SSHR: Leveraging Self-supervised Hierarchical Representations for Multilingual Automatic Speech Recognition

Fuente: arXiv
Saved in:
Bibliographic Details
Main Authors: Xue, Hongfei, Shao, Qijie, Huang, Kaixun, Chen, Peikun, Liu, Jie, Xie, Lei
Format: Preprint
Published: 2023
Subjects:
Online Access:
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1866929329178411008
author Xue, Hongfei
Shao, Qijie
Huang, Kaixun
Chen, Peikun
Liu, Jie
Xie, Lei
author_facet Xue, Hongfei
Shao, Qijie
Huang, Kaixun
Chen, Peikun
Liu, Jie
Xie, Lei
contents Multilingual automatic speech recognition (ASR) systems have garnered attention for their potential to extend language coverage globally. While self-supervised learning (SSL) models, like MMS, have demonstrated their effectiveness in multilingual ASR, it is worth noting that various layers' representations potentially contain distinct information that has not been fully leveraged. In this study, we propose a novel method that leverages self-supervised hierarchical representations (SSHR) to fine-tune the MMS model. We first analyze the different layers of MMS and show that the middle layers capture language-related information, and the high layers encode content-related information, which gradually decreases in the final layers. Then, we extract a language-related frame from correlated middle layers and guide specific language extraction through self-attention mechanisms. Additionally, we steer the model toward acquiring more content-related information in the final layers using our proposed Cross-CTC. We evaluate SSHR on two multilingual datasets, Common Voice and ML-SUPERB, and the experimental results demonstrate that our method achieves state-of-the-art performance.
format Preprint
id arxiv_https___arxiv_org_abs_2309_16937
institution arXiv
publishDate 2023
record_format arxiv
spellingShingle SSHR: Leveraging Self-supervised Hierarchical Representations for Multilingual Automatic Speech Recognition
Xue, Hongfei
Shao, Qijie
Huang, Kaixun
Chen, Peikun
Liu, Jie
Xie, Lei
Computation and Language
Sound
Audio and Speech Processing
Multilingual automatic speech recognition (ASR) systems have garnered attention for their potential to extend language coverage globally. While self-supervised learning (SSL) models, like MMS, have demonstrated their effectiveness in multilingual ASR, it is worth noting that various layers' representations potentially contain distinct information that has not been fully leveraged. In this study, we propose a novel method that leverages self-supervised hierarchical representations (SSHR) to fine-tune the MMS model. We first analyze the different layers of MMS and show that the middle layers capture language-related information, and the high layers encode content-related information, which gradually decreases in the final layers. Then, we extract a language-related frame from correlated middle layers and guide specific language extraction through self-attention mechanisms. Additionally, we steer the model toward acquiring more content-related information in the final layers using our proposed Cross-CTC. We evaluate SSHR on two multilingual datasets, Common Voice and ML-SUPERB, and the experimental results demonstrate that our method achieves state-of-the-art performance.
title SSHR: Leveraging Self-supervised Hierarchical Representations for Multilingual Automatic Speech Recognition
topic Computation and Language
Sound
Audio and Speech Processing
url https://arxiv.org/abs/2309.16937