Saved in:
Bibliographic Details
Main Authors: Yang, Chih-Kai, Huang, Kuan-Po, Lu, Ke-Han, Kuan, Chun-Yi, Hsiao, Chi-Yuan, Lee, Hung-yi
Format: Preprint
Published: 2023
Subjects:
Online Access:https://arxiv.org/abs/2401.00273
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1866911744443547648
author Yang, Chih-Kai
Huang, Kuan-Po
Lu, Ke-Han
Kuan, Chun-Yi
Hsiao, Chi-Yuan
Lee, Hung-yi
author_facet Yang, Chih-Kai
Huang, Kuan-Po
Lu, Ke-Han
Kuan, Chun-Yi
Hsiao, Chi-Yuan
Lee, Hung-yi
contents This work evaluated several cutting-edge large-scale foundation models based on self-supervision or weak supervision, including SeamlessM4T, SeamlessM4T v2, and Whisper-large-v3, on three code-switched corpora. We found that self-supervised models can achieve performances close to the supervised model, indicating the effectiveness of multilingual self-supervised pre-training. We also observed that these models still have room for improvement as they kept making similar mistakes and had unsatisfactory performances on modeling intra-sentential code-switching. In addition, the validity of several variants of Whisper was explored, and we concluded that they remained effective in a code-switching scenario, and similar techniques for self-supervised models are worth studying to boost the performance of code-switched tasks.
format Preprint
id arxiv_https___arxiv_org_abs_2401_00273
institution arXiv
publishDate 2023
record_format arxiv
spellingShingle Investigating Zero-Shot Generalizability on Mandarin-English Code-Switched ASR and Speech-to-text Translation of Recent Foundation Models with Self-Supervision and Weak Supervision
Yang, Chih-Kai
Huang, Kuan-Po
Lu, Ke-Han
Kuan, Chun-Yi
Hsiao, Chi-Yuan
Lee, Hung-yi
Audio and Speech Processing
Computation and Language
This work evaluated several cutting-edge large-scale foundation models based on self-supervision or weak supervision, including SeamlessM4T, SeamlessM4T v2, and Whisper-large-v3, on three code-switched corpora. We found that self-supervised models can achieve performances close to the supervised model, indicating the effectiveness of multilingual self-supervised pre-training. We also observed that these models still have room for improvement as they kept making similar mistakes and had unsatisfactory performances on modeling intra-sentential code-switching. In addition, the validity of several variants of Whisper was explored, and we concluded that they remained effective in a code-switching scenario, and similar techniques for self-supervised models are worth studying to boost the performance of code-switched tasks.
title Investigating Zero-Shot Generalizability on Mandarin-English Code-Switched ASR and Speech-to-text Translation of Recent Foundation Models with Self-Supervision and Weak Supervision
topic Audio and Speech Processing
Computation and Language
url https://arxiv.org/abs/2401.00273