Saved in:
Bibliographic Details
Main Authors: Wang, Shih-Heng, Chen, Zih-Ching, Shi, Jiatong, Chuang, Ming-To, Lin, Guan-Ting, Huang, Kuan-Po, Harwath, David, Li, Shang-Wen, Lee, Hung-yi
Format: Preprint
Published: 2024
Subjects:
Online Access:https://arxiv.org/abs/2411.18217
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1866913635905830912
author Wang, Shih-Heng
Chen, Zih-Ching
Shi, Jiatong
Chuang, Ming-To
Lin, Guan-Ting
Huang, Kuan-Po
Harwath, David
Li, Shang-Wen
Lee, Hung-yi
author_facet Wang, Shih-Heng
Chen, Zih-Ching
Shi, Jiatong
Chuang, Ming-To
Lin, Guan-Ting
Huang, Kuan-Po
Harwath, David
Li, Shang-Wen
Lee, Hung-yi
contents The utilization of speech Self-Supervised Learning (SSL) models achieves impressive performance on Automatic Speech Recognition (ASR). However, in low-resource language ASR, they encounter the domain mismatch problem between pre-trained and low-resource languages. Typical solutions like fine-tuning the SSL model suffer from high computation costs while using frozen SSL models as feature extractors comes with poor performance. To handle these issues, we extend a conventional efficient fine-tuning scheme based on the adapter. We add an extra intermediate adaptation to warm up the adapter and downstream model initialization. Remarkably, we update only 1-5% of the total model parameters to achieve the adaptation. Experimental results on the ML-SUPERB dataset show that our solution outperforms conventional efficient fine-tuning. It achieves up to a 28% relative improvement in the Character/Phoneme error rate when adapting to unseen languages.
format Preprint
id arxiv_https___arxiv_org_abs_2411_18217
institution arXiv
publishDate 2024
record_format arxiv
spellingShingle How to Learn a New Language? An Efficient Solution for Self-Supervised Learning Models Unseen Languages Adaption in Low-Resource Scenario
Wang, Shih-Heng
Chen, Zih-Ching
Shi, Jiatong
Chuang, Ming-To
Lin, Guan-Ting
Huang, Kuan-Po
Harwath, David
Li, Shang-Wen
Lee, Hung-yi
Sound
Computation and Language
Audio and Speech Processing
The utilization of speech Self-Supervised Learning (SSL) models achieves impressive performance on Automatic Speech Recognition (ASR). However, in low-resource language ASR, they encounter the domain mismatch problem between pre-trained and low-resource languages. Typical solutions like fine-tuning the SSL model suffer from high computation costs while using frozen SSL models as feature extractors comes with poor performance. To handle these issues, we extend a conventional efficient fine-tuning scheme based on the adapter. We add an extra intermediate adaptation to warm up the adapter and downstream model initialization. Remarkably, we update only 1-5% of the total model parameters to achieve the adaptation. Experimental results on the ML-SUPERB dataset show that our solution outperforms conventional efficient fine-tuning. It achieves up to a 28% relative improvement in the Character/Phoneme error rate when adapting to unseen languages.
title How to Learn a New Language? An Efficient Solution for Self-Supervised Learning Models Unseen Languages Adaption in Low-Resource Scenario
topic Sound
Computation and Language
Audio and Speech Processing
url https://arxiv.org/abs/2411.18217