Meta-Transfer Learning for Code-Switched Speech Recognition

04/29/2020
by   Genta Indra Winata, et al.
0

An increasing number of people in the world today speak a mixed-language as a result of being multilingual. However, building a speech recognition system for code-switching remains difficult due to the availability of limited resources and the expense and significant effort required to collect mixed-language data. We therefore propose a new learning method, meta-transfer learning, to transfer learn on a code-switched speech recognition system in a low-resource setting by judiciously extracting information from high-resource monolingual datasets. Our model learns to recognize individual languages, and transfer them so as to better recognize mixed-language speech by conditioning the optimization on the code-switching data. Based on experimental results, our model outperforms existing baselines on speech recognition and language modeling tasks, and is faster to converge.

READ FULL TEXT

page 1

page 2

page 3

page 4

research
04/01/2021

Multilingual and code-switching ASR challenges for low resource Indian languages

Recently, there is increasing interest in multilingual automatic speech ...
research
05/31/2023

Simple yet Effective Code-Switching Language Identification with Multitask Pre-Training and Transfer Learning

Code-switching, also called code-mixing, is the linguistics phenomenon w...
research
04/13/2021

Multilingual Transfer Learning for Code-Switched Language and Speech Neural Modeling

In this thesis, we address the data scarcity and limitations of linguist...
research
10/04/2018

Multilingual sequence-to-sequence speech recognition: architecture, transfer learning, and language modeling

Sequence-to-sequence (seq2seq) approach for low-resource ASR is a relati...
research
11/03/2020

Towards Code-switched Classification Exploiting Constituent Language Resources

Code-switching is a commonly observed communicative phenomenon denoting ...
research
03/05/2021

Transfer Learning based Speech Affect Recognition in Urdu

It has been established that Speech Affect Recognition for low resource ...
research
10/30/2015

Prediction-Adaptation-Correction Recurrent Neural Networks for Low-Resource Language Speech Recognition

In this paper, we investigate the use of prediction-adaptation-correctio...

Please sign up or login with your details

Forgot password? Click here to reset