle = {{IEEE} Spoken Language Technology Workshop, {SLT} 2021, Shenzhen, China, January 19-22, 2021}, pages = {1036--1043}, publisher = {{IEEE}}, year = {2021}, url = {https://doi.org/10.1109/SLT48900.2021.9383544}, doi = {10.1109/SLT48900.2021.9383544}, timestamp = {Thu, 14 Oct 2021 01:00:00 +0200}, biburl = {https://dblp.org/rec/conf/slt/LuLZZ21.bib}, bibsource = {dblp computer science bibliography, https://dblp.org} }
@inproceedings{DBLP:conf/slt/LuoWCJX21, author = {Jian Luo and Jianzong Wang and Ning Cheng and Guilin Jiang and Jing Xiao}, title = {Multi-Quartznet: Multi-Resolution Convolution for Speech Recognition with Multi-Layer Feature Fusion}, booktitle = {{IEEE} Spoken Language Technology Workshop, {SLT} 2021, Shenzhen, China, January 19-22, 2021}, pages = {82--88}, publisher = {{IEEE}}, year = {2021}, url = {https://doi.org/10.1109/SLT48900.2021.9383532}, doi = {10.1109/SLT48900.2021.9383532}, timestamp = {Wed, 14 Jun 2023 01:00:00 +0200}, biburl = {https://dblp.org/rec/conf/slt/LuoWCJX21.bib}, bibsource = {dblp computer science bibliography, https://dblp.org} }
@inproceedings{DBLP:conf/slt/LuoWCJX21a, author = {Jian Luo and Jianzong Wang and Ning Cheng and Guilin Jiang and Jing Xiao}, title = {End-To-End Silent Speech Recognition with Acoustic Sensing}, booktitle = {{IEEE} Spoken Language Technology Workshop, {SLT} 2021, Shenzhen, China, January 19-22, 2021}, pages = {606--612}, publisher = {{IEEE}}, year = {2021}, url = {https://doi.org/10.1109/SLT48900.2021.9383622}, doi = {10.1109/SLT48900.2021.9383622}, timestamp = {Wed, 14 Jun 2023 01:00:00 +0200}, biburl = {https://dblp.org/rec/conf/slt/LuoWCJX21a.bib}, bibsource = {dblp computer science bibliography, https://dblp.org} }
@inproceedings{DBLP:conf/slt/LuoZLX21, author = {Haoneng Luo and Shiliang Zhang and Ming Lei and Lei Xie}, title = {Simplified Self-Attention for Transformer-Based end-to-end Speech Recognition}, booktitle = {{IEEE} Spoken Language Technology Workshop, {SLT} 2021, Shenzhen, China, January 19-22, 2021}, pages = {75--81}, publisher = {{IEEE}}, year = {2021}, url = {https://doi.org/10.1109/SLT48900.2021.9383581}, doi = {10.1109/SLT48900.2021.9383581}, timestamp = {Fri, 09 Dec 2022 00:00:00 +0100}, biburl = {https://dblp.org/rec/conf/slt/LuoZLX21.bib}, bibsource = {dblp computer science bibliography, https://dblp.org} }
@inproceedings{DBLP:conf/slt/MacaryTER21, author = {Manon Macary and Marie Tahon and Yannick Est{\`{e}}ve and Anthony Rousseau}, title = {On the Use of Self-Supervised Pre-Trained Acoustic and Linguistic Features for Continuous Speech Emotion Recognition}, booktitle = {{IEEE} Spoken Language Technology Workshop, {SLT} 2021, Shenzhen, China, January 19-22, 2021}, pages = {373--380}, publisher = {{IEEE}}, year = {2021}, url = {https://doi.org/10.1109/SLT48900.2021.9383456}, doi = {10.1109/SLT48900.2021.9383456}, timestamp = {Thu, 08 Apr 2021 01:00:00 +0200}, biburl = {https://dblp.org/rec/conf/slt/MacaryTER21.bib}, bibsource = {dblp computer science bibliography, https://dblp.org} }
@inproceedings{DBLP:conf/slt/MahadeokarSLKSL21, author = {Jay Mahadeokar and Yuan Shangguan and Duc Le and Gil Keren and Hang Su and Thong Le and Ching{-}Feng Yeh and Christian Fuegen and Michael L. Seltzer}, title = {Alignment Restricted Streaming Recurrent Neural Network Transducer}, booktitle = {{IEEE} Spoken Language Technology Workshop, {SLT} 2021, Shenzhen, China, January 19-22, 2021}, pages = {52--59}, publisher = {{IEEE}}, year = {2021}, url = {https://doi.org/10.1109/SLT48900.2021.9383606}, doi = {10.1109/SLT48900.2021.9383606}, timestamp = {Thu, 08 Apr 2021 01:00:00 +0200}, biburl = {https://dblp.org/rec/conf/slt/MahadeokarSLKSL21.bib}, bibsource = {dblp computer science bibliography, https://dblp.org} }
@inproceedings{DBLP:conf/slt/MariniVCZSFDDF21, author = {Marco Marini and Mauro Vigan{\`{o}} and Massimo Corbo and Marina Zettin and Gloria Simoncini and Bruno Fattori and Clelia D'Anna and Massimiliano Donati and Luca Fanucci}, title = {{IDEA:} An Italian Dysarthric Speech Database}, booktitle = {{IEEE} Spoken Language Technology Workshop, {SLT} 2021, Shenzhen, China, January 19-22, 2021}, pages = {1086--1093}, publisher = {{IEEE}}, year = {2021}, url = {https://doi.org/10.1109/SLT48900.2021.9383467}, doi = {10.1109/SLT48900.2021.9383467}, timestamp = {Wed, 07 Dec 2022 00:00:00 +0100}, biburl = {https://dblp.org/rec/conf/slt/MariniVCZSFDDF21.bib}, bibsource = {dblp computer science bibliography, https://dblp.org} }
@inproceedings{DBLP:conf/slt/MasumuraMITTO21, author = {Ryo Masumura and Naoki Makishima and Mana Ihori and Akihiko Takashima and Tomohiro Tanaka and Shota Orihashi}, title = {Large-Context Conversational Representation Learning: Self-Supervised Learning For Conversational Documents}, booktitle = {{IEEE} Spoken Language Technology Workshop, {SLT} 2021, Shenzhen, China, January 19-22, 2021}, pages = {1012--1019}, publisher = {{IEEE}}, year = {2021}, url = {https://doi.org/10.1109/SLT48900.2021.9383584}, doi = {10.1109/SLT48900.2021.9383584}, timestamp = {Thu, 08 Apr 2021 01:00:00 +0200}, biburl = {https://dblp.org/rec/conf/slt/MasumuraMITTO21.bib}, bibsource = {dblp computer science bibliography, https://dblp.org} }
@inproceedings{DBLP:conf/slt/MeghananiSR21, author = {Amit Meghanani and Chandran Savithri Anoop and A. G. Ramakrishnan}, title = {An Exploration of Log-Mel Spectrogram and {MFCC} Features for Alzheimer's Dementia Recognition from Spontaneous Speech}, booktitle = {{IEEE} Spoken Language Technology Workshop, {SLT} 2021, Shenzhen, China, January 19-22, 2021}, pages = {670--677}, publisher = {{IEEE}}, year = {2021}, url = {https://doi.org/10.1109/SLT48900.2021.9383491}, doi = {10.1109/SLT48900.2021.9383491}, timestamp = {Mon, 25 Dec 2023 00:00:00 +0100}, biburl = {https://dblp.org/rec/conf/slt/MeghananiSR21.bib}, bibsource = {dblp computer science bibliography, https://dblp.org} }
@inproceedings{DBLP:conf/slt/MengPSGKLCZLG21, author = {Zhong Meng and Sarangarajan Parthasarathy and Eric Sun and Yashesh Gaur and Naoyuki Kanda and Liang Lu and Xie Chen and Rui Zhao and Jinyu Li and Yifan Gong}, title = {Internal Language Model Estimation for Domain-Adaptive End-to-End Speech Recognition}, booktitle = {{IEEE} Spoken Language Technology Workshop, {SLT} 2021, Shenzhen, China, January 19-22, 2021}, pages = {243--250}, publisher = {{IEEE}}, year = {2021}, url = {https://doi.org/10.1109/SLT48900.2021.9383515}, doi = {10.1109/SLT48900.2021.9383515}, timestamp = {Tue, 21 Mar 2023 00:00:00 +0100}, biburl = {https://dblp.org/rec/conf/slt/MengPSGKLCZLG21.bib}, bibsource = {dblp computer science bibliography, https://dblp.org} }
@inproceedings{DBLP:conf/slt/MeyerXF21, author = {Patrick Meyer and Ziyi Xu and Tim Fingscheidt}, title = {Improving Convolutional Recurrent Neural Networks for Speech Emotion Recognition}, booktitle = {{IEEE} Spoken Language Technology Workshop, {SLT} 2021, Shenzhen, China, January 19-22, 2021}, pages = {365--372}, publisher = {{IEEE}}, year = {2021}, url = {https://doi.org/10.1109/SLT48900.2021.9383513}, doi = {10.1109/SLT48900.2021.9383513}, timestamp = {Sat, 30 Sep 2023 01:00:00 +0200}, biburl = {https://dblp.org/rec/conf/slt/MeyerXF21.bib}, bibsource = {dblp computer science bibliography, https://dblp.org} }
@inproceedings{DBLP:conf/slt/NakadaiFT21, author = {Kazuhiro Nakadai and Yosuke Fukumoto and Ryu Takeda}, title = {Investigation of Node Pruning Criteria for Neural Networks Model Compression with Non-Linear Function and Non-Uniform Network Topology}, booktitle = {{IEEE} Spoken Language Technology Workshop, {SLT} 2021, Shenzhen, China, January 19-22, 2021}, pages = {117--124}, publisher = {{IEEE}}, year = {2021}, url = {https://doi.org/10.1109/SLT48900.2021.9383593}, doi = {10.1109/SLT48900.2021.9383593}, timestamp = {Mon, 26 Jun 2023 01:00:00 +0200}, biburl = {https://dblp.org/rec/conf/slt/NakadaiFT21.bib}, bibsource = {dblp computer science bibliography, https://dblp.org} }
@inproceedings{DBLP:conf/slt/NamazifarTH21, author = {Mahdi Namazifar and G{\"{o}}khan T{\"{u}}r and Dilek Hakkani{-}T{\"{u}}r}, title = {Warped Language Models for Noise Robust Language Understanding}, booktitle = {{IEEE} Spoken Language Technology Workshop, {SLT} 2021, Shenzhen, China, January 19-22, 2021}, pages = {981--988}, publisher = {{IEEE}}, year = {2021}, url = {https://doi.org/10.1109/SLT48900.2021.9383493}, doi = {10.1109/SLT48900.2021.9383493}, timestamp = {Thu, 08 Apr 2021 01:00:00 +0200}, biburl = {https://dblp.org/rec/conf/slt/NamazifarTH21.bib}, bibsource = {dblp computer science bibliography, https://dblp.org} }
@inproceedings{DBLP:conf/slt/NeumannV21, author = {Michael Neumann and Ngoc Thang Vu}, title = {Investigations on audiovisual emotion recognition in noisy conditions}, booktitle = {{IEEE} Spoken Language Technology Workshop, {SLT} 2021, Shenzhen, China, January 19-22, 2021}, pages = {358--364}, publisher = {{IEEE}}, year = {2021}, url = {https://doi.org/10.1109/SLT48900.2021.9383588}, doi = {10.1109/SLT48900.2021.9383588}, timestamp = {Thu, 08 Apr 2021 01:00:00 +0200}, biburl = {https://dblp.org/rec/conf/slt/NeumannV21.bib}, bibsource = {dblp computer science bibliography, https://dblp.org} }
@inproceedings{DBLP:conf/slt/NiXYWZYM21, author = {Zhaoheng Ni and Yong Xu and Meng Yu and Bo Wu and Shi{-}Xiong Zhang and Dong Yu and Michael I. Mandel}, title = {{WPD++:} An Improved Neural Beamformer for Simultaneous Speech Separation and Dereverberation}, booktitle = {{IEEE} Spoken Language Technology Workshop, {SLT} 2021, Shenzhen, China, January 19-22, 2021}, pages = {817--824}, publisher = {{IEEE}}, year = {2021}, url = {https://doi.org/10.1109/SLT48900.2021.9383528}, doi = {10.1109/SLT48900.2021.9383528}, timestamp = {Fri, 23 Apr 2021 01:00:00 +0200}, biburl = {https://dblp.org/rec/conf/slt/NiXYWZYM21.bib}, bibsource = {dblp computer science bibliography, https://dblp.org} }
@inproceedings{DBLP:conf/slt/OneataCSC21, author = {Dan Oneata and Alexandru Caranica and Adriana Stan and Horia Cucu}, title = {An Evaluation of Word-Level Confidence Estimation for End-to-End Automatic Speech Recognition}, booktitle = {{IEEE} Spoken Language Technology Workshop, {SLT} 2021, Shenzhen, China, January 19-22, 2021}, pages = {258--265}, publisher = {{IEEE}}, year = {2021}, url = {https://doi.org/10.1109/SLT48900.2021.9383570}, doi = {10.1109/SLT48900.2021.9383570}, timestamp = {Sun, 25 Jul 2021 01:00:00 +0200}, biburl = {https://dblp.org/rec/conf/slt/OneataCSC21.bib}, bibsource = {dblp computer science bibliography, https://dblp.org} }
@inproceedings{DBLP:conf/slt/PandeyLWS21, author = {Ashutosh Pandey and Chunxi Liu and Yun Wang and Yatharth Saraf}, title = {Dual Application of Speech Enhancement for Automatic Speech Recognition}, booktitle = {{IEEE} Spoken Language Technology Workshop, {SLT} 2021, Shenzhen, China, January 19-22, 2021}, pages = {223--228}, publisher = {{IEEE}}, year = {2021}, url = {https://doi.org/10.1109/SLT48900.2021.9383624}, doi = {10.1109/SLT48900.2021.9383624}, timestamp = {Tue, 30 Nov 2021 00:00:00 +0100}, biburl = {https://dblp.org/rec/conf/slt/PandeyLWS21.bib}, bibsource = {dblp computer science bibliography, https://dblp.org} }
@inproceedings{DBLP:conf/slt/ParkKS21, author = {Jinhwan Park and Chanwoo Kim and Wonyong Sung}, title = {Convolution-Based Attention Model With Positional Encoding For Streaming Speech Recognition On Embedded Devices}, booktitle = {{IEEE} Spoken Language Technology Workshop, {SLT} 2021, Shenzhen, China, January 19-22, 2021}, pages = {30--37}, publisher = {{IEEE}}, year = {2021}, url = {https://doi.org/10.1109/SLT48900.2021.9383583}, doi = {10.1109/SLT48900.2021.9383583}, timestamp = {Mon, 24 Apr 2023 01:00:00 +0200}, biburl = {https://dblp.org/rec/conf/slt/ParkKS21.bib}, bibsource = {dblp computer science bibliography, https://dblp.org} }
@inproceedings{DBLP:conf/slt/ParkR21, author = {Su Ji Park and Alan Rozet}, title = {Film Quality Prediction Using Acoustic, Prosodic and Lexical Cues}, booktitle = {{IEEE} Spoken Language Technology Workshop, {SLT} 2021, Shenzhen, China, January 19-22, 2021}, pages = {678--684}, publisher = {{IEEE}}, year = {2021}, url = {https://doi.org/10.1109/SLT48900.2021.9383509}, doi = {10.1109/SLT48900.2021.9383509}, timestamp = {Thu, 08 Apr 2021 01:00:00 +0200}, biburl = {https://dblp.org/rec/conf/slt/ParkR21.bib}, bibsource = {dblp computer science bibliography, https://dblp.org} }
@inproceedings{DBLP:conf/slt/ParthasarathyS21, author = {Srinivas Parthasarathy and Shiva Sundaram}, title = {Detecting Expressions with Multimodal Transformers}, booktitle = {{IEEE} Spoken Language Technology Workshop, {SLT} 2021, Shenzhen, China, January 19-22, 2021}, pages = {636--643}, publisher = {{IEEE}}, year = {2021}, url = {https://doi.org/10.1109/SLT48900.2021.9383573}, doi = {10.1109/SLT48900.2021.9383573}, timestamp = {Thu, 08 Apr 2021 01:00:00 +0200}, biburl = {https://dblp.org/rec/conf/slt/ParthasarathyS21.bib}, bibsource = {dblp computer science bibliography, https://dblp.org} }
@inproceedings{DBLP:conf/slt/PellegriniZM21, author = {Thomas Pellegrini and Romain Zimmer and Timoth{\'{e}}e Masquelier}, title = {Low-Activity Supervised Convolutional Spiking Neural Networks Applied to Speech Commands Recognition}, booktitle = {{IEEE} Spoken Language Technology Workshop, {SLT} 2021, Shenzhen, China, January 19-22, 2021}, pages = {97--103}, publisher = {{IEEE}}, year = {2021}, url = {https://doi.org/10.1109/SLT48900.2021.9383587}, doi = {10.1109/SLT48900.2021.9383587}, timestamp = {Thu, 14 Oct 2021 01:00:00 +0200}, biburl = {https://dblp.org/rec/conf/slt/PellegriniZM21.bib}, bibsource = {dblp computer science bibliography, https://dblp.org} }
@inproceedings{DBLP:conf/slt/PraveenPKRB21, author = {Kiran Praveen and Abhishek Pandey and Deepak Kumar and Shakti Prasad Rath and Sandip Shriram Bapat}, title = {Dynamically Weighted Ensemble Models for Automatic Speech Recognition}, booktitle = {{IEEE} Spoken Language Technology Workshop, {SLT} 2021, Shenzhen, China, January 19-22, 2021}, pages = {111--116}, publisher = {{IEEE}}, year = {2021}, url = {https://doi.org/10.1109/SLT48900.2021.9383463}, doi = {10.1109/SLT48900.2021.9383463}, timestamp = {Thu, 08 Apr 2021 01:00:00 +0200}, biburl = {https://dblp.org/rec/conf/slt/PraveenPKRB21.bib}, bibsource = {dblp computer science bibliography, https://dblp.org} }
@inproceedings{DBLP:conf/slt/RajDCEHH0DYLKLW21, author = {Desh Raj and Pavel Denisov and Zhuo Chen and Hakan Erdogan and Zili Huang and Maokui He and Shinji Watanabe and Jun Du and Takuya Yoshioka and Yi Luo and Naoyuki Kanda and Jinyu Li and Scott Wisdom and John R. Hershey}, title = {Integration of Speech Separation, Diarization, and Recognition for Multi-Speaker Meetings: System Description, Comparison, and Analysis}, booktitle = {{IEEE} Spoken Language Technology Workshop, {SLT} 2021, Shenzhen, China, January 19-22, 2021}, pages = {897--904}, publisher = {{IEEE}}, year = {2021}, url = {https://doi.org/10.1109/SLT48900.2021.9383556}, doi = {10.1109/SLT48900.2021.9383556}, timestamp = {Mon, 05 Feb 2024 00:00:00 +0100}, biburl = {https://dblp.org/rec/conf/slt/RajDCEHH0DYLKLW21.bib}, bibsource = {dblp computer science bibliography, https://dblp.org} }
@inproceedings{DBLP:conf/slt/RajGH0PSK21, author = {Desh Raj and Leibny Paola Garc{\'{\i}}a{-}Perera and Zili Huang and Shinji Watanabe and Daniel Povey and Andreas Stolcke and Sanjeev Khudanpur}, title = {DOVER-Lap: {A} Method for Combining Overlap-Aware Diarization Outputs}, booktitle = {{IEEE} Spoken Language Technology Workshop, {SLT} 2021, Shenzhen, China, January 19-22, 2021}, pages = {881--888}, publisher = {{IEEE}}, year = {2021}, url = {https://doi.org/10.1109/SLT48900.2021.9383490}, doi = {10.1109/SLT48900.2021.9383490}, timestamp = {Mon, 05 Feb 2024 00:00:00 +0100}, biburl = {https://dblp.org/rec/conf/slt/RajGH0PSK21.bib}, bibsource = {dblp computer science bibliography, https://dblp.org} }
@inproceedings{DBLP:conf/slt/RajHK21, author = {Desh Raj and Zili Huang and Sanjeev Khudanpur}, title = {Multi-Class Spectral Clustering with Overlaps for Speaker Diarization}, booktitle = {{IEEE} Spoken Language Technology Workshop, {SLT} 2021, Shenzhen, China, January 19-22, 2021}, pages = {582--589}, publisher = {{IEEE}}, year = {2021}, url = {https://doi.org/10.1109/SLT48900.2021.9383602}, doi = {10.1109/SLT48900.2021.9383602}, timestamp = {Mon, 05 Feb 2024 00:00:00 +0100}, biburl = {https://dblp.org/rec/conf/slt/RajHK21.bib}, bibsource = {dblp computer science bibliography, https://dblp.org} }
@inproceedings{DBLP:conf/slt/RaoPK21, author = {Hrishikesh Rao and Kedar Phatak and Elie Khoury}, title = {Improving Speaker Recognition with Quality Indicators}, booktitle = {{IEEE} Spoken Language Technology Workshop, {SLT} 2021, Shenzhen, China, January 19-22, 2021}, pages = {338--343}, publisher = {{IEEE}}, year = {2021}, url = {https://doi.org/10.1109/SLT48900.2021.9383627}, doi = {10.1109/SLT48900.2021.9383627}, timestamp = {Thu, 15 Jul 2021 01:00:00 +0200}, biburl = {https://dblp.org/rec/conf/slt/RaoPK21.bib}, bibsource = {dblp computer science bibliography, https://dblp.org} }
@inproceedings{DBLP:conf/slt/RibeiroSZEWRR21, author = {Manuel Sam Ribeiro and Jennifer Sanger and Jing{-}Xuan Zhang and Aciel Eshky and Alan Wrench and Korin Richmond and Steve Renals}, title = {Tal: {A} Synchronised Multi-Speaker Corpus of Ultrasound Tongue Imaging, Audio, and Lip Videos}, booktitle = {{IEEE} Spoken Language Technology Workshop, {SLT} 2021, Shenzhen, China, January 19-22, 2021}, pages = {1109--1116}, publisher = {{IEEE}}, year = {2021}, url = {https://doi.org/10.1109/SLT48900.2021.9383619}, doi = {10.1109/SLT48900.2021.9383619}, timestamp = {Tue, 21 Mar 2023 00:00:00 +0100}, biburl = {https://dblp.org/rec/conf/slt/RibeiroSZEWRR21.bib}, bibsource = {dblp computer science bibliography, https://dblp.org} }
@inproceedings{DBLP:conf/slt/RiviereD21, author = {Morgane Rivi{\`{e}}re and Emmanuel Dupoux}, title = {Towards Unsupervised Learning of Speech Features in the Wild}, booktitle = {{IEEE} Spoken Language Technology Workshop, {SLT} 2021, Shenzhen, China, January 19-22, 2021}, pages = {156--163}, publisher = {{IEEE}}, year = {2021}, url = {https://doi.org/10.1109/SLT48900.2021.9383461}, doi = {10.1109/SLT48900.2021.9383461}, timestamp = {Thu, 08 Apr 2021 01:00:00 +0200}, biburl = {https://dblp.org/rec/conf/slt/RiviereD21.bib}, bibsource = {dblp computer science bibliography, https://dblp.org} }
@inproceedings{DBLP:conf/slt/RutowskiSHLOC21, author = {Tomek Rutowski and Elizabeth Shriberg and Amir Harati and Yang Lu and Ricardo Oliveira and Piotr Chlebek}, title = {Cross-Demographic Portability of Deep NLP-Based Depression Models}, booktitle = {{IEEE} Spoken Language Technology Workshop, {SLT} 2021, Shenzhen, China, January 19-22, 2021}, pages = {1052--1057}, publisher = {{IEEE}}, year = {2021}, url = {https://doi.org/10.1109/SLT48900.2021.9383609}, doi = {10.1109/SLT48900.2021.9383609}, timestamp = {Thu, 08 Apr 2021 01:00:00 +0200}, biburl = {https://dblp.org/rec/conf/slt/RutowskiSHLOC21.bib}, bibsource = {dblp computer science bibliography, https://dblp.org} }
@inproceedings{DBLP:conf/slt/SaekiMKOK21, author = {Mao Saeki and Yoichi Matsuyama and Satoshi Kobashikawa and Tetsuji Ogawa and Tetsunori Kobayashi}, title = {Analysis of Multimodal Features for Speaking Proficiency Scoring in an Interview Dialogue}, booktitle = {{IEEE} Spoken Language Technology Workshop, {SLT} 2021, Shenzhen, China, January 19-22, 2021}, pages = {629--635}, publisher = {{IEEE}}, year = {2021}, url = {https://doi.org/10.1109/SLT48900.2021.9383590}, doi = {10.1109/SLT48900.2021.9383590}, timestamp = {Thu, 14 Oct 2021 01:00:00 +0200}, biburl = {https://dblp.org/rec/conf/slt/SaekiMKOK21.bib}, bibsource = {dblp computer science bibliography, https://dblp.org} }
@inproceedings{DBLP:conf/slt/SahidullahSVLSK21, author = {Md. Sahidullah and Achintya Kumar Sarkar and Ville Vestman and Xuechen Liu and Romain Serizel and Tomi Kinnunen and Zheng{-}Hua Tan and Emmanuel Vincent}, title = {{UIAI} System for Short-Duration Speaker Verification Challenge 2020}, booktitle = {{IEEE} Spoken Language Technology Workshop, {SLT} 2021, Shenzhen, China, January 19-22, 2021}, pages = {323--329}, publisher = {{IEEE}}, year = {2021}, url = {https://doi.org/10.1109/SLT48900.2021.9383596}, doi = {10.1109/SLT48900.2021.9383596}, timestamp = {Thu, 08 Apr 2021 01:00:00 +0200}, biburl = {https://dblp.org/rec/conf/slt/SahidullahSVLSK21.bib}, bibsource = {dblp computer science bibliography, https://dblp.org} }
@inproceedings{DBLP:conf/slt/SantosAWX21, author = {Timothy Israel Santos and Andrew Abel and Nick Wilson and Yan Xu}, title = {Speaker-Independent Visual Speech Recognition with the Inception {V3} Model}, booktitle = {{IEEE} Spoken Language Technology Workshop, {SLT} 2021, Shenzhen, China, January 19-22, 2021}, pages = {613--620}, publisher = {{IEEE}}, year = {2021}, url = {https://doi.org/10.1109/SLT48900.2021.9383540}, doi = {10.1109/SLT48900.2021.9383540}, timestamp = {Thu, 14 Oct 2021 01:00:00 +0200}, biburl = {https://dblp.org/rec/conf/slt/SantosAWX21.bib}, bibsource = {dblp computer science bibliography, https://dblp.org} }
@inproceedings{DBLP:conf/slt/SatoOKDNA21, author = {Hiroshi Sato and Tsubasa Ochiai and Keisuke Kinoshita and Marc Delcroix and Tomohiro Nakatani and Shoko Araki}, title = {Multimodal Attention Fusion for Target Speaker Extraction}, booktitle = {{IEEE} Spoken Language Technology Workshop, {SLT} 2021, Shenzhen, China, January 19-22, 2021}, pages = {778--784}, publisher = {{IEEE}}, year = {2021}, url = {https://doi.org/10.1109/SLT48900.2021.9383539}, doi = {10.1109/SLT48900.2021.9383539}, timestamp = {Sun, 12 Nov 2023 00:00:00 +0100}, biburl = {https://dblp.org/rec/conf/slt/SatoOKDNA21.bib}, bibsource = {dblp computer science bibliography, https://dblp.org} }
@inproceedings{DBLP:conf/slt/SemenzinHSKC21, author = {Chiara Semenzin and Lisa Hamrick and Amanda Seidl and Bridgette Kelleher and Alejandrina Cristi{\`{a}}}, title = {Towards Large-Scale Data Annotation of Audio from Wearables: Validating Zooniverse Annotations of Infant Vocalization Types}, booktitle = {{IEEE} Spoken Language Technology Workshop, {SLT} 2021, Shenzhen, China, January 19-22, 2021}, pages = {1079--1085}, publisher = {{IEEE}}, year = {2021}, url = {https://doi.org/10.1109/SLT48900.2021.9383511}, doi = {10.1109/SLT48900.2021.9383511}, timestamp = {Thu, 08 Apr 2021 01:00:00 +0200}, biburl = {https://dblp.org/rec/conf/slt/SemenzinHSKC21.bib}, bibsource = {dblp computer science bibliography, https://dblp.org} }
@inproceedings{DBLP:conf/slt/SenAGV21, author = {Bipasha Sen and Aditya Agarwal and Mirishkar Sai Ganesh and Anil Kumar Vuppala}, title = {Reed: An Approach Towards Quickly Bootstrapping Multilingual Acoustic Models}, booktitle = {{IEEE} Spoken Language Technology Workshop, {SLT} 2021, Shenzhen, China, January 19-22, 2021}, pages = {272--279}, publisher = {{IEEE}}, year = {2021}, url = {https://doi.org/10.1109/SLT48900.2021.9383457}, doi = {10.1109/SLT48900.2021.9383457}, timestamp = {Thu, 08 Apr 2021 01:00:00 +0200}, biburl = {https://dblp.org/rec/conf/slt/SenAGV21.bib}, bibsource = {dblp computer science bibliography, https://dblp.org} }
@inproceedings{DBLP:conf/slt/SenayIH21, author = {Gr{\'{e}}gory Senay and Badr Youbi Idrissi and Marine Haziza}, title = {VirAAL: Virtual Adversarial Active Learning for {NLU}}, booktitle = {{IEEE} Spoken Language Technology Workshop, {SLT} 2021, Shenzhen, China, January 19-22, 2021}, pages = {973--980}, publisher = {{IEEE}}, year = {2021}, url = {https://doi.org/10.1109/SLT48900.2021.9383576}, doi = {10.1109/SLT48900.2021.9383576}, timestamp = {Thu, 08 Apr 2021 01:00:00 +0200}, biburl = {https://dblp.org/rec/conf/slt/SenayIH21.bib}, bibsource = {dblp computer science bibliography, https://dblp.org} }
@inproceedings{DBLP:conf/slt/ShechtmanFH21, author = {Slava Shechtman and Raul Fernandez and David Haws}, title = {Supervised and unsupervised approaches for controlling narrow lexical focus in sequence-to-sequence speech synthesis}, booktitle = {{IEEE} Spoken Language Technology Workshop, {SLT} 2021, Shenzhen, China, January 19-22, 2021}, pages = {431--437}, publisher = {{IEEE}}, year = {2021}, url = {https://doi.org/10.1109/SLT48900.2021.9383591}, doi = {10.1109/SLT48900.2021.9383591}, timestamp = {Thu, 08 Apr 2021 01:00:00 +0200}, biburl = {https://dblp.org/rec/conf/slt/ShechtmanFH21.bib}, bibsource = {dblp computer science bibliography, https://dblp.org} }
@inproceedings{DBLP:conf/slt/ShekarBH21, author = {Ram C. M. C. Shekar and Chelzy Belitz and John H. L. Hansen}, title = {Development of CNN-Based Cochlear Implant and Normal Hearing Sound Recognition Models Using Natural and Auralized Environmental Audio}, booktitle = {{IEEE} Spoken Language Technology Workshop, {SLT} 2021, Shenzhen, China, January 19-22, 2021}, pages = {728--733}, publisher = {{IEEE}}, year = {2021}, url = {https://doi.org/10.1109/SLT48900.2021.9383550}, doi = {10.1109/SLT48900.2021.9383550}, timestamp = {Thu, 08 Apr 2021 01:00:00 +0200}, biburl = {https://dblp.org/rec/conf/slt/ShekarBH21.bib}, bibsource = {dblp computer science bibliography, https://dblp.org} }
@inproceedings{DBLP:conf/slt/ShenYSMS21, author = {Yang Shen and Ayano Yasukagawa and Daisuke Saito and Nobuaki Minematsu and Kazuya Saito}, title = {Optimized Prediction of Fluency of {L2} English Based on Interpretable Network Using Quantity of Phonation and Quality of Pronunciation}, booktitle = {{IEEE} Spoken Language Technology Workshop, {SLT} 2021, Shenzhen, China, January 19-22, 2021}, pages = {698--704}, publisher = {{IEEE}}, year = {2021}, url = {https://doi.org/10.1109/SLT48900.2021.9383458}, doi = {10.1109/SLT48900.2021.9383458}, timestamp = {Thu, 08 Apr 2021 01:00:00 +0200}, biburl = {https://dblp.org/rec/conf/slt/ShenYSMS21.bib}, bibsource = {dblp computer science bibliography, https://dblp.org} }
@inproceedings{DBLP:conf/slt/ShiCTL0H21, author = {Ying Shi and Haolin Chen and Zhiyuan Tang and Lantian Li and Dong Wang and Jiqing Han}, title = {Can We Trust Deep Speech Prior?}, booktitle = {{IEEE} Spoken Language Technology Workshop, {SLT} 2021, Shenzhen, China, January 19-22, 2021}, pages = {742--749}, publisher = {{IEEE}}, year = {2021}, url = {https://doi.org/10.1109/SLT48900.2021.9383499}, doi = {10.1109/SLT48900.2021.9383499}, timestamp = {Thu, 26 Oct 2023 01:00:00 +0200}, biburl = {https://dblp.org/rec/conf/slt/ShiCTL0H21.bib}, bibsource = {dblp computer science bibliography, https://dblp.org} }
@inproceedings{DBLP:conf/slt/ShiH21, author = {Yanpei Shi and Thomas Hain}, title = {Contextual Joint Factor Acoustic Embeddings}, booktitle = {{IEEE} Spoken Language Technology Workshop, {SLT} 2021, Shenzhen, China, January 19-22, 2021}, pages = {750--757}, publisher = {{IEEE}}, year = {2021}, url = {https://doi.org/10.1109/SLT48900.2021.9383592}, doi = {10.1109/SLT48900.2021.9383592}, timestamp = {Sun, 25 Jul 2021 01:00:00 +0200}, biburl = {https://dblp.org/rec/conf/slt/ShiH21.bib}, bibsource = {dblp computer science bibliography, https://dblp.org} }
@inproceedings{DBLP:conf/slt/ShiH21a, author = {Yanpei Shi and Thomas Hain}, title = {Supervised Speaker Embedding De-Mixing in Two-Speaker Environment}, booktitle = {{IEEE} Spoken Language Technology Workshop, {SLT} 2021, Shenzhen, China, January 19-22, 2021}, pages = {758--765}, publisher = {{IEEE}}, year = {2021}, url = {https://doi.org/10.1109/SLT48900.2021.9383580}, doi = {10.1109/SLT48900.2021.9383580}, timestamp = {Sun, 25 Jul 2021 01:00:00 +0200}, biburl = {https://dblp.org/rec/conf/slt/ShiH21a.bib}, bibsource = {dblp computer science bibliography, https://dblp.org} }
@inproceedings{DBLP:conf/slt/ShiSL21, author = {Bowen Shi and Shane Settle and Karen Livescu}, title = {Whole-Word Segmental Speech Recognition with Acoustic Word Embeddings}, booktitle = {{IEEE} Spoken Language Technology Workshop, {SLT} 2021, Shenzhen, China, January 19-22, 2021}, pages = {164--171}, publisher = {{IEEE}}, year = {2021}, url = {https://doi.org/10.1109/SLT48900.2021.9383578}, doi = {10.1109/SLT48900.2021.9383578}, timestamp = {Thu, 08 Apr 2021 01:00:00 +0200}, biburl = {https://dblp.org/rec/conf/slt/ShiSL21.bib}, bibsource = {dblp computer science bibliography, https://dblp.org} }
@inproceedings{DBLP:conf/slt/ShibataZS21, author = {Hayato Shibata and Mingxin Zhang and Takahiro Shinozaki}, title = {Unsupervised Acoustic-to-Articulatory Inversion Neural Network Learning Based on Deterministic Policy Gradient}, booktitle = {{IEEE} Spoken Language Technology Workshop, {SLT} 2021, Shenzhen, China, January 19-22, 2021}, pages = {530--537}, publisher = {{IEEE}}, year = {2021}, url = {https://doi.org/10.1109/SLT48900.2021.9383554}, doi = {10.1109/SLT48900.2021.9383554}, timestamp = {Thu, 08 Apr 2021 01:00:00 +0200}, biburl = {https://dblp.org/rec/conf/slt/ShibataZS21.bib}, bibsource = {dblp computer science bibliography, https://dblp.org} }
@inproceedings{DBLP:conf/slt/Shivakumar0GN21, author = {Prashanth Gurunath Shivakumar and Naveen Kumar and Panayiotis G. Georgiou and Shrikanth Narayanan}, title = {{RNN} Based Incremental Online Spoken Language Understanding}, booktitle = {{IEEE} Spoken Language Technology Workshop, {SLT} 2021, Shenzhen, China, January 19-22, 2021}, pages = {989--996}, publisher = {{IEEE}}, year = {2021}, url = {https://doi.org/10.1109/SLT48900.2021.9383614}, doi = {10.1109/SLT48900.2021.9383614}, timestamp = {Thu, 08 Apr 2021 01:00:00 +0200}, biburl = {https://dblp.org/rec/conf/slt/Shivakumar0GN21.bib}, bibsource = {dblp computer science bibliography, https://dblp.org} }
@inproceedings{DBLP:conf/slt/SongYHKKK21, author = {Eunwoo Song and Ryuichi Yamamoto and Min{-}Jae Hwang and Jin{-}Seob Kim and Ohsung Kwon and Jae{-}Min Kim}, title = {Improved Parallel Wavegan Vocoder with Perceptually Weighted Spectrogram Loss}, booktitle = {{IEEE} Spoken Language Technology Workshop, {SLT} 2021, Shenzhen, China, January 19-22, 2021}, pages = {470--476}, publisher = {{IEEE}}, year = {2021}, url = {https://doi.org/10.1109/SLT48900.2021.9383549}, doi = {10.1109/SLT48900.2021.9383549}, timestamp = {Thu, 08 Apr 2021 01:00:00 +0200}, biburl = {https://dblp.org/rec/conf/slt/SongYHKKK21.bib}, bibsource = {dblp computer science bibliography, https://dblp.org} }
@inproceedings{DBLP:conf/slt/SongZWH21, author = {Minguang Song and Yunxin Zhao and Shaojun Wang and Mei Han}, title = {Word Similarity Based Label Smoothing in Rnnlm Training for {ASR}}, booktitle = {{IEEE} Spoken Language Technology Workshop, {SLT} 2021, Shenzhen, China, January 19-22, 2021}, pages = {280--285}, publisher = {{IEEE}}, year = {2021}, url = {https://doi.org/10.1109/SLT48900.2021.9383598}, doi = {10.1109/SLT48900.2021.9383598}, timestamp = {Thu, 08 Apr 2021 01:00:00 +0200}, biburl = {https://dblp.org/rec/conf/slt/SongZWH21.bib}, bibsource = {dblp computer science bibliography, https://dblp.org} }
@inproceedings{DBLP:conf/slt/StadenK21, author = {Lisa van Staden and Herman Kamper}, title = {A Comparison of Self-Supervised Speech Representations As Input Features For Unsupervised Acoustic Word Embeddings}, booktitle = {{IEEE} Spoken Language Technology Workshop, {SLT} 2021, Shenzhen, China, January 19-22, 2021}, pages = {927--934}, publisher = {{IEEE}}, year = {2021}, url = {https://doi.org/10.1109/SLT48900.2021.9383625}, doi = {10.1109/SLT48900.2021.9383625}, timestamp = {Thu, 14 Oct 2021 01:00:00 +0200}, biburl = {https://dblp.org/rec/conf/slt/StadenK21.bib}, bibsource = {dblp computer science bibliography, https://dblp.org} }
@inproceedings{DBLP:conf/slt/SterpuSH21, author = {George Sterpu and Christian Saam and Naomi Harte}, title = {Learning to Count Words in Fluent Speech Enables Online Speech Recognition}, booktitle = {{IEEE} Spoken Language Technology Workshop, {SLT} 2021, Shenzhen, China, January 19-22, 2021}, pages = {38--45}, publisher = {{IEEE}}, year = {2021}, url = {https://doi.org/10.1109/SLT48900.2021.9383563}, doi = {10.1109/SLT48900.2021.9383563}, timestamp = {Thu, 08 Apr 2021 01:00:00 +0200}, biburl = {https://dblp.org/rec/conf/slt/SterpuSH21.bib}, bibsource = {dblp computer science bibliography, https://dblp.org} }
@inproceedings{DBLP:conf/slt/SuL21, author = {Bo{-}Hao Su and Chi{-}Chun Lee}, title = {A Conditional Cycle Emotion Gan for Cross Corpus Speech Emotion Recognition}, booktitle = {{IEEE} Spoken Language Technology Workshop, {SLT} 2021, Shenzhen, China, January 19-22, 2021}, pages = {351--357}, publisher = {{IEEE}}, year = {2021}, url = {https://doi.org/10.1109/SLT48900.2021.9383512}, doi = {10.1109/SLT48900.2021.9383512}, timestamp = {Mon, 05 Feb 2024 00:00:00 +0100}, biburl = {https://dblp.org/rec/conf/slt/SuL21.bib}, bibsource = {dblp computer science bibliography, https://dblp.org} }
@inproceedings{DBLP:conf/slt/SudroD0P21, author = {Protima Nomo Sudro and Rohan Kumar Das and Rohit Sinha and S. R. Mahadeva Prasanna}, title = {Enhancing the Intelligibility of Cleft Lip and Palate Speech Using Cycle-Consistent Adversarial Networks}, booktitle = {{IEEE} Spoken Language Technology Workshop, {SLT} 2021, Shenzhen, China, January 19-22, 2021}, pages = {720--727}, publisher = {{IEEE}}, year = {2021}, url = {https://doi.org/10.1109/SLT48900.2021.9383543}, doi = {10.1109/SLT48900.2021.9383543}, timestamp = {Thu, 23 Jun 2022 01:00:00 +0200}, biburl = {https://dblp.org/rec/conf/slt/SudroD0P21.bib}, bibsource = {dblp computer science bibliography, https://dblp.org} }
@inproceedings{DBLP:conf/slt/SunWCPZKX21, author = {Aolan Sun and Jianzong Wang and Ning Cheng and Huayi Peng and Zhen Zeng and Lingwei Kong and Jing Xiao}, title = {GraphPB: Graphical Representations of Prosody Boundary in Speech Synthesis}, booktitle = {{IEEE} Spoken Language Technology Workshop, {SLT} 2021, Shenzhen, China, January 19-22, 2021}, pages = {438--445}, publisher = {{IEEE}}, year = {2021}, url = {https://doi.org/10.1109/SLT48900.2021.9383530}, doi = {10.1109/SLT48900.2021.9383530}, timestamp = {Wed, 14 Jun 2023 01:00:00 +0200}, biburl = {https://dblp.org/rec/conf/slt/SunWCPZKX21.bib}, bibsource = {dblp computer science bibliography, https://dblp.org} }
@inproceedings{DBLP:conf/slt/SwarupCSTAG21, author = {Prakhar Swarup and Debmalya Chakrabarty and Ashtosh Sapru and Hitesh Tulsiani and Harish Arsikere and Sri Garimella}, title = {Efficient Large Scale Semi-Supervised Learning for {CTC} Based Acoustic Models}, booktitle = {{IEEE} Spoken Language Technology Workshop, {SLT} 2021, Shenzhen, China, January 19-22, 2021}, pages = {148--155}, publisher = {{IEEE}}, year = {2021}, url = {https://doi.org/10.1109/SLT48900.2021.9383536}, doi = {10.1109/SLT48900.2021.9383536}, timestamp = {Thu, 08 Apr 2021 01:00:00 +0200}, biburl = {https://dblp.org/rec/conf/slt/SwarupCSTAG21.bib}, bibsource = {dblp computer science bibliography, https://dblp.org} }
@inproceedings{DBLP:conf/slt/TakashimaF0HGN21, author = {Yuki Takashima and Yusuke Fujita and Shinji Watanabe and Shota Horiguchi and Paola Garc{\'{\i}}a and Kenji Nagamatsu}, title = {End-to-End Speaker Diarization Conditioned on Speech Activity and Overlap Detection}, booktitle = {{IEEE} Spoken Language Technology Workshop, {SLT} 2021, Shenzhen, China, January 19-22, 2021}, pages = {849--856}, publisher = {{IEEE}}, year = {2021}, url = {https://doi.org/10.1109/SLT48900.2021.9383555}, doi = {10.1109/SLT48900.2021.9383555}, timestamp = {Thu, 07 Sep 2023 01:00:00 +0200}, biburl = {https://dblp.org/rec/conf/slt/TakashimaF0HGN21.bib}, bibsource = {dblp computer science bibliography, https://dblp.org} }
@inproceedings{DBLP:conf/slt/TakatsuOMHFK21, author = {Hiroaki Takatsu and Mayu Okuda and Yoichi Matsuyama and Hiroshi Honda and Shinya Fujie and Tetsunori Kobayashi}, title = {Personalized Extractive Summarization for a News Dialogue System}, booktitle = {{IEEE} Spoken Language Technology Workshop, {SLT} 2021, Shenzhen, China, January 19-22, 2021}, pages = {1044--1051}, publisher = {{IEEE}}, year = {2021}, url = {https://doi.org/10.1109/SLT48900.2021.9383568}, doi = {10.1109/SLT48900.2021.9383568}, timestamp = {Thu, 14 Oct 2021 01:00:00 +0200}, biburl = {https://dblp.org/rec/conf/slt/TakatsuOMHFK21.bib}, bibsource = {dblp computer science bibliography, https://dblp.org} }
@inproceedings{DBLP:conf/slt/TongHMJPCRM21, author = {Xiaosu Tong and Che{-}Wei Huang and Sri Harish Mallidi and Shaun Joseph and Sonal Pareek and Chander Chandak and Ariya Rastrow and Roland Maas}, title = {Streaming ResLSTM with Causal Mean Aggregation for Device-Directed Utterance Detection}, booktitle = {{IEEE} Spoken Language Technology Workshop, {SLT} 2021, Shenzhen, China, January 19-22, 2021}, pages = {659--664}, publisher = {{IEEE}}, year = {2021}, url = {https://doi.org/10.1109/SLT48900.2021.9383607}, doi = {10.1109/SLT48900.2021.9383607}, timestamp = {Thu, 08 Apr 2021 01:00:00 +0200}, biburl = {https://dblp.org/rec/conf/slt/TongHMJPCRM21.bib}, bibsource = {dblp computer science bibliography, https://dblp.org} }
@inproceedings{DBLP:conf/slt/TsunooK021, author = {Emiru Tsunoo and Yosuke Kashiwagi and Shinji Watanabe}, title = {Streaming Transformer Asr With Blockwise Synchronous Beam Search}, booktitle = {{IEEE} Spoken Language Technology Workshop, {SLT} 2021, Shenzhen, China, January 19-22, 2021}, pages = {22--29}, publisher = {{IEEE}}, year = {2021}, url = {https://doi.org/10.1109/SLT48900.2021.9383517}, doi = {10.1109/SLT48900.2021.9383517}, timestamp = {Tue, 21 Mar 2023 00:00:00 +0100}, biburl = {https://dblp.org/rec/conf/slt/TsunooK021.bib}, bibsource = {dblp computer science bibliography, https://dblp.org} }
@inproceedings{DBLP:conf/slt/UnluA21, author = {Merve {\"{U}}nl{\"{u}} and Ebru Arisoy}, title = {Uncertainty-Aware Representations for Spoken Question Answering}, booktitle = {{IEEE} Spoken Language Technology Workshop, {SLT} 2021, Shenzhen, China, January 19-22, 2021}, pages = {943--949}, publisher = {{IEEE}}, year = {2021}, url = {https://doi.org/10.1109/SLT48900.2021.9383547}, doi = {10.1109/SLT48900.2021.9383547}, timestamp = {Thu, 23 Jun 2022 01:00:00 +0200}, biburl = {https://dblp.org/rec/conf/slt/UnluA21.bib}, bibsource = {dblp computer science bibliography, https://dblp.org} }
@inproceedings{DBLP:conf/slt/ValkA21, author = {J{\"{o}}rgen Valk and Tanel Alum{\"{a}}e}, title = {{VOXLINGUA107:} {A} Dataset for Spoken Language Recognition}, booktitle = {{IEEE} Spoken Language Technology Workshop, {SLT} 2021, Shenzhen, China, January 19-22, 2021}, pages = {652--658}, publisher = {{IEEE}}, year = {2021}, url = {https://doi.org/10.1109/SLT48900.2021.9383459}, doi = {10.1109/SLT48900.2021.9383459}, timestamp = {Wed, 16 Mar 2022 00:00:00 +0100}, biburl = {https://dblp.org/rec/conf/slt/ValkA21.bib}, bibsource = {dblp computer science bibliography, https://dblp.org} }
@inproceedings{DBLP:conf/slt/WangEQM21, author = {Xinhao Wang and Keelan Evanini and Yao Qian and Matthew Mulholland}, title = {Automated Scoring of Spontaneous Speech from Young Learners of English Using Transformers}, booktitle = {{IEEE} Spoken Language Technology Workshop, {SLT} 2021, Shenzhen, China, January 19-22, 2021}, pages = {705--712}, publisher = {{IEEE}}, year = {2021}, url = {https://doi.org/10.1109/SLT48900.2021.9383553}, doi = {10.1109/SLT48900.2021.9383553}, timestamp = {Thu, 08 Apr 2021 01:00:00 +0200}, biburl = {https://dblp.org/rec/conf/slt/WangEQM21.bib}, bibsource = {dblp computer science bibliography, https://dblp.org} }
@inproceedings{DBLP:conf/slt/WangEWWR0CH21, author = {Zhong{-}Qiu Wang and Hakan Erdogan and Scott Wisdom and Kevin W. Wilson and Desh Raj and Shinji Watanabe and Zhuo Chen and John R. Hershey}, title = {Sequential Multi-Frame Neural Beamforming for Speech Separation and Enhancement}, booktitle = {{IEEE} Spoken Language Technology Workshop, {SLT} 2021, Shenzhen, China, January 19-22, 2021}, pages = {905--911}, publisher = {{IEEE}}, year = {2021}, url = {https://doi.org/10.1109/SLT48900.2021.9383522}, doi = {10.1109/SLT48900.2021.9383522}, timestamp = {Mon, 05 Feb 2024 00:00:00 +0100}, biburl = {https://dblp.org/rec/conf/slt/WangEWWR0CH21.bib}, bibsource = {dblp computer science bibliography, https://dblp.org} }
@inproceedings{DBLP:conf/slt/WangKGCMY21, author = {Xiaofei Wang and Naoyuki Kanda and Yashesh Gaur and Zhuo Chen and Zhong Meng and Takuya Yoshioka}, title = {Exploring End-to-End Multi-Channel {ASR} with Bias Information for Meeting Transcription}, booktitle = {{IEEE} Spoken Language Technology Workshop, {SLT} 2021, Shenzhen, China, January 19-22, 2021}, pages = {833--840}, publisher = {{IEEE}}, year = {2021}, url = {https://doi.org/10.1109/SLT48900.2021.9383500}, doi = {10.1109/SLT48900.2021.9383500}, timestamp = {Wed, 19 Oct 2022 01:00:00 +0200}, biburl = {https://dblp.org/rec/conf/slt/WangKGCMY21.bib}, bibsource = {dblp computer science bibliography, https://dblp.org} }
@inproceedings{DBLP:conf/slt/WangYSX21, author = {Xiong Wang and Zhuoyuan Yao and Xian Shi and Lei Xie}, title = {Cascade RNN-Transducer: Syllable Based Streaming On-Device Mandarin Speech Recognition with a Syllable-To-Character Converter}, booktitle = {{IEEE} Spoken Language Technology Workshop, {SLT} 2021, Shenzhen, China, January 19-22, 2021}, pages = {15--21}, publisher = {{IEEE}}, year = {2021}, url = {https://doi.org/10.1109/SLT48900.2021.9383506}, doi = {10.1109/SLT48900.2021.9383506}, timestamp = {Tue, 29 Nov 2022 00:00:00 +0100}, biburl = {https://dblp.org/rec/conf/slt/WangYSX21.bib}, bibsource = {dblp computer science bibliography, https://dblp.org} }
@inproceedings{DBLP:conf/slt/Wangh21, author = {Pu Wang and Hugo Van hamme}, title = {A Light Transformer For Speech-To-Intent Applications}, booktitle = {{IEEE} Spoken Language Technology Workshop, {SLT} 2021, Shenzhen, China, January 19-22, 2021}, pages = {997--1003}, publisher = {{IEEE}}, year = {2021}, url = {https://doi.org/10.1109/SLT48900.2021.9383559}, doi = {10.1109/SLT48900.2021.9383559}, timestamp = {Tue, 07 May 2024 01:00:00 +0200}, biburl = {https://dblp.org/rec/conf/slt/Wangh21.bib}, bibsource = {dblp computer science bibliography, https://dblp.org} }
@inproceedings{DBLP:conf/slt/WuS021, author = {Bin Wu and Sakriani Sakti and Satoshi Nakamura}, title = {Incorporating Discriminative {DPGMM} Posteriorgrams for Low-Resource {ASR}}, booktitle = {{IEEE} Spoken Language Technology Workshop, {SLT} 2021, Shenzhen, China, January 19-22, 2021}, pages = {201--208}, publisher = {{IEEE}}, year = {2021}, url = {https://doi.org/10.1109/SLT48900.2021.9383597}, doi = {10.1109/SLT48900.2021.9383597}, timestamp = {Thu, 08 Apr 2021 01:00:00 +0200}, biburl = {https://dblp.org/rec/conf/slt/WuS021.bib}, bibsource = {dblp computer science bibliography, https://dblp.org} }
@inproceedings{DBLP:conf/slt/XueHF0GN21, author = {Yawen Xue and Shota Horiguchi and Yusuke Fujita and Shinji Watanabe and Paola Garc{\'{\i}}a and Kenji Nagamatsu}, title = {Online End-To-End Neural Diarization with Speaker-Tracing Buffer}, booktitle = {{IEEE} Spoken Language Technology Workshop, {SLT} 2021, Shenzhen, China, January 19-22, 2021}, pages = {841--848}, publisher = {{IEEE}}, year = {2021}, url = {https://doi.org/10.1109/SLT48900.2021.9383523}, doi = {10.1109/SLT48900.2021.9383523}, timestamp = {Thu, 07 Sep 2023 01:00:00 +0200}, biburl = {https://dblp.org/rec/conf/slt/XueHF0GN21.bib}, bibsource = {dblp computer science bibliography, https://dblp.org} }
@inproceedings{DBLP:conf/slt/XueYLXL21, author = {Heyang Xue and Shan Yang and Yi Lei and Lei Xie and Xiulin Li}, title = {Learn2Sing: Target Speaker Singing Voice Synthesis by Learning from a Singing Teacher}, booktitle = {{IEEE} Spoken Language Technology Workshop, {SLT} 2021, Shenzhen, China, January 19-22, 2021}, pages = {522--529}, publisher = {{IEEE}}, year = {2021}, url = {https://doi.org/10.1109/SLT48900.2021.9383585}, doi = {10.1109/SLT48900.2021.9383585}, timestamp = {Fri, 05 Nov 2021 00:00:00 +0100}, biburl = {https://dblp.org/rec/conf/slt/XueYLXL21.bib}, bibsource = {dblp computer science bibliography, https://dblp.org} }
@inproceedings{DBLP:conf/slt/YangYLF0X21, author = {Geng Yang and Shan Yang and Kai Liu and Peng Fang and Wei Chen and Lei Xie}, title = {Multi-Band Melgan: Faster Waveform Generation For High-Quality Text-To-Speech}, booktitle = {{IEEE} Spoken Language Technology Workshop, {SLT} 2021, Shenzhen, China, January 19-22, 2021}, pages = {492--498}, publisher = {{IEEE}}, year = {2021}, url = {https://doi.org/10.1109/SLT48900.2021.9383551}, doi = {10.1109/SLT48900.2021.9383551}, timestamp = {Fri, 05 Nov 2021 00:00:00 +0100}, biburl = {https://dblp.org/rec/conf/slt/YangYLF0X21.bib}, bibsource = {dblp computer science bibliography, https://dblp.org} }
@inproceedings{DBLP:conf/slt/YehWSW0CS21, author = {Ching{-}Feng Yeh and Yongqiang Wang and Yangyang Shi and Chunyang Wu and Frank Zhang and Julian Chan and Michael L. Seltzer}, title = {Streaming Attention-Based Models with Augmented Memory for End-To-End Speech Recognition}, booktitle = {{IEEE} Spoken Language Technology Workshop, {SLT} 2021, Shenzhen, China, January 19-22, 2021}, pages = {8--14}, publisher = {{IEEE}}, year = {2021}, url = {https://doi.org/10.1109/SLT48900.2021.9383504}, doi = {10.1109/SLT48900.2021.9383504}, timestamp = {Wed, 02 Nov 2022 00:00:00 +0100}, biburl = {https://dblp.org/rec/conf/slt/YehWSW0CS21.bib}, bibsource = {dblp computer science bibliography, https://dblp.org} }
@inproceedings{DBLP:conf/slt/YuYWAXOLLM21, author = {Fan Yu and Zhuoyuan Yao and Xiong Wang and Keyu An and Lei Xie and Zhijian Ou and Bo Liu and Xiulin Li and Guanqiong Miao}, title = {The {SLT} 2021 Children Speech Recognition Challenge: Open Datasets, Rules and Baselines}, booktitle = {{IEEE} Spoken Language Technology Workshop, {SLT} 2021, Shenzhen, China, January 19-22, 2021}, pages = {1117--1123}, publisher = {{IEEE}}, year = {2021}, url = {https://doi.org/10.1109/SLT48900.2021.9383608}, doi = {10.1109/SLT48900.2021.9383608}, timestamp = {Tue, 29 Nov 2022 00:00:00 +0100}, biburl = {https://dblp.org/rec/conf/slt/YuYWAXOLLM21.bib}, bibsource = {dblp computer science bibliography, https://dblp.org} }
@inproceedings{DBLP:conf/slt/ZengWCX21, author = {Zhen Zeng and Jianzong Wang and Ning Cheng and Jing Xiao}, title = {MelGlow: Efficient Waveform Generative Network Based On Location-Variable Convolution}, booktitle = {{IEEE} Spoken Language Technology Workshop, {SLT} 2021, Shenzhen, China, January 19-22, 2021}, pages = {485--491}, publisher = {{IEEE}}, year = {2021}, url = {https://doi.org/10.1109/SLT48900.2021.9383603}, doi = {10.1109/SLT48900.2021.9383603}, timestamp = {Wed, 14 Jun 2023 01:00:00 +0200}, biburl = {https://dblp.org/rec/conf/slt/ZengWCX21.bib}, bibsource = {dblp computer science bibliography, https://dblp.org} }
@inproceedings{DBLP:conf/slt/Zhang0LSCPLYPSZ21, author = {Xiaohui Zhang and Frank Zhang and Chunxi Liu and Kjell Schubert and Julian Chan and Pradyot Prakash and Jun Liu and Ching{-}Feng Yeh and Fuchun Peng and Yatharth Saraf and Geoffrey Zweig}, title = {Benchmarking LF-MMI, {CTC} And {RNN-T} Criteria For Streaming {ASR}}, booktitle = {{IEEE} Spoken Language Technology Workshop, {SLT} 2021, Shenzhen, China, January 19-22, 2021}, pages = {46--51}, publisher = {{IEEE}}, year = {2021}, url = {https://doi.org/10.1109/SLT48900.2021.9383623}, doi = {10.1109/SLT48900.2021.9383623}, timestamp = {Thu, 04 Apr 2024 01:00:00 +0200}, biburl = {https://dblp.org/rec/conf/slt/Zhang0LSCPLYPSZ21.bib}, bibsource = {dblp computer science bibliography, https://dblp.org} }
@inproceedings{DBLP:conf/slt/ZhangL0R21, author = {Shucong Zhang and Erfan Loweimi and Peter Bell and Steve Renals}, title = {On The Usefulness of Self-Attention for Automatic Speech Recognition with Transformers}, booktitle = {{IEEE} Spoken Language Technology Workshop, {SLT} 2021, Shenzhen, China, January 19-22, 2021}, pages = {89--96}, publisher = {{IEEE}}, year = {2021}, url = {https://doi.org/10.1109/SLT48900.2021.9383521}, doi = {10.1109/SLT48900.2021.9383521}, timestamp = {Thu, 08 Apr 2021 01:00:00 +0200}, biburl = {https://dblp.org/rec/conf/slt/ZhangL0R21.bib}, bibsource = {dblp computer science bibliography, https://dblp.org} }
@inproceedings{DBLP:conf/slt/ZhengAO21, author = {Huahuan Zheng and Keyu An and Zhijian Ou}, title = {Efficient Neural Architecture Search for End-to-End Speech Recognition Via Straight-Through Gradients}, booktitle = {{IEEE} Spoken Language Technology Workshop, {SLT} 2021, Shenzhen, China, January 19-22, 2021}, pages = {60--67}, publisher = {{IEEE}}, year = {2021}, url = {https://doi.org/10.1109/SLT48900.2021.9383527}, doi = {10.1109/SLT48900.2021.9383527}, timestamp = {Thu, 08 Apr 2021 01:00:00 +0200}, biburl = {https://dblp.org/rec/conf/slt/ZhengAO21.bib}, bibsource = {dblp computer science bibliography, https://dblp.org} }
@inproceedings{DBLP:conf/slt/ZhouCHYL21, author = {Zhengyu Zhou and In Gyu Choi and Yongliang He and Vikas Yadav and Chin{-}Hui Lee}, title = {Using Paralinguistic Information to Disambiguate User Intentions for Distinguishing Phrase Structure and Sarcasm in Spoken Dialog Systems}, booktitle = {{IEEE} Spoken Language Technology Workshop, {SLT} 2021, Shenzhen, China, January 19-22, 2021}, pages = {1020--1027}, publisher = {{IEEE}}, year = {2021}, url = {https://doi.org/10.1109/SLT48900.2021.9383505}, doi = {10.1109/SLT48900.2021.9383505}, timestamp = {Thu, 08 Apr 2021 01:00:00 +0200}, biburl = {https://dblp.org/rec/conf/slt/ZhouCHYL21.bib}, bibsource = {dblp computer science bibliography, https://dblp.org} }
@inproceedings{DBLP:conf/slt/ZhouS021, author = {Kun Zhou and Berrak Sisman and Haizhou Li}, title = {Vaw-Gan For Disentanglement And Recomposition Of Emotional Elements In Speech}, booktitle = {{IEEE} Spoken Language Technology Workshop, {SLT} 2021, Shenzhen, China, January 19-22, 2021}, pages = {415--422}, publisher = {{IEEE}}, year = {2021}, url = {https://doi.org/10.1109/SLT48900.2021.9383526}, doi = {10.1109/SLT48900.2021.9383526}, timestamp = {Sat, 06 Jan 2024 00:00:00 +0100}, biburl = {https://dblp.org/rec/conf/slt/ZhouS021.bib}, bibsource = {dblp computer science bibliography, https://dblp.org} }
@inproceedings{DBLP:conf/slt/ZhouZW21, author = {Tianyan Zhou and Yong Zhao and Jian Wu}, title = {ResNeXt and Res2Net Structures for Speaker Verification}, booktitle = {{IEEE} Spoken Language Technology Workshop, {SLT} 2021, Shenzhen, China, January 19-22, 2021}, pages = {301--307}, publisher = {{IEEE}}, year = {2021}, url = {https://doi.org/10.1109/SLT48900.2021.9383531}, doi = {10.1109/SLT48900.2021.9383531}, timestamp = {Sat, 20 May 2023 01:00:00 +0200}, biburl = {https://dblp.org/rec/conf/slt/ZhouZW21.bib}, bibsource = {dblp computer science bibliography, https://dblp.org} }
@inproceedings{DBLP:conf/slt/ZmolikovaDBNC21, author = {Katerina Zmol{\'{\i}}kov{\'{a}} and Marc Delcroix and Luk{\'{a}}s Burget and Tomohiro Nakatani and Jan Honza Cernock{\'{y}}}, title = {Integration of Variational Autoencoder and Spatial Clustering for Adaptive Multi-Channel Neural Speech Separation}, booktitle = {{IEEE} Spoken Language Technology Workshop, {SLT} 2021, Shenzhen, China, January 19-22, 2021}, pages = {889--896}, publisher = {{IEEE}}, year = {2021}, url = {https://doi.org/10.1109/SLT48900.2021.9383612}, doi = {10.1109/SLT48900.2021.9383612}, timestamp = {Mon, 03 Jan 2022 00:00:00 +0100}, biburl = {https://dblp.org/rec/conf/slt/ZmolikovaDBNC21.bib}, bibsource = {dblp computer science bibliography, https://dblp.org} }
@inproceedings{DBLP:conf/slt/ZorilaLD21, author = {Catalin Zorila and Mohan Li and Rama Doddipatla}, title = {An Investigation into the Multi-channel Time Domain Speaker Extraction Network}, booktitle = {{IEEE} Spoken Language Technology Workshop, {SLT} 2021, Shenzhen, China, January 19-22, 2021}, pages = {793--800}, publisher = {{IEEE}}, year = {2021}, url = {https://doi.org/10.1109/SLT48900.2021.9383582}, doi = {10.1109/SLT48900.2021.9383582}, timestamp = {Mon, 05 Feb 2024 00:00:00 +0100}, biburl = {https://dblp.org/rec/conf/slt/ZorilaLD21.bib}, bibsource = {dblp computer science bibliography, https://dblp.org} }
@proceedings{DBLP:conf/slt/2021, title = {{IEEE} Spoken Language Technology Workshop, {SLT} 2021, Shenzhen, China, January 19-22, 2021}, publisher = {{IEEE}}, year = {2021}, url = {https://doi.org/10.1109/SLT48900.2021}, doi = {10.1109/SLT48900.2021}, isbn = {978-1-7281-7066-4}, timestamp = {Thu, 08 Apr 2021 01:00:00 +0200}, biburl = {https://dblp.org/rec/conf/slt/2021.bib}, bibsource = {dblp computer science bibliography, https://dblp.org} }
![](https://dblp.uni-trier.de/img/cog.dark.24x24.png)
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.