no code implementations • 29 Sep 2023 • Martin Pelikan, Sheikh Shams Azam, Vitaly Feldman, Jan "Honza" Silovsky, Kunal Talwar, Tatiana Likhomanenko
($4. 5$, $10^{-9}$)-$\textbf{DP}$) with a 1. 3% (resp.
Automatic Speech Recognition Automatic Speech Recognition (ASR) +2
no code implementations • 29 Sep 2023 • Andrew Rouditchenko, Ronan Collobert, Tatiana Likhomanenko
Audio-visual speech contains synchronized audio and visual information that provides cross-modal supervision to learn representations for both automatic speech recognition (ASR) and visual speech recognition (VSR).
Audio-Visual Speech Recognition Automatic Speech Recognition +4
no code implementations • 22 Sep 2023 • Sheikh Shams Azam, Tatiana Likhomanenko, Martin Pelikan, Jan "Honza" Silovsky
In this paper, we start by training End-to-End Automatic Speech Recognition (ASR) models using Federated Learning (FL) and examining the fundamental considerations that can be pivotal in minimizing the performance gap in terms of word error rate between models trained using FL versus their centralized counterpart.
Automatic Speech Recognition Automatic Speech Recognition (ASR) +2
no code implementations • 13 Jun 2023 • Haoping Bai, Shancong Mou, Tatiana Likhomanenko, Ramazan Gokberk Cinbis, Oncel Tuzel, Ping Huang, Jiulong Shan, Jianjun Shi, Meng Cao
We introduce the VISION Datasets, a diverse collection of 14 industrial inspection datasets, uniquely poised to meet these challenges.
no code implementations • 19 May 2023 • Tatiana Likhomanenko, Loren Lugosch, Ronan Collobert
Here, "unsupervised" means no labeled audio is available for the $\textit{target}$ language.
Automatic Speech Recognition Automatic Speech Recognition (ASR) +2
1 code implementation • 11 Mar 2023 • Shuangfei Zhai, Tatiana Likhomanenko, Etai Littwin, Dan Busbridge, Jason Ramapuram, Yizhe Zhang, Jiatao Gu, Josh Susskind
We show that $\sigma$Reparam provides stability and robustness with respect to the choice of hyperparameters, going so far as enabling training (a) a Vision Transformer {to competitive performance} without warmup, weight decay, layer normalization or adaptive optimizers; (b) deep architectures in machine translation and (c) speech recognition to competitive performance without warmup and adaptive optimizers.
no code implementations • 20 Dec 2022 • Mozhdeh Gheini, Tatiana Likhomanenko, Matthias Sperber, Hendra Setiawan
Self-training has been shown to be helpful in addressing data scarcity for many domains, including vision, speech, and language.
no code implementations • 11 Nov 2022 • Tatiana Likhomanenko, Ronan Collobert, Navdeep Jaitly, Samy Bengio
Continuous pseudo-labeling (PL) algorithms such as slimIPL have recently emerged as a powerful strategy for semi-supervised learning in speech recognition.
no code implementations • 2 Nov 2022 • Dan Berrebbi, Ronan Collobert, Navdeep Jaitly, Tatiana Likhomanenko
We perform a systematic analysis on both labeled and unlabeled data by varying the number of speakers while keeping the number of hours fixed and vice versa.
Automatic Speech Recognition Automatic Speech Recognition (ASR) +2
no code implementations • 17 Oct 2022 • Dan Berrebbi, Ronan Collobert, Samy Bengio, Navdeep Jaitly, Tatiana Likhomanenko
Nevertheless, these approaches still rely on bootstrapping the ST using an initial supervised learning phase where the model is trained on labeled data alone.
Automatic Speech Recognition Automatic Speech Recognition (ASR) +2
1 code implementation • 15 Jul 2022 • Shuangfei Zhai, Navdeep Jaitly, Jason Ramapuram, Dan Busbridge, Tatiana Likhomanenko, Joseph Yitan Cheng, Walter Talbott, Chen Huang, Hanlin Goh, Joshua Susskind
This pretraining strategy which has been used in BERT models in NLP, Wav2Vec models in Speech and, recently, in MAE models in Vision, forces the model to learn about relationships between the content in different parts of the input using autoencoding related objectives.
2 code implementations • 29 Jan 2022 • Jacob Kahn, Vineel Pratap, Tatiana Likhomanenko, Qiantong Xu, Awni Hannun, Jeff Cai, Paden Tomasello, Ann Lee, Edouard Grave, Gilad Avidov, Benoit Steiner, Vitaliy Liptchinsky, Gabriel Synnaeve, Ronan Collobert
This is in part due to the difficulties involved in prototyping new computational paradigms with existing frameworks.
no code implementations • 30 Oct 2021 • Loren Lugosch, Tatiana Likhomanenko, Gabriel Synnaeve, Ronan Collobert
Semi-supervised learning through pseudo-labeling has become a staple of state-of-the-art monolingual speech recognition systems.
no code implementations • 12 Oct 2021 • Vineel Pratap, Qiantong Xu, Tatiana Likhomanenko, Gabriel Synnaeve, Ronan Collobert
In this paper, we study training of automatic speech recognition system in a weakly supervised setting where the order of words in transcript labels of the audio training data is not known.
Automatic Speech Recognition Automatic Speech Recognition (ASR) +1
no code implementations • 14 Jun 2021 • Vimal Manohar, Tatiana Likhomanenko, Qiantong Xu, Wei-Ning Hsu, Ronan Collobert, Yatharth Saraf, Geoffrey Zweig, Abdelrahman Mohamed
In this paper, we introduce the Kaizen framework that uses a continuously improving teacher to generate pseudo-labels for semi-supervised speech recognition (ASR).
1 code implementation • NeurIPS 2021 • Tatiana Likhomanenko, Qiantong Xu, Gabriel Synnaeve, Ronan Collobert, Alex Rogozhnikov
Absolute or relative positional embeddings are the most popular ways to feed Transformer models with positional information.
3 code implementations • 2 Apr 2021 • Wei-Ning Hsu, Anuroop Sriram, Alexei Baevski, Tatiana Likhomanenko, Qiantong Xu, Vineel Pratap, Jacob Kahn, Ann Lee, Ronan Collobert, Gabriel Synnaeve, Michael Auli
On a large-scale competitive setup, we show that pre-training on unlabeled in-domain data reduces the gap between models trained on in-domain and out-of-domain labeled data by 66%-73%.
1 code implementation • 30 Oct 2020 • Chaitanya Talnikar, Tatiana Likhomanenko, Ronan Collobert, Gabriel Synnaeve
Self-supervised learning (SSL) has shown promise in learning representations of audio that are useful for automatic speech recognition (ASR).
Automatic Speech Recognition Automatic Speech Recognition (ASR) +2
no code implementations • 22 Oct 2020 • Tatiana Likhomanenko, Qiantong Xu, Jacob Kahn, Gabriel Synnaeve, Ronan Collobert
We improve upon the IPL algorithm: as the model learns, we propose to iteratively re-generate transcriptions with hard labels (the most probable tokens), that is, without a language model.
Automatic Speech Recognition Automatic Speech Recognition (ASR) +3
1 code implementation • 22 Oct 2020 • Tatiana Likhomanenko, Qiantong Xu, Vineel Pratap, Paden Tomasello, Jacob Kahn, Gilad Avidov, Ronan Collobert, Gabriel Synnaeve
Finally, we show that training a single acoustic model on the most widely-used datasets - combined - reaches competitive performance on both research and real-world benchmarks.
Automatic Speech Recognition Automatic Speech Recognition (ASR) +1
3 code implementations • 22 Oct 2020 • Qiantong Xu, Alexei Baevski, Tatiana Likhomanenko, Paden Tomasello, Alexis Conneau, Ronan Collobert, Gabriel Synnaeve, Michael Auli
Self-training and unsupervised pre-training have emerged as effective approaches to improve speech recognition systems using unlabeled data.
Ranked #1 on Speech Recognition on LibriSpeech train-clean-100 test-other (using extra training data)
1 code implementation • 19 May 2020 • Qiantong Xu, Tatiana Likhomanenko, Jacob Kahn, Awni Hannun, Gabriel Synnaeve, Ronan Collobert
In particular, IPL fine-tunes an existing model at each iteration using both labeled data and a subset of unlabeled data.
Ranked #11 on Speech Recognition on LibriSpeech test-other
Automatic Speech Recognition Automatic Speech Recognition (ASR) +3
no code implementations • 27 Jan 2020 • Vineel Pratap, Qiantong Xu, Jacob Kahn, Gilad Avidov, Tatiana Likhomanenko, Awni Hannun, Vitaliy Liptchinsky, Gabriel Synnaeve, Ronan Collobert
We design an online end-to-end speech recognition system based on Time-Depth Separable (TDS) convolutions and Connectionist Temporal Classification (CTC).
2 code implementations • 17 Dec 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, Abdel-rahman Mohamed, Emmanuel Dupoux
Additionally, we provide baseline systems and evaluation metrics working under three settings: (1) the zero resource/unsupervised setting (ABX), (2) the semi-supervised setting (PER, CER) and (3) the distant supervision setting (WER).
Ranked #1 on Speech Recognition on Libri-Light test-other (ABX-within metric)
1 code implementation • 19 Nov 2019 • Gabriel Synnaeve, Qiantong Xu, Jacob Kahn, Tatiana Likhomanenko, Edouard Grave, Vineel Pratap, Anuroop Sriram, Vitaliy Liptchinsky, Ronan Collobert
We study pseudo-labeling for the semi-supervised training of ResNet, Time-Depth Separable ConvNets, and Transformers for speech recognition, with either CTC or Seq2Seq loss functions.
Ranked #16 on Speech Recognition on LibriSpeech test-other (using extra training data)
no code implementations • 9 Apr 2019 • Tatiana Likhomanenko, Gabriel Synnaeve, Ronan Collobert
Lexicon-free speech recognition naturally deals with the problem of out-of-vocabulary (OOV) words.
1 code implementation • 4 Jun 2017 • Alex Rogozhnikov, Tatiana Likhomanenko
In machine learning ensemble methods have demonstrated high accuracy for the variety of problems in different areas.
no code implementations • 24 May 2017 • Tatiana Likhomanenko, Denis Derkach, Alex Rogozhnikov
The proposed inclusive flavour-tagging algorithm is applicable to tag the flavour of $B$ mesons in any proton-proton experiment.
1 code implementation • 1 Oct 2015 • Tatiana Likhomanenko, Alex Rogozhnikov, Alexander Baranov, Egor Khairullin, Andrey Ustyuzhanin
Data analysis in fundamental sciences nowadays is an essential process that pushes frontiers of our knowledge and leads to new discoveries.
Data Analysis, Statistics and Probability