470 citations · 1.5k across the 10 of their papers we have counts for
12 papers
Flashlight: Enabling Innovation in Tools for Machine Learning
Jacob Kahn, Vineel Pratap, Tatiana Likhomanenko +11
As the computational requirements for machine learning systems and the size and complexity of machine learning frameworks increases, essential framework innovation has become chall…
Self-supervised Pretraining of Visual Features in the Wild
Priya Goyal, Mathilde Caron, Benjamin Lefaudeux +8
Recently, self-supervised learning methods like MoCo, SimCLR, BYOL and SwAV have reduced the gap with supervised methods. These results have been achieved in a control environment,…
Beyond English-Centric Multilingual Machine Translation
Angela Fan, Shruti Bhosale, Holger Schwenk +14
Existing work in translation demonstrated the potential of massively multilingual machine translation by training a single model able to translate between any pair of languages. Ho…
Massively Multilingual ASR: 50 Languages, 1 Model, 1 Billion Parameters
Vineel Pratap, Anuroop Sriram, Paden Tomasello +4
We study training a single acoustic model for multiple languages with the aim of improving automatic speech recognition (ASR) performance on low-resource languages, and over-all si…
Large scale weakly and semi-supervised learning for low-resource video ASR
Kritika Singh, Vimal Manohar, Alex Xiao +7
Many semi- and weakly-supervised approaches have been investigated for overcoming the labeling cost of building high quality speech recognition systems. On the challenging task of…
Scaling Up Online Speech Recognition Using ConvNets
Vineel Pratap, Qiantong Xu, Jacob Kahn +6
We design an online end-to-end speech recognition system based on Time-Depth Separable (TDS) convolutions and Connectionist Temporal Classification (CTC). We improve the core TDS a…
Libri-Light: A Benchmark for ASR with Limited or No Supervision
Jacob Kahn, Morgane Rivière, Weiyi Zheng +12
We introduce a new collection of spoken English audio suitable for training speech recognition systems under limited or no supervision. It is derived from open-source audio books f…
End-to-end ASR: from Supervised to Semi-Supervised Learning with Modern Architectures
Gabriel Synnaeve, Qiantong Xu, Jacob Kahn +6
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 functio…
wav2letter++: The Fastest Open-source Speech Recognition System
Vineel Pratap, Awni Hannun, Qiantong Xu +5
This paper introduces wav2letter++, the fastest open-source deep learning speech recognition framework. wav2letter++ is written entirely in C++, and uses the ArrayFire tensor libra…
Fully Convolutional Speech Recognition
Neil Zeghidour, Qiantong Xu, Vitaliy Liptchinsky +3
Current state-of-the-art speech recognition systems build on recurrent neural networks for acoustic and/or language modeling, and rely on feature extraction pipelines to extract me…
To Reverse the Gradient or Not: An Empirical Comparison of Adversarial and Multi-task Learning in Speech Recognition
Yossi Adi, Neil Zeghidour, Ronan Collobert +3
Transcribed datasets typically contain speaker identity for each instance in the data. We investigate two ways to incorporate this information during training: Multi-Task Learning…
Letter-Based Speech Recognition with Gated ConvNets
Vitaliy Liptchinsky, Gabriel Synnaeve, Ronan Collobert
In the recent literature, "end-to-end" speech systems often refer to letter-based acoustic models trained in a sequence-to-sequence manner, either via a recurrent model or via a st…