Selection of Supplementary Acoustic Data for Meta-Learning in Under-Resourced Speech Recognition

I. Ting Hsieh, Chung Hsien Wu, Zhe Hong Zhao

研究成果: Conference contribution

1 引文 斯高帕斯(Scopus)

摘要

Automatic speech recognition (ASR) for under-resourced languages has been a challenging task during the past decade. In this paper, regarding Taiwanese as the under resourced language, the speech data of the high-resourced languages which have most phonemes in common with Taiwanese are selected as the supplementary resources for meta-training the acoustic models for Taiwanese ASR. Mandarin, English, Japanese, Cantonese and Thai as the high-resourced languages are selected as the supplementary languages based on the designed selection criteria. Model-agnostic meta-learning (MAML) is then used as the meta-training strategy. For evaluation, when 4000 utterances were selected from each supplementary language, we obtained the WER of 20.89% and the SER of 8.86% for Taiwanese ASR. The results were better than the baseline model (26.18% and 13.99%) using only the Taiwanese corpus and traditional method.

原文English
主出版物標題Proceedings of 2022 Asia-Pacific Signal and Information Processing Association Annual Summit and Conference, APSIPA ASC 2022
發行者Institute of Electrical and Electronics Engineers Inc.
頁面409-414
頁數6
ISBN(電子)9786165904773
DOIs
出版狀態Published - 2022
事件2022 Asia-Pacific Signal and Information Processing Association Annual Summit and Conference, APSIPA ASC 2022 - Chiang Mai, Thailand
持續時間: 2022 11月 72022 11月 10

出版系列

名字Proceedings of 2022 Asia-Pacific Signal and Information Processing Association Annual Summit and Conference, APSIPA ASC 2022

Conference

Conference2022 Asia-Pacific Signal and Information Processing Association Annual Summit and Conference, APSIPA ASC 2022
國家/地區Thailand
城市Chiang Mai
期間22-11-0722-11-10

All Science Journal Classification (ASJC) codes

  • 電腦網路與通信
  • 資訊系統
  • 訊號處理

指紋

深入研究「Selection of Supplementary Acoustic Data for Meta-Learning in Under-Resourced Speech Recognition」主題。共同形成了獨特的指紋。

引用此