research
∙
05/19/2023
Unsupervised ASR via Cross-Lingual Pseudo-Labeling
Recent work has shown that it is possible to train an unsupervised autom...
share
research
∙
11/11/2022
Continuous Soft Pseudo-Labeling in ASR
Continuous pseudo-labeling (PL) algorithms such as slimIPL have recently...
research
∙
11/02/2022
More Speaking or More Speakers?
Self-training (ST) and self-supervised learning (SSL) methods have demon...
research
∙
10/17/2022
Continuous Pseudo-Labeling from the Start
Self-training (ST), or pseudo-labeling has sparked significant interest ...
research
∙
01/29/2022
Flashlight: Enabling Innovation in Tools for Machine Learning
As the computational requirements for machine learning systems and the s...
research
∙
01/28/2022
Star Temporal Classification: Sequence Classification with Partially Labeled Data
We develop an algorithm which can learn from partially labeled and unseg...
research
∙
10/30/2021
Pseudo-Labeling for Massively Multilingual Speech Recognition
Semi-supervised learning through pseudo-labeling has become a staple of ...
research
∙
10/12/2021
Word Order Does Not Matter For Speech Recognition
In this paper, we study training of automatic speech recognition system ...
research
∙
06/14/2021
Kaizen: Continuously improving teacher using Exponential Moving Average for semi-supervised speech recognition
In this paper, we introduce the Kaizen framework that uses a continuousl...
research
∙
06/06/2021
CAPE: Encoding Relative Positions with Continuous Augmented Positional Embeddings
Without positional information, attention-based transformer neural netwo...
research
∙
04/02/2021
Robust wav2vec 2.0: Analyzing Domain Shift in Self-Supervised Pre-Training
Self-supervised learning of speech representations has been a very activ...
research
∙
12/07/2020
MLS: A Large-Scale Multilingual Dataset for Speech Research
This paper introduces Multilingual LibriSpeech (MLS) dataset, a large mu...
research
∙
10/30/2020
Joint Masked CPC and CTC Training for ASR
Self-supervised learning (SSL) has shown promise in learning representat...
research
∙
10/22/2020
Rethinking Evaluation in ASR: Are Our Models Robust Enough?
Is pushing numbers on a single benchmark valuable in automatic speech re...
research
∙
10/22/2020
slimIPL: Language-Model-Free Iterative Pseudo-Labeling
Recent results in end-to-end ASR have demonstrated the efficacy of simpl...
research
∙
10/22/2020
Self-training and Pre-training are Complementary for Speech Recognition
Self-training and unsupervised pre-training have emerged as effective ap...
research
∙
07/06/2020
Massively Multilingual ASR: 50 Languages, 1 Model, 1 Billion Parameters
We study training a single acoustic model for multiple languages with th...
research
∙
06/24/2020
Unsupervised Cross-lingual Representation Learning for Speech Recognition
This paper presents XLSR which learns cross-lingual speech representatio...
research
∙
05/19/2020
Iterative Pseudo-Labeling for Speech Recognition
Pseudo-labeling has recently shown promise in end-to-end automatic speec...
research
∙
05/01/2020
Multi-scale Transformer Language Models
We investigate multi-scale transformer language models that learn repres...
research
∙
01/27/2020
Scaling Up Online Speech Recognition Using ConvNets
We design an online end-to-end speech recognition system based on Time-D...
research
∙
12/17/2019
Libri-Light: A Benchmark for ASR with Limited or No Supervision
We introduce a new collection of spoken English audio suitable for train...
research
∙
11/19/2019
End-to-end ASR: from Supervised to Semi-Supervised Learning with Modern Architectures
We study ResNet-, Time-Depth Separable ConvNets-, and Transformer-based ...
research
∙
06/10/2019
Word-level Speech Recognition with a Dynamic Lexicon
We propose a direct-to-word sequence model with a dynamic lexicon. Our w...
research
∙
04/11/2019
wav2vec: Unsupervised Pre-training for Speech Recognition
We explore unsupervised pre-training for speech recognition by learning ...
research
∙
04/09/2019
Who Needs Words? Lexicon-Free Speech Recognition
Lexicon-free speech recognition naturally deals with the problem of out-...
research
∙
04/04/2019
Sequence-to-Sequence Speech Recognition with Time-Depth Separable Convolutions
We propose a fully convolutional sequence-to-sequence encoder architectu...
research
∙
02/16/2019
A Fully Differentiable Beam Search Decoder
We introduce a new beam search decoder that is fully differentiable, mak...
research
∙
12/18/2018
wav2letter++: The Fastest Open-source Speech Recognition System
This paper introduces wav2letter++, the fastest open-source deep learnin...
research
∙
12/17/2018
Fully Convolutional Speech Recognition
Current state-of-the-art speech recognition systems build on recurrent n...
research
∙
12/09/2018
To Reverse the Gradient or Not: An Empirical Comparison of Adversarial and Multi-task Learning in Speech Recognition
Transcribed datasets typically contain speaker identity for each instanc...
research
∙
06/19/2018
End-to-End Speech Recognition From the Raw Waveform
State-of-the-art speech recognition systems rely on fixed, hand-crafted ...
research
∙
12/22/2017
Letter-Based Speech Recognition with Gated ConvNets
In this paper we introduce a new speech recognition system, leveraging a...
research
∙
09/11/2016
Wav2Letter: an End-to-End ConvNet-based Speech Recognition System
This paper presents a simple end-to-end model for speech recognition, co...
research
∙
06/30/2016
Neural Network-based Word Alignment through Score Aggregation
We present a simple neural network for word alignment that builds source...
research
∙
03/29/2016
Learning to Refine Object Segments
Object segmentation requires both object-level information and low-level...
research
∙
11/12/2015
ProNet: Learning to Propose Object-specific Boxes for Cascaded Neural Networks
This paper aims to classify and locate objects accurately and efficientl...
research
∙
06/20/2015
Learning to Segment Object Candidates
Recent object detection systems rely on two critical steps: (1) a set of...
research
∙
06/18/2015
"The Sum of Its Parts": Joint Learning of Word and Phrase Representations with Autoencoders
Recently, there has been a lot of effort to represent words in continuou...
research
∙
02/12/2015
Phrase-based Image Captioning
Generating a novel textual description of an image is an interesting pro...
research
∙
12/29/2014
Simple Image Description Generator via a Linear Phrase-Based Approach
Generating a novel textual description of an image is an interesting pro...
research
∙
12/22/2014
Learning linearly separable features for speech recognition using convolutional neural networks
Automatic speech recognition systems usually rely on spectral-based feat...
research
∙
12/22/2014
Joint RNN-Based Greedy Parsing and Word Composition
This paper introduces a greedy parser based on neural networks, which le...
research
∙
12/20/2014
Video (language) modeling: a baseline for generative models of natural videos
We propose a strong baseline model for unsupervised feature learning usi...
research
∙
12/19/2014
N-gram-Based Low-Dimensional Representation for Document Classification
The bag-of-words (BOW) model is the common approach for classifying docu...
research
∙
12/16/2014
Rehabilitation of Count-based Models for Word Vector Representations
Recent works on word representations mostly rely on predictive models. D...
research
∙
11/23/2014
From Image-level to Pixel-level Labeling with Convolutional Networks
We are interested in inferring object segmentation by leveraging only ob...
research
∙
12/07/2013
End-to-end Phoneme Sequence Recognition using Convolutional Neural Networks
Most phoneme recognition state-of-the-art systems rely on a classical ne...
research
∙
06/12/2013
Recurrent Convolutional Neural Networks for Scene Parsing
Scene parsing is a technique that consist on giving a label to all pixel...
research
∙
04/03/2013