Pushing the Limits of Semi-Supervised Learning for Automatic Speech Recognition

10/20/2020
by   Yu Zhang, et al.
0

We employ a combination of recent developments in semi-supervised learning for automatic speech recognition to obtain state-of-the-art results on LibriSpeech utilizing the unlabeled audio of the Libri-Light dataset. More precisely, we carry out noisy student training with SpecAugment using giant Conformer models pre-trained using wav2vec 2.0 pre-training. By doing so, we are able to achieve word-error-rates (WERs) 1.4 test/test-other sets against the current state-of-the-art WERs 1.7

READ FULL TEXT

page 1

page 2

page 3

page 4

05/19/2020

Improved Noisy Student Training for Automatic Speech Recognition

Recently, a semi-supervised learning method known as "noisy student trai...
02/01/2020

Fully Learnable Front-End for Multi-Channel Acoustic Modeling using Semi-Supervised Learning

In this work, we investigated the teacher-student training paradigm to t...
10/01/2020

SESQA: semi-supervised learning for speech quality assessment

Automatic speech quality assessment is an important, transversal task wh...
09/14/2021

Performance-Efficiency Trade-offs in Unsupervised Pre-training for Speech Recognition

This paper is a study of performance-efficiency trade-offs in pre-traine...
12/01/2020

Semi-Supervised Noisy Student Pre-training on EfficientNet Architectures for Plant Pathology Classification

In recent years, deep learning has vastly improved the identification an...
11/20/2009

Likelihood-based semi-supervised model selection with applications to speech processing

In conventional supervised pattern recognition tasks, model selection is...
10/03/2016

Semi-supervised Learning with Sparse Autoencoders in Phone Classification

We propose the application of a semi-supervised learning method to impro...