Domain Adversarial Training for Accented Speech Recognition

06/07/2018
by   Sining Sun, et al.
0

In this paper, we propose a domain adversarial training (DAT) algorithm to alleviate the accented speech recognition problem. In order to reduce the mismatch between labeled source domain data ("standard" accent) and unlabeled target domain data (with heavy accents), we augment the learning objective for a Kaldi TDNN network with a domain adversarial training (DAT) objective to encourage the model to learn accent-invariant features. In experiments with three Mandarin accents, we show that DAT yields up to 7.45 error rate reduction when we do not have transcriptions of the accented speech, compared with the baseline trained on standard accent data only. We also find a benefit from DAT when used in combination with training from automatic transcriptions on the accented data. Furthermore, we find that DAT is superior to multi-task learning for accented speech recognition.

READ FULL TEXT

page 1

page 2

page 3

page 4

research
11/21/2017

Unsupervised Adaptation with Domain Separation Networks for Robust Speech Recognition

Unsupervised domain adaptation of speech signal aims at adapting a well-...
research
08/04/2017

Improving Speaker-Independent Lipreading with Domain-Adversarial Training

We present a Lipreading system, i.e. a speech recognition system using o...
research
04/29/2023

Adversarial Representation Learning for Robust Privacy Preservation in Audio

Sound event detection systems are widely used in various applications su...
research
12/05/2021

Toward Real-World Pathological Voice Detection

Voice disorders significantly undermine people's ability to speak in the...
research
04/08/2019

Issue Framing in Online Discussion Fora

In online discussion fora, speakers often make arguments for or against ...
research
06/17/2019

Adversarial Training for Multilingual Acoustic Modeling

Multilingual training has been shown to improve acoustic modeling perfor...
research
01/10/2020

Improving Dysarthric Speech Intelligibility Using Cycle-consistent Adversarial Training

Dysarthria is a motor speech impairment affecting millions of people. Dy...

Please sign up or login with your details

Forgot password? Click here to reset