https://scholars.lib.ntu.edu.tw/handle/123456789/558974
Title: | Meta Learning for End-To-End Low-Resource Speech Recognition | Authors: | Hsu, J.-Y. Chen, Y.-J. HUNG-YI LEE |
Keywords: | IARPA-BABEL; language adaptation; low-resource; meta-learning; speech recognition | Issue Date: | 2020 | Journal Volume: | 2020-May | Start page/Pages: | 7844-7848 | Source: | ICASSP, IEEE International Conference on Acoustics, Speech and Signal Processing - Proceedings | Abstract: | In this paper, we proposed to apply meta learning approach for low-resource automatic speech recognition (ASR). We formulated ASR for different languages as different tasks, and meta-learned the initialization parameters from many pretraining languages to achieve fast adaptation on unseen target language, via recently proposed model-agnostic meta learning algorithm (MAML). We evaluated the proposed approach using six languages as pretraining tasks and four languages as target tasks. Preliminary results showed that the proposed method, MetaASR, significantly outperforms the state-of-the-art multitask pretraining approach on all target languages with different combinations of pretraining languages. In addition, since MAML's model-agnostic property, this paper also opens new research direction of applying meta learning to more speech-related applications. © 2020 IEEE. |
URI: | https://www.scopus.com/inward/record.url?eid=2-s2.0-85089208969&partnerID=40&md5=c3fcd2a227e6e220c84cc6de30f7ab61 https://scholars.lib.ntu.edu.tw/handle/123456789/558974 |
ISSN: | 15206149 | DOI: | 10.1109/ICASSP40776.2020.9053112 |
Appears in Collections: | 電機工程學系 |
Items in DSpace are protected by copyright, with all rights reserved, unless otherwise indicated.