1.1k citations · 4.4k across the 113 of their papers we have counts for
15 papers · 1 filter
MLS: A Large-Scale Multilingual Dataset for Speech Research
Vineel Pratap, Qiantong Xu, Anuroop Sriram +2
This paper introduces Multilingual LibriSpeech (MLS) dataset, a large multilingual corpus suitable for speech research. The dataset is derived from read audiobooks from LibriVox an…
Joint Masked CPC and CTC Training for ASR
Chaitanya Talnikar, Tatiana Likhomanenko, Ronan Collobert +1
Self-supervised learning (SSL) has shown promise in learning representations of audio that are useful for automatic speech recognition (ASR). But, training SSL models like wav2vec~…
Self-training and Pre-training are Complementary for Speech Recognition
Qiantong Xu, Alexei Baevski, Tatiana Likhomanenko +5
Self-training and unsupervised pre-training have emerged as effective approaches to improve speech recognition systems using unlabeled data. However, it is not clear whether they l…
Population Based Training for Data Augmentation and Regularization in Speech Recognition
Daniel Haziza, Jérémy Rapin, Gabriel Synnaeve
Varying data augmentation policies and regularization over the course of optimization has led to performance improvements over using fixed values. We show that population based tra…
Rethinking Evaluation in ASR: Are Our Models Robust Enough?
Tatiana Likhomanenko, Qiantong Xu, Vineel Pratap +5
Is pushing numbers on a single benchmark valuable in automatic speech recognition? Research results in acoustic modeling are typically evaluated based on performance on a single da…
SlimIPL: Language-Model-Free Iterative Pseudo-Labeling
Tatiana Likhomanenko, Qiantong Xu, Jacob Kahn +2
Recent results in end-to-end automatic speech recognition have demonstrated the efficacy of pseudo-labeling for semi-supervised models trained both with Connectionist Temporal Clas…
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…
Data Augmenting Contrastive Learning of Speech Representations in the Time Domain
Eugene Kharitonov, Morgane Rivière, Gabriel Synnaeve +4
Contrastive Predictive Coding (CPC), based on predicting future segments of speech based on past segments is emerging as a powerful algorithm for representation learning of speech…
Real Time Speech Enhancement in the Waveform Domain
Alexandre Defossez, Gabriel Synnaeve, Yossi Adi
We present a causal speech enhancement model working on the raw waveform that runs in real-time on a laptop CPU. The proposed model is based on an encoder-decoder architecture with…
End-to-End Object Detection with Transformers
Nicolas Carion, Francisco Massa, Gabriel Synnaeve +3
We present a new method that views object detection as a direct set prediction problem. Our approach streamlines the detection pipeline, effectively removing the need for many hand…
Contextualizing ASR Lattice Rescoring with Hybrid Pointer Network Language Model
Da-Rong Liu, Chunxi Liu, Frank Zhang +3
Videos uploaded on social media are often accompanied with textual descriptions. In building automatic speech recognition (ASR) systems for videos, we can exploit the contextual in…
Iterative Pseudo-Labeling for Speech Recognition
Qiantong Xu, Tatiana Likhomanenko, Jacob Kahn +3
Pseudo-labeling has recently shown promise in end-to-end automatic speech recognition (ASR). We study Iterative Pseudo-Labeling (IPL), a semi-supervised algorithm which efficiently…
Semi-Supervised Speech Recognition via Local Prior Matching
Wei-Ning Hsu, Ann Lee, Gabriel Synnaeve +1
For sequence transduction tasks like speech recognition, a strong structured prior model encodes rich information about the target space, implicitly ruling out invalid sequences by…
Polygames: Improved Zero Learning
Tristan Cazenave, Yen-Chi Chen, Guan-Wei Chen +21
Since DeepMind's AlphaZero, Zero learning quickly became the state-of-the-art method for many board games. It can be improved using a fully convolutional structure (no fully connec…
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…