activity
20112026
most citedNatural Language Processing (almost) from Scratch

5.2k citations · 5.6k across the 17 of their papers we have counts for

collaborators
Showing eess.ASShow all

5 papers · 1 filter

eess.AS2023

Unsupervised ASR via Cross-Lingual Pseudo-Labeling

Tatiana Likhomanenko, Loren Lugosch, Ronan Collobert

Recent work has shown that it is possible to train an automatic speech recognition (ASR) system using only unpaired audio and text. Existing unsupervised AS…

eess.AS2021

Word Order Does Not Matter For Speech Recognition

Vineel Pratap, Qiantong Xu, Tatiana Likhomanenko +2

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 n…

eess.AS20211 cited

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

Vimal Manohar, Tatiana Likhomanenko, Qiantong Xu +5

In this paper, we introduce the Kaizen framework that uses a continuously improving teacher to generate pseudo-labels for semi-supervised speech recognition (ASR). The proposed app…

eess.AS2020354 cited

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…

eess.AS2020

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…