Get our free extension to see links to code for papers anywhere online!

Chrome logo Add to Chrome

Firefox logo Add to Firefox
Picture for Emmanuel Dupoux

Emmanuel Dupoux

LSCP, CoML

The Interspeech Zero Resource Speech Challenge 2021: Spoken language modelling


Apr 29, 2021
Ewan Dunbar, Mathieu Bernard, Nicolas Hamilakis, Tu Anh Nguyen, Maureen de Seyssel, Patricia Rozé, Morgane Rivière, Eugene Kharitonov, Emmanuel Dupoux

Figure 1 for The Interspeech Zero Resource Speech Challenge 2021: Spoken language modelling
Figure 2 for The Interspeech Zero Resource Speech Challenge 2021: Spoken language modelling
* Submitted to Interspeech 2021. arXiv admin note: text overlap with arXiv:2011.11588 
  Access Paper or Ask Questions

Speech Resynthesis from Discrete Disentangled Self-Supervised Representations


Apr 02, 2021
Adam Polyak, Yossi Adi, Jade Copet, Eugene Kharitonov, Kushal Lakhotia, Wei-Ning Hsu, Abdelrahman Mohamed, Emmanuel Dupoux

Figure 1 for Speech Resynthesis from Discrete Disentangled Self-Supervised Representations
Figure 2 for Speech Resynthesis from Discrete Disentangled Self-Supervised Representations
Figure 3 for Speech Resynthesis from Discrete Disentangled Self-Supervised Representations
Figure 4 for Speech Resynthesis from Discrete Disentangled Self-Supervised Representations

  Access Paper or Ask Questions

Learning spectro-temporal representations of complex sounds with parameterized neural networks


Mar 12, 2021
Rachid Riad, Julien Karadayi, Anne-Catherine Bachoud-Lévi, Emmanuel Dupoux

Figure 1 for Learning spectro-temporal representations of complex sounds with parameterized neural networks
Figure 2 for Learning spectro-temporal representations of complex sounds with parameterized neural networks
Figure 3 for Learning spectro-temporal representations of complex sounds with parameterized neural networks
Figure 4 for Learning spectro-temporal representations of complex sounds with parameterized neural networks

  Access Paper or Ask Questions

Generative Spoken Language Modeling from Raw Audio


Feb 01, 2021
Kushal Lakhotia, Evgeny Kharitonov, Wei-Ning Hsu, Yossi Adi, Adam Polyak, Benjamin Bolte, Tu-Anh Nguyen, Jade Copet, Alexei Baevski, Adelrahman Mohamed, Emmanuel Dupoux

Figure 1 for Generative Spoken Language Modeling from Raw Audio
Figure 2 for Generative Spoken Language Modeling from Raw Audio
Figure 3 for Generative Spoken Language Modeling from Raw Audio
Figure 4 for Generative Spoken Language Modeling from Raw Audio

  Access Paper or Ask Questions

VoxPopuli: A Large-Scale Multilingual Speech Corpus for Representation Learning, Semi-Supervised Learning and Interpretation


Jan 02, 2021
Changhan Wang, Morgane Rivière, Ann Lee, Anne Wu, Chaitanya Talnikar, Daniel Haziza, Mary Williamson, Juan Pino, Emmanuel Dupoux

Figure 1 for VoxPopuli: A Large-Scale Multilingual Speech Corpus for Representation Learning, Semi-Supervised Learning and Interpretation
Figure 2 for VoxPopuli: A Large-Scale Multilingual Speech Corpus for Representation Learning, Semi-Supervised Learning and Interpretation
Figure 3 for VoxPopuli: A Large-Scale Multilingual Speech Corpus for Representation Learning, Semi-Supervised Learning and Interpretation
Figure 4 for VoxPopuli: A Large-Scale Multilingual Speech Corpus for Representation Learning, Semi-Supervised Learning and Interpretation

  Access Paper or Ask Questions

The Zero Resource Speech Benchmark 2021: Metrics and baselines for unsupervised spoken language modeling


Dec 01, 2020
Tu Anh Nguyen, Maureen de Seyssel, Patricia Rozé, Morgane Rivière, Evgeny Kharitonov, Alexei Baevski, Ewan Dunbar, Emmanuel Dupoux

Figure 1 for The Zero Resource Speech Benchmark 2021: Metrics and baselines for unsupervised spoken language modeling
Figure 2 for The Zero Resource Speech Benchmark 2021: Metrics and baselines for unsupervised spoken language modeling
Figure 3 for The Zero Resource Speech Benchmark 2021: Metrics and baselines for unsupervised spoken language modeling
Figure 4 for The Zero Resource Speech Benchmark 2021: Metrics and baselines for unsupervised spoken language modeling
* 14 pages, including references and supplementary material 
  Access Paper or Ask Questions

Comparison of Speaker Role Recognition and Speaker Enrollment Protocol for conversational Clinical Interviews


Nov 05, 2020
Rachid Riad, Hadrien Titeux, Laurie Lemoine, Justine Montillot, Agnes Sliwinski, Jennifer Hamet Bagnou, Xuan Nga Cao, Anne-Catherine Bachoud-Lévi, Emmanuel Dupoux

Figure 1 for Comparison of Speaker Role Recognition and Speaker Enrollment Protocol for conversational Clinical Interviews
Figure 2 for Comparison of Speaker Role Recognition and Speaker Enrollment Protocol for conversational Clinical Interviews
Figure 3 for Comparison of Speaker Role Recognition and Speaker Enrollment Protocol for conversational Clinical Interviews
Figure 4 for Comparison of Speaker Role Recognition and Speaker Enrollment Protocol for conversational Clinical Interviews
* Submitted to ICASSP 2021,1 pages of supplementary material appear only in the arxiv version 
  Access Paper or Ask Questions

The Zero Resource Speech Challenge 2020: Discovering discrete subword and word units


Oct 12, 2020
Ewan Dunbar, Julien Karadayi, Mathieu Bernard, Xuan-Nga Cao, Robin Algayres, Lucas Ondel, Laurent Besacier, Sakriani Sakti, Emmanuel Dupoux

Figure 1 for The Zero Resource Speech Challenge 2020: Discovering discrete subword and word units
Figure 2 for The Zero Resource Speech Challenge 2020: Discovering discrete subword and word units
Figure 3 for The Zero Resource Speech Challenge 2020: Discovering discrete subword and word units
* Proceedings of Interspeech 2020 
  Access Paper or Ask Questions

Analogies minus analogy test: measuring regularities in word embeddings


Oct 07, 2020
Louis Fournier, Emmanuel Dupoux, Ewan Dunbar

Figure 1 for Analogies minus analogy test: measuring regularities in word embeddings
Figure 2 for Analogies minus analogy test: measuring regularities in word embeddings
Figure 3 for Analogies minus analogy test: measuring regularities in word embeddings
Figure 4 for Analogies minus analogy test: measuring regularities in word embeddings
* Proceedings of CoNLL 2020 
  Access Paper or Ask Questions

"LazImpa": Lazy and Impatient neural agents learn to communicate efficiently


Oct 05, 2020
Mathieu Rita, Rahma Chaabouni, Emmanuel Dupoux

Figure 1 for "LazImpa": Lazy and Impatient neural agents learn to communicate efficiently
Figure 2 for "LazImpa": Lazy and Impatient neural agents learn to communicate efficiently
Figure 3 for "LazImpa": Lazy and Impatient neural agents learn to communicate efficiently
Figure 4 for "LazImpa": Lazy and Impatient neural agents learn to communicate efficiently
* Accepted to CoNLL 2020 
  Access Paper or Ask Questions

Evaluating the reliability of acoustic speech embeddings


Jul 27, 2020
Robin Algayres, Mohamed Salah Zaiem, Benoit Sagot, Emmanuel Dupoux

Figure 1 for Evaluating the reliability of acoustic speech embeddings
Figure 2 for Evaluating the reliability of acoustic speech embeddings
Figure 3 for Evaluating the reliability of acoustic speech embeddings
* Conference paper at Interspeech 2020 
  Access Paper or Ask Questions

Data Augmenting Contrastive Learning of Speech Representations in the Time Domain


Jul 02, 2020
Eugene Kharitonov, Morgane Rivière, Gabriel Synnaeve, Lior Wolf, Pierre-Emmanuel Mazaré, Matthijs Douze, Emmanuel Dupoux

Figure 1 for Data Augmenting Contrastive Learning of Speech Representations in the Time Domain
Figure 2 for Data Augmenting Contrastive Learning of Speech Representations in the Time Domain
Figure 3 for Data Augmenting Contrastive Learning of Speech Representations in the Time Domain
Figure 4 for Data Augmenting Contrastive Learning of Speech Representations in the Time Domain

  Access Paper or Ask Questions

Vocal markers from sustained phonation in Huntington's Disease


Jun 09, 2020
Rachid Riad, Hadrien Titeux, Laurie Lemoine, Justine Montillot, Jennifer Hamet Bagnou, Xuan Nga Cao, Emmanuel Dupoux, Anne-Catherine Bachoud-Lévi

Figure 1 for Vocal markers from sustained phonation in Huntington's Disease
Figure 2 for Vocal markers from sustained phonation in Huntington's Disease
Figure 3 for Vocal markers from sustained phonation in Huntington's Disease
Figure 4 for Vocal markers from sustained phonation in Huntington's Disease
* submitted to INTERSPEECH 2020. 1 pages of supplementary material appear only in the arxiv version 
  Access Paper or Ask Questions

Occlusion resistant learning of intuitive physics from videos


Apr 30, 2020
Ronan Riochet, Josef Sivic, Ivan Laptev, Emmanuel Dupoux

Figure 1 for Occlusion resistant learning of intuitive physics from videos
Figure 2 for Occlusion resistant learning of intuitive physics from videos
Figure 3 for Occlusion resistant learning of intuitive physics from videos
Figure 4 for Occlusion resistant learning of intuitive physics from videos

  Access Paper or Ask Questions

Compositionality and Generalization in Emergent Languages


Apr 20, 2020
Rahma Chaabouni, Eugene Kharitonov, Diane Bouchacourt, Emmanuel Dupoux, Marco Baroni

Figure 1 for Compositionality and Generalization in Emergent Languages
Figure 2 for Compositionality and Generalization in Emergent Languages
Figure 3 for Compositionality and Generalization in Emergent Languages
Figure 4 for Compositionality and Generalization in Emergent Languages

  Access Paper or Ask Questions

Seshat: A tool for managing and verifying annotation campaigns of audio data


Mar 03, 2020
Hadrien Titeux, Rachid Riad, Xuan-Nga Cao, Nicolas Hamilakis, Kris Madden, Alejandrina Cristia, Anne-Catherine Bachoud-Lévi, Emmanuel Dupoux

Figure 1 for Seshat: A tool for managing and verifying annotation campaigns of audio data
Figure 2 for Seshat: A tool for managing and verifying annotation campaigns of audio data
Figure 3 for Seshat: A tool for managing and verifying annotation campaigns of audio data
Figure 4 for Seshat: A tool for managing and verifying annotation campaigns of audio data
* LREC, May 2020, Marseilles, France 
  Access Paper or Ask Questions

Identification of primary and collateral tracks in stuttered speech


Mar 02, 2020
Rachid Riad, Anne-Catherine Bachoud-Lévi, Frank Rudzicz, Emmanuel Dupoux

Figure 1 for Identification of primary and collateral tracks in stuttered speech
Figure 2 for Identification of primary and collateral tracks in stuttered speech
Figure 3 for Identification of primary and collateral tracks in stuttered speech
Figure 4 for Identification of primary and collateral tracks in stuttered speech
* To be published in LREC 2020 
  Access Paper or Ask Questions

Unsupervised pretraining transfers well across languages


Feb 07, 2020
Morgane Rivière, Armand Joulin, Pierre-Emmanuel Mazaré, Emmanuel Dupoux

Figure 1 for Unsupervised pretraining transfers well across languages
Figure 2 for Unsupervised pretraining transfers well across languages
Figure 3 for Unsupervised pretraining transfers well across languages
Figure 4 for Unsupervised pretraining transfers well across languages
* ICASSP 2020 
 * 6 pages. Accepted at ICASSP 2020. However the 2 pages of supplementary materials will appear only in the arxiv version 
  Access Paper or Ask Questions

Libri-Light: A Benchmark for ASR with Limited or No Supervision


Dec 17, 2019
Jacob Kahn, Morgane Rivière, Weiyi Zheng, Evgeny Kharitonov, Qiantong Xu, Pierre-Emmanuel Mazaré, Julien Karadayi, Vitaliy Liptchinsky, Ronan Collobert, Christian Fuegen, Tatiana Likhomanenko, Gabriel Synnaeve, Armand Joulin, Abdelrahman Mohamed, Emmanuel Dupoux

Figure 1 for Libri-Light: A Benchmark for ASR with Limited or No Supervision
Figure 2 for Libri-Light: A Benchmark for ASR with Limited or No Supervision
Figure 3 for Libri-Light: A Benchmark for ASR with Limited or No Supervision
Figure 4 for Libri-Light: A Benchmark for ASR with Limited or No Supervision

  Access Paper or Ask Questions

Modeling German Verb Argument Structures: LSTMs vs. Humans


Nov 30, 2019
Charlotte Rochereau, Benoît Sagot, Emmanuel Dupoux

Figure 1 for Modeling German Verb Argument Structures: LSTMs vs. Humans
Figure 2 for Modeling German Verb Argument Structures: LSTMs vs. Humans
Figure 3 for Modeling German Verb Argument Structures: LSTMs vs. Humans
Figure 4 for Modeling German Verb Argument Structures: LSTMs vs. Humans

  Access Paper or Ask Questions

Word-order biases in deep-agent emergent communication


Jun 14, 2019
Rahma Chaabouni, Eugene Kharitonov, Alessandro Lazaric, Emmanuel Dupoux, Marco Baroni

Figure 1 for Word-order biases in deep-agent emergent communication
Figure 2 for Word-order biases in deep-agent emergent communication
Figure 3 for Word-order biases in deep-agent emergent communication
Figure 4 for Word-order biases in deep-agent emergent communication
* Conference: Association for Computational Linguistics (ACL) 
  Access Paper or Ask Questions

Anti-efficient encoding in emergent communication


Jun 13, 2019
Rahma Chaabouni, Eugene Kharitonov, Emmanuel Dupoux, Marco Baroni

Figure 1 for Anti-efficient encoding in emergent communication
Figure 2 for Anti-efficient encoding in emergent communication
Figure 3 for Anti-efficient encoding in emergent communication
Figure 4 for Anti-efficient encoding in emergent communication

  Access Paper or Ask Questions

The Zero Resource Speech Challenge 2019: TTS without T


Apr 25, 2019
Ewan Dunbar, Robin Algayres, Julien Karadayi, Mathieu Bernard, Juan Benjumea, Xuan-Nga Cao, Lucie Miskic, Charlotte Dugrain, Lucas Ondel, Alan W. Black, Laurent Besacier, Sakriani Sakti, Emmanuel Dupoux

Figure 1 for The Zero Resource Speech Challenge 2019: TTS without T
Figure 2 for The Zero Resource Speech Challenge 2019: TTS without T
Figure 3 for The Zero Resource Speech Challenge 2019: TTS without T
Figure 4 for The Zero Resource Speech Challenge 2019: TTS without T
* Interspeech 2019 
  Access Paper or Ask Questions