Adversarial Training for Multilingual Acoustic Modeling

06/17/2019
by   Ke Hu, et al.
0

Multilingual training has been shown to improve acoustic modeling performance by sharing and transferring knowledge in modeling different languages. Knowledge sharing is usually achieved by using common lower-level layers for different languages in a deep neural network. Recently, the domain adversarial network was proposed to reduce domain mismatch of training data and learn domain-invariant features. It is thus worth exploring whether adversarial training can further promote knowledge sharing in multilingual models. In this work, we apply the domain adversarial network to encourage the shared layers of a multilingual model to learn language-invariant features. Bidirectional Long Short-Term Memory (LSTM) recurrent neural networks (RNN) are used as building blocks. We show that shared layers learned this way contain less language identification information and lead to better performance. In an automatic speech recognition task for seven languages, the resultant acoustic model improves the word error rate (WER) of the multilingual model by 4 average, and the monolingual models by 10

READ FULL TEXT

page 1

page 2

page 3

page 4

research
09/11/2019

Large-Scale Multilingual Speech Recognition with a Streaming End-to-End Model

Multilingual end-to-end (E2E) models have shown great promise in expansi...
research
07/23/2018

Automatic Speech Recognition for Humanitarian Applications in Somali

We present our first efforts in building an automatic speech recognition...
research
06/07/2018

Domain Adversarial Training for Accented Speech Recognition

In this paper, we propose a domain adversarial training (DAT) algorithm ...
research
01/24/2022

Data and knowledge-driven approaches for multilingual training to improve the performance of speech recognition systems of Indian languages

We propose data and knowledge-driven approaches for multilingual trainin...
research
07/05/2018

Neural Language Codes for Multilingual Acoustic Models

Multilingual Speech Recognition is one of the most costly AI problems, b...
research
03/01/2023

Building High-accuracy Multilingual ASR with Gated Language Experts and Curriculum Training

We propose gated language experts to improve multilingual transformer tr...
research
03/12/2021

A Distributed Optimisation Framework Combining Natural Gradient with Hessian-Free for Discriminative Sequence Training

This paper presents a novel natural gradient and Hessian-free (NGHF) opt...

Please sign up or login with your details

Forgot password? Click here to reset