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 Ronan Collobert

Word Order Does Not Matter For Speech Recognition


Oct 18, 2021
Vineel Pratap, Qiantong Xu, Tatiana Likhomanenko, Gabriel Synnaeve, Ronan Collobert


  Access Paper or Ask Questions

Kaizen: Continuously improving teacher using Exponential Moving Average for semi-supervised speech recognition


Jun 14, 2021
Vimal Manohar, Tatiana Likhomanenko, Qiantong Xu, Wei-Ning Hsu, Ronan Collobert, Yatharth Saraf, Geoffrey Zweig, Abdelrahman Mohamed

* 4 figures, 7 pages; fixed author list going out of margin 

  Access Paper or Ask Questions

CAPE: Encoding Relative Positions with Continuous Augmented Positional Embeddings


Jun 06, 2021
Tatiana Likhomanenko, Qiantong Xu, Ronan Collobert, Gabriel Synnaeve, Alex Rogozhnikov


  Access Paper or Ask Questions

Robust wav2vec 2.0: Analyzing Domain Shift in Self-Supervised Pre-Training


Apr 02, 2021
Wei-Ning Hsu, Anuroop Sriram, Alexei Baevski, Tatiana Likhomanenko, Qiantong Xu, Vineel Pratap, Jacob Kahn, Ann Lee, Ronan Collobert, Gabriel Synnaeve, Michael Auli


  Access Paper or Ask Questions

MLS: A Large-Scale Multilingual Dataset for Speech Research


Dec 19, 2020
Vineel Pratap, Qiantong Xu, Anuroop Sriram, Gabriel Synnaeve, Ronan Collobert

* Interspeech 2020 

  Access Paper or Ask Questions

Joint Masked CPC and CTC Training for ASR


Oct 30, 2020
Chaitanya Talnikar, Tatiana Likhomanenko, Ronan Collobert, Gabriel Synnaeve


  Access Paper or Ask Questions

Rethinking Evaluation in ASR: Are Our Models Robust Enough?


Oct 22, 2020
Tatiana Likhomanenko, Qiantong Xu, Vineel Pratap, Paden Tomasello, Jacob Kahn, Gilad Avidov, Ronan Collobert, Gabriel Synnaeve


  Access Paper or Ask Questions

slimIPL: Language-Model-Free Iterative Pseudo-Labeling


Oct 22, 2020
Tatiana Likhomanenko, Qiantong Xu, Jacob Kahn, Gabriel Synnaeve, Ronan Collobert


  Access Paper or Ask Questions

Self-training and Pre-training are Complementary for Speech Recognition


Oct 22, 2020
Qiantong Xu, Alexei Baevski, Tatiana Likhomanenko, Paden Tomasello, Alexis Conneau, Ronan Collobert, Gabriel Synnaeve, Michael Auli


  Access Paper or Ask Questions

Massively Multilingual ASR: 50 Languages, 1 Model, 1 Billion Parameters


Jul 08, 2020
Vineel Pratap, Anuroop Sriram, Paden Tomasello, Awni Hannun, Vitaliy Liptchinsky, Gabriel Synnaeve, Ronan Collobert


  Access Paper or Ask Questions

Unsupervised Cross-lingual Representation Learning for Speech Recognition


Jun 24, 2020
Alexis Conneau, Alexei Baevski, Ronan Collobert, Abdelrahman Mohamed, Michael Auli


  Access Paper or Ask Questions

Iterative Pseudo-Labeling for Speech Recognition


May 19, 2020
Qiantong Xu, Tatiana Likhomanenko, Jacob Kahn, Awni Hannun, Gabriel Synnaeve, Ronan Collobert


  Access Paper or Ask Questions

Multi-scale Transformer Language Models


May 01, 2020
Sandeep Subramanian, Ronan Collobert, Marc'Aurelio Ranzato, Y-Lan Boureau


  Access Paper or Ask Questions

Scaling Up Online Speech Recognition Using ConvNets


Jan 27, 2020
Vineel Pratap, Qiantong Xu, Jacob Kahn, Gilad Avidov, Tatiana Likhomanenko, Awni Hannun, Vitaliy Liptchinsky, Gabriel Synnaeve, Ronan Collobert


  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


  Access Paper or Ask Questions

End-to-end ASR: from Supervised to Semi-Supervised Learning with Modern Architectures


Nov 19, 2019
Gabriel Synnaeve, Qiantong Xu, Jacob Kahn, Edouard Grave, Tatiana Likhomanenko, Vineel Pratap, Anuroop Sriram, Vitaliy Liptchinsky, Ronan Collobert


  Access Paper or Ask Questions

Word-level Speech Recognition with a Dynamic Lexicon


Jun 10, 2019
Ronan Collobert, Awni Hannun, Gabriel Synnaeve


  Access Paper or Ask Questions

wav2vec: Unsupervised Pre-training for Speech Recognition


May 24, 2019
Steffen Schneider, Alexei Baevski, Ronan Collobert, Michael Auli


  Access Paper or Ask Questions

Who Needs Words? Lexicon-Free Speech Recognition


Apr 09, 2019
Tatiana Likhomanenko, Gabriel Synnaeve, Ronan Collobert

* 8 pages, 1 figure 

  Access Paper or Ask Questions

Sequence-to-Sequence Speech Recognition with Time-Depth Separable Convolutions


Apr 04, 2019
Awni Hannun, Ann Lee, Qiantong Xu, Ronan Collobert


  Access Paper or Ask Questions

A Fully Differentiable Beam Search Decoder


Feb 16, 2019
Ronan Collobert, Awni Hannun, Gabriel Synnaeve


  Access Paper or Ask Questions

wav2letter++: The Fastest Open-source Speech Recognition System


Dec 18, 2018
Vineel Pratap, Awni Hannun, Qiantong Xu, Jeff Cai, Jacob Kahn, Gabriel Synnaeve, Vitaliy Liptchinsky, Ronan Collobert


  Access Paper or Ask Questions

Fully Convolutional Speech Recognition


Dec 17, 2018
Neil Zeghidour, Qiantong Xu, Vitaliy Liptchinsky, Nicolas Usunier, Gabriel Synnaeve, Ronan Collobert


  Access Paper or Ask Questions

To Reverse the Gradient or Not: An Empirical Comparison of Adversarial and Multi-task Learning in Speech Recognition


Dec 13, 2018
Yossi Adi, Neil Zeghidour, Ronan Collobert, Nicolas Usunier, Vitaliy Liptchinsky, Gabriel Synnaeve


  Access Paper or Ask Questions

End-to-End Speech Recognition From the Raw Waveform


Jun 21, 2018
Neil Zeghidour, Nicolas Usunier, Gabriel Synnaeve, Ronan Collobert, Emmanuel Dupoux

* Accepted for presentation at Interspeech 2018 

  Access Paper or Ask Questions

Letter-Based Speech Recognition with Gated ConvNets


Dec 22, 2017
Vitaliy Liptchinsky, Gabriel Synnaeve, Ronan Collobert

* 13 pages.arXiv admin note: text overlap with arXiv:1609.03193 

  Access Paper or Ask Questions

Word Emdeddings through Hellinger PCA


Jan 04, 2017
Rémi Lebret, Ronan Collobert

* Conference of the European Chapter of the Association for Computational Linguistics (EACL), 2014 
* 9 pages, 5 tables 

  Access Paper or Ask Questions