Search dblp for Publications

export results for "Ramon Sanabria"

 download as .bib file

@inproceedings{DBLP:conf/icassp/SalibaLSL24,
  author       = {Alexandra Saliba and
                  Yuanchao Li and
                  Ramon Sanabria and
                  Catherine Lai},
  title        = {Layer-Wise Analysis of Self-Supervised Acoustic Word Embeddings: {A}
                  Study on Speech Emotion Recognition},
  booktitle    = {{IEEE} International Conference on Acoustics, Speech, and Signal Processing,
                  {ICASSP} 2024 - Workshops, Seoul, Republic of Korea, April 14-19,
                  2024},
  pages        = {590--594},
  publisher    = {{IEEE}},
  year         = {2024},
  url          = {https://doi.org/10.1109/ICASSPW62465.2024.10627629},
  doi          = {10.1109/ICASSPW62465.2024.10627629},
  timestamp    = {Wed, 04 Sep 2024 08:54:35 +0200},
  biburl       = {https://dblp.org/rec/conf/icassp/SalibaLSL24.bib},
  bibsource    = {dblp computer science bibliography, https://dblp.org}
}
@article{DBLP:journals/corr/abs-2402-02617,
  author       = {Alexandra Saliba and
                  Yuanchao Li and
                  Ramon Sanabria and
                  Catherine Lai},
  title        = {Layer-Wise Analysis of Self-Supervised Acoustic Word Embeddings: {A}
                  Study on Speech Emotion Recognition},
  journal      = {CoRR},
  volume       = {abs/2402.02617},
  year         = {2024},
  url          = {https://doi.org/10.48550/arXiv.2402.02617},
  doi          = {10.48550/ARXIV.2402.02617},
  eprinttype    = {arXiv},
  eprint       = {2402.02617},
  timestamp    = {Mon, 12 Feb 2024 00:00:00 +0100},
  biburl       = {https://dblp.org/rec/journals/corr/abs-2402-02617.bib},
  bibsource    = {dblp computer science bibliography, https://dblp.org}
}
@article{DBLP:journals/corr/abs-2404-01616,
  author       = {Frank Palma Gomez and
                  Ramon Sanabria and
                  Yun{-}Hsuan Sung and
                  Daniel Cer and
                  Siddharth Dalmia and
                  Gustavo Hern{\'{a}}ndez {\'{A}}brego},
  title        = {Transforming LLMs into Cross-modal and Cross-lingual Retrieval Systems},
  journal      = {CoRR},
  volume       = {abs/2404.01616},
  year         = {2024},
  url          = {https://doi.org/10.48550/arXiv.2404.01616},
  doi          = {10.48550/ARXIV.2404.01616},
  eprinttype    = {arXiv},
  eprint       = {2404.01616},
  timestamp    = {Wed, 08 May 2024 01:00:00 +0200},
  biburl       = {https://dblp.org/rec/journals/corr/abs-2404-01616.bib},
  bibsource    = {dblp computer science bibliography, https://dblp.org}
}
@inproceedings{DBLP:conf/enc/GarciaMSPS23,
  author       = {Ricardo Garc{\'{\i}}a and
                  Soria Sergio Emmanuel Soria Medina and
                  Aldo Ram{\'{o}}n Sanabria Santiago and
                  Guillermo Rey Pe{\~{n}}aloza{-}Mendoza and
                  Carlos Alberto Trejo Ser{\'{a}}fico},
  title        = {Blood cell counting(Erythocytes) through image procesing in Matlab},
  booktitle    = {Mexican International Conference on Computer Science, {ENC} 2023,
                  Guanajuato, Guanajuato, Mexico, September 11-13, 2023},
  pages        = {1--5},
  publisher    = {{IEEE}},
  year         = {2023},
  url          = {https://doi.org/10.1109/ENC60556.2023.10508612},
  doi          = {10.1109/ENC60556.2023.10508612},
  timestamp    = {Thu, 16 May 2024 01:00:00 +0200},
  biburl       = {https://dblp.org/rec/conf/enc/GarciaMSPS23.bib},
  bibsource    = {dblp computer science bibliography, https://dblp.org}
}
@inproceedings{DBLP:conf/icassp/SanabriaBMCKB23,
  author       = {Ramon Sanabria and
                  Nikolay Bogoychev and
                  Nina Markl and
                  Andrea Carmantini and
                  Ondrej Klejch and
                  Peter Bell},
  title        = {The Edinburgh International Accents of English Corpus: Towards the
                  Democratization of English {ASR}},
  booktitle    = {{IEEE} International Conference on Acoustics, Speech and Signal Processing
                  {ICASSP} 2023, Rhodes Island, Greece, June 4-10, 2023},
  pages        = {1--5},
  publisher    = {{IEEE}},
  year         = {2023},
  url          = {https://doi.org/10.1109/ICASSP49357.2023.10095057},
  doi          = {10.1109/ICASSP49357.2023.10095057},
  timestamp    = {Mon, 05 Feb 2024 00:00:00 +0100},
  biburl       = {https://dblp.org/rec/conf/icassp/SanabriaBMCKB23.bib},
  bibsource    = {dblp computer science bibliography, https://dblp.org}
}
@inproceedings{DBLP:conf/icassp/SanabriaHBA23,
  author       = {Ramon Sanabria and
                  Wei{-}Ning Hsu and
                  Alexei Baevski and
                  Michael Auli},
  title        = {Measuring the Impact of Domain Factors in Self-Supervised Pre-Training},
  booktitle    = {{IEEE} International Conference on Acoustics, Speech, and Signal Processing,
                  {ICASSP} 2023 - Workshops, Rhodes Island, Greece, June 4-10, 2023},
  pages        = {1--5},
  publisher    = {{IEEE}},
  year         = {2023},
  url          = {https://doi.org/10.1109/ICASSPW59220.2023.10193184},
  doi          = {10.1109/ICASSPW59220.2023.10193184},
  timestamp    = {Mon, 07 Aug 2023 15:56:26 +0200},
  biburl       = {https://dblp.org/rec/conf/icassp/SanabriaHBA23.bib},
  bibsource    = {dblp computer science bibliography, https://dblp.org}
}
@inproceedings{DBLP:conf/icassp/SanabriaTG23,
  author       = {Ramon Sanabria and
                  Hao Tang and
                  Sharon Goldwater},
  title        = {Analyzing Acoustic Word Embeddings from Pre-Trained Self-Supervised
                  Speech Models},
  booktitle    = {{IEEE} International Conference on Acoustics, Speech and Signal Processing
                  {ICASSP} 2023, Rhodes Island, Greece, June 4-10, 2023},
  pages        = {1--5},
  publisher    = {{IEEE}},
  year         = {2023},
  url          = {https://doi.org/10.1109/ICASSP49357.2023.10096099},
  doi          = {10.1109/ICASSP49357.2023.10096099},
  timestamp    = {Sun, 05 Nov 2023 00:00:00 +0100},
  biburl       = {https://dblp.org/rec/conf/icassp/SanabriaTG23.bib},
  bibsource    = {dblp computer science bibliography, https://dblp.org}
}
@inproceedings{DBLP:conf/interspeech/SanabriaKTG23,
  author       = {Ramon Sanabria and
                  Ondrej Klejch and
                  Hao Tang and
                  Sharon Goldwater},
  editor       = {Naomi Harte and
                  Julie Carson{-}Berndsen and
                  Gareth Jones},
  title        = {Acoustic Word Embeddings for Untranscribed Target Languages with Continued
                  Pretraining and Learned Pooling},
  booktitle    = {24th Annual Conference of the International Speech Communication Association,
                  Interspeech 2023, Dublin, Ireland, August 20-24, 2023},
  pages        = {406--410},
  publisher    = {{ISCA}},
  year         = {2023},
  url          = {https://doi.org/10.21437/Interspeech.2023-268},
  doi          = {10.21437/INTERSPEECH.2023-268},
  timestamp    = {Fri, 14 Jun 2024 14:12:12 +0200},
  biburl       = {https://dblp.org/rec/conf/interspeech/SanabriaKTG23.bib},
  bibsource    = {dblp computer science bibliography, https://dblp.org}
}
@article{DBLP:journals/corr/abs-2303-18110,
  author       = {Ramon Sanabria and
                  Nikolay Bogoychev and
                  Nina Markl and
                  Andrea Carmantini and
                  Ondrej Klejch and
                  Peter Bell},
  title        = {The Edinburgh International Accents of English Corpus: Towards the
                  Democratization of English {ASR}},
  journal      = {CoRR},
  volume       = {abs/2303.18110},
  year         = {2023},
  url          = {https://doi.org/10.48550/arXiv.2303.18110},
  doi          = {10.48550/ARXIV.2303.18110},
  eprinttype    = {arXiv},
  eprint       = {2303.18110},
  timestamp    = {Mon, 17 Apr 2023 01:00:00 +0200},
  biburl       = {https://dblp.org/rec/journals/corr/abs-2303-18110.bib},
  bibsource    = {dblp computer science bibliography, https://dblp.org}
}
@article{DBLP:journals/corr/abs-2306-02153,
  author       = {Ramon Sanabria and
                  Ondrej Klejch and
                  Hao Tang and
                  Sharon Goldwater},
  title        = {Acoustic Word Embeddings for Untranscribed Target Languages with Continued
                  Pretraining and Learned Pooling},
  journal      = {CoRR},
  volume       = {abs/2306.02153},
  year         = {2023},
  url          = {https://doi.org/10.48550/arXiv.2306.02153},
  doi          = {10.48550/ARXIV.2306.02153},
  eprinttype    = {arXiv},
  eprint       = {2306.02153},
  timestamp    = {Mon, 12 Jun 2023 01:00:00 +0200},
  biburl       = {https://dblp.org/rec/journals/corr/abs-2306-02153.bib},
  bibsource    = {dblp computer science bibliography, https://dblp.org}
}
@article{DBLP:journals/corr/abs-2203-00648,
  author       = {Ramon Sanabria and
                  Wei{-}Ning Hsu and
                  Alexei Baevski and
                  Michael Auli},
  title        = {Measuring the Impact of Individual Domain Factors in Self-Supervised
                  Pre-Training},
  journal      = {CoRR},
  volume       = {abs/2203.00648},
  year         = {2022},
  url          = {https://doi.org/10.48550/arXiv.2203.00648},
  doi          = {10.48550/ARXIV.2203.00648},
  eprinttype    = {arXiv},
  eprint       = {2203.00648},
  timestamp    = {Wed, 16 Mar 2022 00:00:00 +0100},
  biburl       = {https://dblp.org/rec/journals/corr/abs-2203-00648.bib},
  bibsource    = {dblp computer science bibliography, https://dblp.org}
}
@article{DBLP:journals/corr/abs-2210-16043,
  author       = {Ramon Sanabria and
                  Hao Tang and
                  Sharon Goldwater},
  title        = {Analyzing Acoustic Word Embeddings from Pre-trained Self-supervised
                  Speech Models},
  journal      = {CoRR},
  volume       = {abs/2210.16043},
  year         = {2022},
  url          = {https://doi.org/10.48550/arXiv.2210.16043},
  doi          = {10.48550/ARXIV.2210.16043},
  eprinttype    = {arXiv},
  eprint       = {2210.16043},
  timestamp    = {Wed, 02 Nov 2022 00:00:00 +0100},
  biburl       = {https://dblp.org/rec/journals/corr/abs-2210-16043.bib},
  bibsource    = {dblp computer science bibliography, https://dblp.org}
}
@inproceedings{DBLP:conf/interspeech/SanabriaWB21,
  author       = {Ramon Sanabria and
                  Austin Waters and
                  Jason Baldridge},
  editor       = {Hynek Hermansky and
                  Honza Cernock{\'{y}} and
                  Luk{\'{a}}s Burget and
                  Lori Lamel and
                  Odette Scharenborg and
                  Petr Motl{\'{\i}}cek},
  title        = {Talk, Don't Write: {A} Study of Direct Speech-Based Image Retrieval},
  booktitle    = {22nd Annual Conference of the International Speech Communication Association,
                  Interspeech 2021, Brno, Czechia, August 30 - September 3, 2021},
  pages        = {2976--2980},
  publisher    = {{ISCA}},
  year         = {2021},
  url          = {https://doi.org/10.21437/Interspeech.2021-96},
  doi          = {10.21437/INTERSPEECH.2021-96},
  timestamp    = {Tue, 11 Jun 2024 16:45:43 +0200},
  biburl       = {https://dblp.org/rec/conf/interspeech/SanabriaWB21.bib},
  bibsource    = {dblp computer science bibliography, https://dblp.org}
}
@article{DBLP:journals/corr/abs-2104-01894,
  author       = {Ramon Sanabria and
                  Austin Waters and
                  Jason Baldridge},
  title        = {Talk, Don't Write: {A} Study of Direct Speech-Based Image Retrieval},
  journal      = {CoRR},
  volume       = {abs/2104.01894},
  year         = {2021},
  url          = {https://arxiv.org/abs/2104.01894},
  eprinttype    = {arXiv},
  eprint       = {2104.01894},
  timestamp    = {Mon, 12 Apr 2021 01:00:00 +0200},
  biburl       = {https://dblp.org/rec/journals/corr/abs-2104-01894.bib},
  bibsource    = {dblp computer science bibliography, https://dblp.org}
}
@article{DBLP:journals/corr/abs-2109-10107,
  author       = {Ramon Sanabria and
                  Hao Tang and
                  Sharon Goldwater},
  title        = {On the Difficulty of Segmenting Words with Attention},
  journal      = {CoRR},
  volume       = {abs/2109.10107},
  year         = {2021},
  url          = {https://arxiv.org/abs/2109.10107},
  eprinttype    = {arXiv},
  eprint       = {2109.10107},
  timestamp    = {Mon, 27 Sep 2021 01:00:00 +0200},
  biburl       = {https://dblp.org/rec/journals/corr/abs-2109-10107.bib},
  bibsource    = {dblp computer science bibliography, https://dblp.org}
}
@article{DBLP:journals/csl/PalaskarSM20,
  author       = {Shruti Palaskar and
                  Ramon Sanabria and
                  Florian Metze},
  title        = {Transfer learning for multimodal dialog},
  journal      = {Comput. Speech Lang.},
  volume       = {64},
  pages        = {101093},
  year         = {2020},
  url          = {https://doi.org/10.1016/j.csl.2020.101093},
  doi          = {10.1016/J.CSL.2020.101093},
  timestamp    = {Mon, 24 Oct 2022 01:00:00 +0200},
  biburl       = {https://dblp.org/rec/journals/csl/PalaskarSM20.bib},
  bibsource    = {dblp computer science bibliography, https://dblp.org}
}
@article{DBLP:journals/jstsp/SpeciaBCDEGHLLL20,
  author       = {Lucia Specia and
                  Lo{\"{\i}}c Barrault and
                  Ozan Caglayan and
                  Amanda Cardoso Duarte and
                  Desmond Elliott and
                  Spandana Gella and
                  Nils Holzenberger and
                  Chiraag Lala and
                  Sun Jae Lee and
                  Jindrich Libovick{\'{y}} and
                  Pranava Madhyastha and
                  Florian Metze and
                  Karl Mulligan and
                  Alissa Ostapenko and
                  Shruti Palaskar and
                  Ramon Sanabria and
                  Josiah Wang and
                  Raman Arora},
  title        = {Grounded Sequence to Sequence Transduction},
  journal      = {{IEEE} J. Sel. Top. Signal Process.},
  volume       = {14},
  number       = {3},
  pages        = {577--591},
  year         = {2020},
  url          = {https://doi.org/10.1109/JSTSP.2020.2998415},
  doi          = {10.1109/JSTSP.2020.2998415},
  timestamp    = {Mon, 26 Jun 2023 01:00:00 +0200},
  biburl       = {https://dblp.org/rec/journals/jstsp/SpeciaBCDEGHLLL20.bib},
  bibsource    = {dblp computer science bibliography, https://dblp.org}
}
@inproceedings{DBLP:conf/emnlp/SrinivasanSME20,
  author       = {Tejas Srinivasan and
                  Ramon Sanabria and
                  Florian Metze and
                  Desmond Elliott},
  editor       = {Trevor Cohn and
                  Yulan He and
                  Yang Liu},
  title        = {Fine-Grained Grounding for Multimodal Speech Recognition},
  booktitle    = {Findings of the Association for Computational Linguistics: {EMNLP}
                  2020, Online Event, 16-20 November 2020},
  series       = {Findings of {ACL}},
  volume       = {{EMNLP} 2020},
  pages        = {2667--2677},
  publisher    = {Association for Computational Linguistics},
  year         = {2020},
  url          = {https://doi.org/10.18653/v1/2020.findings-emnlp.242},
  doi          = {10.18653/V1/2020.FINDINGS-EMNLP.242},
  timestamp    = {Tue, 20 Aug 2024 07:54:42 +0200},
  biburl       = {https://dblp.org/rec/conf/emnlp/SrinivasanSME20.bib},
  bibsource    = {dblp computer science bibliography, https://dblp.org}
}
@inproceedings{DBLP:conf/icassp/SrinivasanSM20,
  author       = {Tejas Srinivasan and
                  Ramon Sanabria and
                  Florian Metze},
  title        = {Looking Enhances Listening: Recovering Missing Speech Using Images},
  booktitle    = {2020 {IEEE} International Conference on Acoustics, Speech and Signal
                  Processing, {ICASSP} 2020, Barcelona, Spain, May 4-8, 2020},
  pages        = {6304--6308},
  publisher    = {{IEEE}},
  year         = {2020},
  url          = {https://doi.org/10.1109/ICASSP40776.2020.9053397},
  doi          = {10.1109/ICASSP40776.2020.9053397},
  timestamp    = {Thu, 23 Jul 2020 16:19:28 +0200},
  biburl       = {https://dblp.org/rec/conf/icassp/SrinivasanSM20.bib},
  bibsource    = {dblp computer science bibliography, https://dblp.org}
}
@article{DBLP:journals/corr/abs-2002-05639,
  author       = {Tejas Srinivasan and
                  Ramon Sanabria and
                  Florian Metze},
  title        = {Looking Enhances Listening: Recovering Missing Speech Using Images},
  journal      = {CoRR},
  volume       = {abs/2002.05639},
  year         = {2020},
  url          = {https://arxiv.org/abs/2002.05639},
  eprinttype    = {arXiv},
  eprint       = {2002.05639},
  timestamp    = {Fri, 14 Feb 2020 00:00:00 +0100},
  biburl       = {https://dblp.org/rec/journals/corr/abs-2002-05639.bib},
  bibsource    = {dblp computer science bibliography, https://dblp.org}
}
@article{DBLP:journals/corr/abs-2010-02384,
  author       = {Tejas Srinivasan and
                  Ramon Sanabria and
                  Florian Metze and
                  Desmond Elliott},
  title        = {Fine-Grained Grounding for Multimodal Speech Recognition},
  journal      = {CoRR},
  volume       = {abs/2010.02384},
  year         = {2020},
  url          = {https://arxiv.org/abs/2010.02384},
  eprinttype    = {arXiv},
  eprint       = {2010.02384},
  timestamp    = {Thu, 14 Oct 2021 01:00:00 +0200},
  biburl       = {https://dblp.org/rec/journals/corr/abs-2010-02384.bib},
  bibsource    = {dblp computer science bibliography, https://dblp.org}
}
@article{DBLP:journals/corr/abs-2010-08642,
  author       = {Tejas Srinivasan and
                  Ramon Sanabria and
                  Florian Metze and
                  Desmond Elliott},
  title        = {Multimodal Speech Recognition with Unstructured Audio Masking},
  journal      = {CoRR},
  volume       = {abs/2010.08642},
  year         = {2020},
  url          = {https://arxiv.org/abs/2010.08642},
  eprinttype    = {arXiv},
  eprint       = {2010.08642},
  timestamp    = {Wed, 21 Oct 2020 01:00:00 +0200},
  biburl       = {https://dblp.org/rec/journals/corr/abs-2010-08642.bib},
  bibsource    = {dblp computer science bibliography, https://dblp.org}
}
@inproceedings{DBLP:conf/icassp/CaglayanSPBM19,
  author       = {Ozan Caglayan and
                  Ramon Sanabria and
                  Shruti Palaskar and
                  Lo{\"{\i}}c Barrault and
                  Florian Metze},
  title        = {Multimodal Grounding for Sequence-to-sequence Speech Recognition},
  booktitle    = {{IEEE} International Conference on Acoustics, Speech and Signal Processing,
                  {ICASSP} 2019, Brighton, United Kingdom, May 12-17, 2019},
  pages        = {8648--8652},
  publisher    = {{IEEE}},
  year         = {2019},
  url          = {https://doi.org/10.1109/ICASSP.2019.8682750},
  doi          = {10.1109/ICASSP.2019.8682750},
  timestamp    = {Wed, 16 Oct 2019 14:14:52 +0200},
  biburl       = {https://dblp.org/rec/conf/icassp/CaglayanSPBM19.bib},
  bibsource    = {dblp computer science bibliography, https://dblp.org}
}
@inproceedings{DBLP:conf/iwslt/NiehuesCSNTHSSB19,
  author       = {Jan Niehues and
                  Roldano Cattoni and
                  Sebastian St{\"{u}}ker and
                  Matteo Negri and
                  Marco Turchi and
                  Thanh{-}Le Ha and
                  Elizabeth Salesky and
                  Ramon Sanabria and
                  Lo{\"{\i}}c Barrault and
                  Lucia Specia and
                  Marcello Federico},
  editor       = {Jan Niehues and
                  Roldano Cattoni and
                  Sebastian St{\"{u}}ker and
                  Matteo Negri and
                  Marco Turchi and
                  Thanh{-}Le Ha and
                  Elizabeth Salesky and
                  Ramon Sanabria and
                  Lo{\"{\i}}c Barrault and
                  Lucia Specia and
                  Marcello Federico},
  title        = {The {IWSLT} 2019 Evaluation Campaign},
  booktitle    = {Proceedings of the 16th International Conference on Spoken Language
                  Translation, {IWSLT} 2019, Hong Kong, November 2-3, 2019},
  publisher    = {Association for Computational Linguistics},
  year         = {2019},
  url          = {https://aclanthology.org/2019.iwslt-1.1},
  timestamp    = {Thu, 01 Aug 2024 15:37:24 +0200},
  biburl       = {https://dblp.org/rec/conf/iwslt/NiehuesCSNTHSSB19.bib},
  bibsource    = {dblp computer science bibliography, https://dblp.org}
}
@inproceedings{DBLP:conf/iwslt/SrinivasanSM19,
  author       = {Tejas Srinivasan and
                  Ramon Sanabria and
                  Florian Metze},
  editor       = {Jan Niehues and
                  Roldano Cattoni and
                  Sebastian St{\"{u}}ker and
                  Matteo Negri and
                  Marco Turchi and
                  Thanh{-}Le Ha and
                  Elizabeth Salesky and
                  Ramon Sanabria and
                  Lo{\"{\i}}c Barrault and
                  Lucia Specia and
                  Marcello Federico},
  title        = {CMU's Machine Translation System for {IWSLT} 2019},
  booktitle    = {Proceedings of the 16th International Conference on Spoken Language
                  Translation, {IWSLT} 2019, Hong Kong, November 2-3, 2019},
  publisher    = {Association for Computational Linguistics},
  year         = {2019},
  url          = {https://aclanthology.org/2019.iwslt-1.10},
  timestamp    = {Thu, 01 Aug 2024 01:00:00 +0200},
  biburl       = {https://dblp.org/rec/conf/iwslt/SrinivasanSM19.bib},
  bibsource    = {dblp computer science bibliography, https://dblp.org}
}
@inproceedings{DBLP:conf/iwslt/SrinivasanSM19a,
  author       = {Tejas Srinivasan and
                  Ramon Sanabria and
                  Florian Metze},
  editor       = {Jan Niehues and
                  Roldano Cattoni and
                  Sebastian St{\"{u}}ker and
                  Matteo Negri and
                  Marco Turchi and
                  Thanh{-}Le Ha and
                  Elizabeth Salesky and
                  Ramon Sanabria and
                  Lo{\"{\i}}c Barrault and
                  Lucia Specia and
                  Marcello Federico},
  title        = {Multitask Learning For Different Subword Segmentations In Neural Machine
                  Translation},
  booktitle    = {Proceedings of the 16th International Conference on Spoken Language
                  Translation, {IWSLT} 2019, Hong Kong, November 2-3, 2019},
  publisher    = {Association for Computational Linguistics},
  year         = {2019},
  url          = {https://aclanthology.org/2019.iwslt-1.25},
  timestamp    = {Thu, 01 Aug 2024 01:00:00 +0200},
  biburl       = {https://dblp.org/rec/conf/iwslt/SrinivasanSM19a.bib},
  bibsource    = {dblp computer science bibliography, https://dblp.org}
}
@inproceedings{DBLP:conf/mediaeval/MoriyaSMJ19,
  author       = {Yasufumi Moriya and
                  Ramon Sanabria and
                  Florian Metze and
                  Gareth J. F. Jones},
  editor       = {Martha A. Larson and
                  Steven Alexander Hicks and
                  Mihai Gabriel Constantin and
                  Benjamin Bischke and
                  Alastair Porter and
                  Peijian Zhao and
                  Mathias Lux and
                  Laura Cabrera Quiros and
                  Jordan Calandre and
                  Gareth Jones},
  title        = {MediaEval 2019: Eyes and Ears Together},
  booktitle    = {Working Notes Proceedings of the MediaEval 2019 Workshop, Sophia Antipolis,
                  France, 27-30 October 2019},
  series       = {{CEUR} Workshop Proceedings},
  volume       = {2670},
  publisher    = {CEUR-WS.org},
  year         = {2019},
  url          = {https://ceur-ws.org/Vol-2670/MediaEval\_19\_paper\_2.pdf},
  timestamp    = {Fri, 10 Mar 2023 16:22:12 +0100},
  biburl       = {https://dblp.org/rec/conf/mediaeval/MoriyaSMJ19.bib},
  bibsource    = {dblp computer science bibliography, https://dblp.org}
}
@proceedings{DBLP:conf/iwslt/2019,
  editor       = {Jan Niehues and
                  Roldano Cattoni and
                  Sebastian St{\"{u}}ker and
                  Matteo Negri and
                  Marco Turchi and
                  Thanh{-}Le Ha and
                  Elizabeth Salesky and
                  Ramon Sanabria and
                  Lo{\"{\i}}c Barrault and
                  Lucia Specia and
                  Marcello Federico},
  title        = {Proceedings of the 16th International Conference on Spoken Language
                  Translation, {IWSLT} 2019, Hong Kong, November 2-3, 2019},
  publisher    = {Association for Computational Linguistics},
  year         = {2019},
  url          = {https://aclanthology.org/volumes/2019.iwslt-1/},
  timestamp    = {Thu, 01 Aug 2024 01:00:00 +0200},
  biburl       = {https://dblp.org/rec/conf/iwslt/2019.bib},
  bibsource    = {dblp computer science bibliography, https://dblp.org}
}
@inproceedings{DBLP:conf/tac/HovyCCGHMMSDCCK19,
  author       = {Eduard H. Hovy and
                  Jaime G. Carbonell and
                  Hans Chalupsky and
                  Anatole Gershman and
                  Alex Hauptmann and
                  Florian Metze and
                  Teruko Mitamura and
                  Zaid Sheikh and
                  Ankit Dangi and
                  Aditi Chaudhary and
                  Xianyang Chen and
                  Xiang Kong and
                  Bernie Huang and
                  Salvador Medina and
                  Hector Liu and
                  Xuezhe Ma and
                  Maria Ryskina and
                  Ramon Sanabria and
                  Varun Gangal},
  title        = {{OPERA:} Operations-oriented Probabilistic Extraction, Reasoning,
                  and Analysis},
  booktitle    = {Proceedings of the 2019 Text Analysis Conference, {TAC} 2019, Gaithersburg,
                  Maryland, USA, November 12-13, 2019},
  publisher    = {{NIST}},
  year         = {2019},
  url          = {https://tac.nist.gov/publications/2019/participant.papers/TAC2019.OPERA.proceedings.pdf},
  timestamp    = {Mon, 19 Apr 2021 12:42:35 +0200},
  biburl       = {https://dblp.org/rec/conf/tac/HovyCCGHMMSDCCK19.bib},
  bibsource    = {dblp computer science bibliography, https://dblp.org}
}
@article{DBLP:journals/corr/abs-1906-06147,
  author       = {Yasufumi Moriya and
                  Ramon Sanabria and
                  Florian Metze and
                  Gareth J. F. Jones},
  title        = {Grounding Object Detections With Transcriptions},
  journal      = {CoRR},
  volume       = {abs/1906.06147},
  year         = {2019},
  url          = {http://arxiv.org/abs/1906.06147},
  eprinttype    = {arXiv},
  eprint       = {1906.06147},
  timestamp    = {Mon, 24 Jun 2019 01:00:00 +0200},
  biburl       = {https://dblp.org/rec/journals/corr/abs-1906-06147.bib},
  bibsource    = {dblp computer science bibliography, https://dblp.org}
}
@article{DBLP:journals/corr/abs-1907-00477,
  author       = {Tejas Srinivasan and
                  Ramon Sanabria and
                  Florian Metze},
  title        = {Analyzing Utility of Visual Context in Multimodal Speech Recognition
                  Under Noisy Conditions},
  journal      = {CoRR},
  volume       = {abs/1907.00477},
  year         = {2019},
  url          = {http://arxiv.org/abs/1907.00477},
  eprinttype    = {arXiv},
  eprint       = {1907.00477},
  timestamp    = {Mon, 08 Jul 2019 01:00:00 +0200},
  biburl       = {https://dblp.org/rec/journals/corr/abs-1907-00477.bib},
  bibsource    = {dblp computer science bibliography, https://dblp.org}
}
@article{DBLP:journals/corr/abs-1910-12368,
  author       = {Tejas Srinivasan and
                  Ramon Sanabria and
                  Florian Metze},
  title        = {Multitask Learning For Different Subword Segmentations In Neural Machine
                  Translation},
  journal      = {CoRR},
  volume       = {abs/1910.12368},
  year         = {2019},
  url          = {http://arxiv.org/abs/1910.12368},
  eprinttype    = {arXiv},
  eprint       = {1910.12368},
  timestamp    = {Thu, 31 Oct 2019 00:00:00 +0100},
  biburl       = {https://dblp.org/rec/journals/corr/abs-1910-12368.bib},
  bibsource    = {dblp computer science bibliography, https://dblp.org}
}
@inproceedings{DBLP:conf/icassp/DalmiaSMB18,
  author       = {Siddharth Dalmia and
                  Ramon Sanabria and
                  Florian Metze and
                  Alan W. Black},
  title        = {Sequence-Based Multi-Lingual Low Resource Speech Recognition},
  booktitle    = {2018 {IEEE} International Conference on Acoustics, Speech and Signal
                  Processing, {ICASSP} 2018, Calgary, AB, Canada, April 15-20, 2018},
  pages        = {4909--4913},
  publisher    = {{IEEE}},
  year         = {2018},
  url          = {https://doi.org/10.1109/ICASSP.2018.8461802},
  doi          = {10.1109/ICASSP.2018.8461802},
  timestamp    = {Wed, 16 Oct 2019 14:14:52 +0200},
  biburl       = {https://dblp.org/rec/conf/icassp/DalmiaSMB18.bib},
  bibsource    = {dblp computer science bibliography, https://dblp.org}
}
@inproceedings{DBLP:conf/icassp/PalaskarSM18,
  author       = {Shruti Palaskar and
                  Ramon Sanabria and
                  Florian Metze},
  title        = {End-to-end Multimodal Speech Recognition},
  booktitle    = {2018 {IEEE} International Conference on Acoustics, Speech and Signal
                  Processing, {ICASSP} 2018, Calgary, AB, Canada, April 15-20, 2018},
  pages        = {5774--5778},
  publisher    = {{IEEE}},
  year         = {2018},
  url          = {https://doi.org/10.1109/ICASSP.2018.8462439},
  doi          = {10.1109/ICASSP.2018.8462439},
  timestamp    = {Tue, 18 Sep 2018 01:00:00 +0200},
  biburl       = {https://dblp.org/rec/conf/icassp/PalaskarSM18.bib},
  bibsource    = {dblp computer science bibliography, https://dblp.org}
}
@inproceedings{DBLP:conf/interspeech/ZenkelSMW18,
  author       = {Thomas Zenkel and
                  Ramon Sanabria and
                  Florian Metze and
                  Alex Waibel},
  editor       = {B. Yegnanarayana},
  title        = {Subword and Crossword Units for {CTC} Acoustic Models},
  booktitle    = {19th Annual Conference of the International Speech Communication Association,
                  Interspeech 2018, Hyderabad, India, September 2-6, 2018},
  pages        = {396--400},
  publisher    = {{ISCA}},
  year         = {2018},
  url          = {https://doi.org/10.21437/Interspeech.2018-2057},
  doi          = {10.21437/INTERSPEECH.2018-2057},
  timestamp    = {Tue, 11 Jun 2024 16:45:43 +0200},
  biburl       = {https://dblp.org/rec/conf/interspeech/ZenkelSMW18.bib},
  bibsource    = {dblp computer science bibliography, https://dblp.org}
}
@inproceedings{DBLP:conf/mediaeval/MoriyaSMJ18,
  author       = {Yasufumi Moriya and
                  Ramon Sanabria and
                  Florian Metze and
                  Gareth J. F. Jones},
  editor       = {Martha A. Larson and
                  Piyush Arora and
                  Claire{-}H{\'{e}}l{\`{e}}ne Demarty and
                  Michael Riegler and
                  Benjamin Bischke and
                  Emmanuel Dellandr{\'{e}}a and
                  Mathias Lux and
                  Alastair Porter and
                  Gareth J. F. Jones},
  title        = {Eyes and Ears Together: New Task for Multimodal Spoken Content Analysis},
  booktitle    = {Working Notes Proceedings of the MediaEval 2018 Workshop, Sophia Antipolis,
                  France, 29-31 October 2018},
  series       = {{CEUR} Workshop Proceedings},
  volume       = {2283},
  publisher    = {CEUR-WS.org},
  year         = {2018},
  url          = {https://ceur-ws.org/Vol-2283/MediaEval\_18\_paper\_59.pdf},
  timestamp    = {Fri, 10 Mar 2023 16:22:12 +0100},
  biburl       = {https://dblp.org/rec/conf/mediaeval/MoriyaSMJ18.bib},
  bibsource    = {dblp computer science bibliography, https://dblp.org}
}
@inproceedings{DBLP:conf/slt/SanabriaM18,
  author       = {Ramon Sanabria and
                  Florian Metze},
  title        = {Hierarchical Multitask Learning With {CTC}},
  booktitle    = {2018 {IEEE} Spoken Language Technology Workshop, {SLT} 2018, Athens,
                  Greece, December 18-21, 2018},
  pages        = {485--490},
  publisher    = {{IEEE}},
  year         = {2018},
  url          = {https://doi.org/10.1109/SLT.2018.8639530},
  doi          = {10.1109/SLT.2018.8639530},
  timestamp    = {Wed, 16 Oct 2019 14:14:53 +0200},
  biburl       = {https://dblp.org/rec/conf/slt/SanabriaM18.bib},
  bibsource    = {dblp computer science bibliography, https://dblp.org}
}
@inproceedings{DBLP:conf/tac/HovyBCCGHMMCCHL18,
  author       = {Eduard H. Hovy and
                  Taylor Berg{-}Kirkpatrick and
                  Jaime G. Carbonell and
                  Hans Chalupsky and
                  Anatole Gershman and
                  Alexander G. Hauptmann and
                  Florian Metze and
                  Teruko Mitamura and
                  Aditi Chaudhary and
                  Xianyang Chen and
                  Bernie Po{-}Yao Huang and
                  Hector Zhengzhong Liu and
                  Xuezhe Ma and
                  Shruti Palaskar and
                  Dheeraj Rajagopal and
                  Maria Ryskina and
                  Ramon Sanabria},
  title        = {{OPERA:} Operations-oriented Probabilistic Extraction, Reasoning,
                  and Analysis},
  booktitle    = {Proceedings of the 2018 Text Analysis Conference, {TAC} 2018, Gaithersburg,
                  Maryland, USA, November 13-14, 2018},
  publisher    = {{NIST}},
  year         = {2018},
  url          = {https://tac.nist.gov/publications/2018/participant.papers/TAC2018.OPERA.proceedings.pdf},
  timestamp    = {Tue, 20 Aug 2019 14:30:47 +0200},
  biburl       = {https://dblp.org/rec/conf/tac/HovyBCCGHMMCCHL18.bib},
  bibsource    = {dblp computer science bibliography, https://dblp.org}
}
@article{DBLP:journals/corr/abs-1802-07420,
  author       = {Siddharth Dalmia and
                  Ramon Sanabria and
                  Florian Metze and
                  Alan W. Black},
  title        = {Sequence-based Multi-lingual Low Resource Speech Recognition},
  journal      = {CoRR},
  volume       = {abs/1802.07420},
  year         = {2018},
  url          = {http://arxiv.org/abs/1802.07420},
  eprinttype    = {arXiv},
  eprint       = {1802.07420},
  timestamp    = {Mon, 13 Aug 2018 01:00:00 +0200},
  biburl       = {https://dblp.org/rec/journals/corr/abs-1802-07420.bib},
  bibsource    = {dblp computer science bibliography, https://dblp.org}
}
@article{DBLP:journals/corr/abs-1804-09713,
  author       = {Shruti Palaskar and
                  Ramon Sanabria and
                  Florian Metze},
  title        = {End-to-End Multimodal Speech Recognition},
  journal      = {CoRR},
  volume       = {abs/1804.09713},
  year         = {2018},
  url          = {http://arxiv.org/abs/1804.09713},
  eprinttype    = {arXiv},
  eprint       = {1804.09713},
  timestamp    = {Mon, 13 Aug 2018 01:00:00 +0200},
  biburl       = {https://dblp.org/rec/journals/corr/abs-1804-09713.bib},
  bibsource    = {dblp computer science bibliography, https://dblp.org}
}
@article{DBLP:journals/corr/abs-1807-07104,
  author       = {Ramon Sanabria and
                  Florian Metze},
  title        = {Hierarchical Multi Task Learning With {CTC}},
  journal      = {CoRR},
  volume       = {abs/1807.07104},
  year         = {2018},
  url          = {http://arxiv.org/abs/1807.07104},
  eprinttype    = {arXiv},
  eprint       = {1807.07104},
  timestamp    = {Mon, 13 Aug 2018 01:00:00 +0200},
  biburl       = {https://dblp.org/rec/journals/corr/abs-1807-07104.bib},
  bibsource    = {dblp computer science bibliography, https://dblp.org}
}
@article{DBLP:journals/corr/abs-1811-00347,
  author       = {Ramon Sanabria and
                  Ozan Caglayan and
                  Shruti Palaskar and
                  Desmond Elliott and
                  Lo{\"{\i}}c Barrault and
                  Lucia Specia and
                  Florian Metze},
  title        = {How2: {A} Large-scale Dataset for Multimodal Language Understanding},
  journal      = {CoRR},
  volume       = {abs/1811.00347},
  year         = {2018},
  url          = {http://arxiv.org/abs/1811.00347},
  eprinttype    = {arXiv},
  eprint       = {1811.00347},
  timestamp    = {Thu, 22 Nov 2018 00:00:00 +0100},
  biburl       = {https://dblp.org/rec/journals/corr/abs-1811-00347.bib},
  bibsource    = {dblp computer science bibliography, https://dblp.org}
}
@article{DBLP:journals/corr/abs-1811-03865,
  author       = {Ozan Caglayan and
                  Ramon Sanabria and
                  Shruti Palaskar and
                  Lo{\"{\i}}c Barrault and
                  Florian Metze},
  title        = {Multimodal Grounding for Sequence-to-Sequence Speech Recognition},
  journal      = {CoRR},
  volume       = {abs/1811.03865},
  year         = {2018},
  url          = {http://arxiv.org/abs/1811.03865},
  eprinttype    = {arXiv},
  eprint       = {1811.03865},
  timestamp    = {Fri, 23 Nov 2018 00:00:00 +0100},
  biburl       = {https://dblp.org/rec/journals/corr/abs-1811-03865.bib},
  bibsource    = {dblp computer science bibliography, https://dblp.org}
}
@inproceedings{DBLP:conf/interspeech/ZenkelSMNSSW17,
  author       = {Thomas Zenkel and
                  Ramon Sanabria and
                  Florian Metze and
                  Jan Niehues and
                  Matthias Sperber and
                  Sebastian St{\"{u}}ker and
                  Alex Waibel},
  editor       = {Francisco Lacerda},
  title        = {Comparison of Decoding Strategies for {CTC} Acoustic Models},
  booktitle    = {18th Annual Conference of the International Speech Communication Association,
                  Interspeech 2017, Stockholm, Sweden, August 20-24, 2017},
  pages        = {513--517},
  publisher    = {{ISCA}},
  year         = {2017},
  url          = {https://doi.org/10.21437/Interspeech.2017-1683},
  doi          = {10.21437/INTERSPEECH.2017-1683},
  timestamp    = {Tue, 11 Jun 2024 16:45:43 +0200},
  biburl       = {https://dblp.org/rec/conf/interspeech/ZenkelSMNSSW17.bib},
  bibsource    = {dblp computer science bibliography, https://dblp.org}
}
@inproceedings{DBLP:conf/nof/VilaltaVMSMCMA17,
  author       = {Ricard Vilalta and
                  Selva Via and
                  Ferm{\'{\i}}n Mira and
                  Luis Sanabria{-}Russo and
                  Ricardo Mart{\'{\i}}nez and
                  Ramon Casellas and
                  Raul Mu{\~{n}}oz and
                  Jesus Alonso{-}Zarate},
  editor       = {Toktam Mahmoodi and
                  Stefano Secci and
                  Antonio Cianfrani and
                  Filip Idzikowski},
  title        = {Control and management of a connected car using {YANG/RESTCONF} and
                  cloud computing},
  booktitle    = {8th International Conference on the Network of the Future, {NOF} 2017,
                  London, United Kingdom, November 22-24, 2017},
  pages        = {120--122},
  publisher    = {{IEEE}},
  year         = {2017},
  url          = {https://doi.org/10.1109/NOF.2017.8251230},
  doi          = {10.1109/NOF.2017.8251230},
  timestamp    = {Mon, 16 Oct 2023 01:00:00 +0200},
  biburl       = {https://dblp.org/rec/conf/nof/VilaltaVMSMCMA17.bib},
  bibsource    = {dblp computer science bibliography, https://dblp.org}
}
@article{DBLP:journals/corr/abs-1708-04469,
  author       = {Thomas Zenkel and
                  Ramon Sanabria and
                  Florian Metze and
                  Jan Niehues and
                  Matthias Sperber and
                  Sebastian St{\"{u}}ker and
                  Alex Waibel},
  title        = {Comparison of Decoding Strategies for {CTC} Acoustic Models},
  journal      = {CoRR},
  volume       = {abs/1708.04469},
  year         = {2017},
  url          = {http://arxiv.org/abs/1708.04469},
  eprinttype    = {arXiv},
  eprint       = {1708.04469},
  timestamp    = {Mon, 13 Aug 2018 01:00:00 +0200},
  biburl       = {https://dblp.org/rec/journals/corr/abs-1708-04469.bib},
  bibsource    = {dblp computer science bibliography, https://dblp.org}
}
@article{DBLP:journals/corr/abs-1712-06855,
  author       = {Thomas Zenkel and
                  Ramon Sanabria and
                  Florian Metze and
                  Alex Waibel},
  title        = {Subword and Crossword Units for {CTC} Acoustic Models},
  journal      = {CoRR},
  volume       = {abs/1712.06855},
  year         = {2017},
  url          = {http://arxiv.org/abs/1712.06855},
  eprinttype    = {arXiv},
  eprint       = {1712.06855},
  timestamp    = {Mon, 13 Aug 2018 01:00:00 +0200},
  biburl       = {https://dblp.org/rec/journals/corr/abs-1712-06855.bib},
  bibsource    = {dblp computer science bibliography, https://dblp.org}
}
@article{DBLP:journals/corr/SanabriaMT16,
  author       = {Ramon Sanabria and
                  Florian Metze and
                  Fernando De la Torre},
  title        = {Robust end-to-end deep audiovisual speech recognition},
  journal      = {CoRR},
  volume       = {abs/1611.06986},
  year         = {2016},
  url          = {http://arxiv.org/abs/1611.06986},
  eprinttype    = {arXiv},
  eprint       = {1611.06986},
  timestamp    = {Mon, 13 Aug 2018 01:00:00 +0200},
  biburl       = {https://dblp.org/rec/journals/corr/SanabriaMT16.bib},
  bibsource    = {dblp computer science bibliography, https://dblp.org}
}
@article{DBLP:journals/corr/abs-1207-1031,
  author       = {Jaume Barcel{\'{o}} and
                  Boris Bellalta and
                  Roger Baig and
                  Ramon Roca and
                  Albert Domingo and
                  Luis Sanabria{-}Russo and
                  Cristina Cano and
                  Miquel Oliver},
  title        = {Bottom-up Broadband Initiatives in the Commons for Europe Project},
  journal      = {CoRR},
  volume       = {abs/1207.1031},
  year         = {2012},
  url          = {http://arxiv.org/abs/1207.1031},
  eprinttype    = {arXiv},
  eprint       = {1207.1031},
  timestamp    = {Mon, 16 Oct 2023 01:00:00 +0200},
  biburl       = {https://dblp.org/rec/journals/corr/abs-1207-1031.bib},
  bibsource    = {dblp computer science bibliography, https://dblp.org}
}
a service of  Schloss Dagstuhl - Leibniz Center for Informatics