Exploiting Adapters for Cross-lingual Low-resource Speech Recognition

05/18/2021
by   Wenxin Hou, et al.
0

Cross-lingual speech adaptation aims to solve the problem of leveraging multiple rich-resource languages to build models for a low-resource target language. Since the low-resource language has limited training data, speech recognition models can easily overfit. In this paper, we propose to use adapters to investigate the performance of multiple adapters for parameter-efficient cross-lingual speech adaptation. Based on our previous MetaAdapter that implicitly leverages adapters, we propose a novel algorithms called SimAdapter for explicitly learning knowledge from adapters. Our algorithm leverages adapters which can be easily integrated into the Transformer structure.MetaAdapter leverages meta-learning to transfer the general knowledge from training data to the test language. SimAdapter aims to learn the similarities between the source and target languages during fine-tuning using the adapters. We conduct extensive experiments on five-low-resource languages in Common Voice dataset. Results demonstrate that our MetaAdapter and SimAdapter methods can reduce WER by 2.98 only 2.5 fine-tuning baseline. Moreover, we also show that these two novel algorithms can be integrated for better performance with up to 3.55 reduction.

READ FULL TEXT

page 1

page 9

research
11/02/2021

Cross-lingual Transfer for Speech Processing using Acoustic Language Similarity

Speech processing systems currently do not support the vast majority of ...
research
06/14/2023

Learning Cross-lingual Mappings for Data Augmentation to Improve Low-Resource Speech Recognition

Exploiting cross-lingual resources is an effective way to compensate for...
research
03/09/2022

Language Adaptive Cross-lingual Speech Representation Learning with Sparse Sharing Sub-networks

Unsupervised cross-lingual speech representation learning (XLSR) has rec...
research
05/31/2023

MetaXLR – Mixed Language Meta Representation Transformation for Low-resource Cross-lingual Learning based on Multi-Armed Bandit

Transfer learning for extremely low resource languages is a challenging ...
research
04/28/2020

Learning to Learn Morphological Inflection for Resource-Poor Languages

We propose to cast the task of morphological inflection - mapping a lemm...
research
04/21/2018

Massively Parallel Cross-Lingual Learning in Low-Resource Target Language Translation

We work on translation from rich-resource languages to low-resource lang...
research
11/12/2020

Using IPA-Based Tacotron for Data Efficient Cross-Lingual Speaker Adaptation and Pronunciation Enhancement

Recent neural Text-to-Speech (TTS) models have been shown to perform ver...

Please sign up or login with your details

Forgot password? Click here to reset