SELECTIVE MUTUAL LEARNING: AN EFFICIENT APPROACH FOR SINGLE CHANNEL SPEECH SEPARATION

Ha Minh Tan, Duc Quang Vu, Chung Ting Lee, Yung-Hui Li, Jia Ching Wang

研究成果: 書貢獻/報告類型會議論文篇章同行評審

7 引文 斯高帕斯(Scopus)

摘要

Mutual learning, the related idea to knowledge distillation, is a group of untrained lightweight networks, which simultaneously learn and share knowledge to perform tasks together during training. In this paper, we propose a novel mutual learning approach, namely selective mutual learning. This is the simple yet effective approach to boost the performance of the networks for speech separation. There are two networks in the selective mutual learning method, they are like a pair of friends learning and sharing knowledge with each other. Especially, the high-confidence predictions are used to guide the remaining network while the low-confidence predictions are ignored. This helps to remove poor predictions of the two networks during sharing knowledge. The experimental results have shown that our proposed selective mutual learning method significantly improves the separation performance compared to existing training strategies including independently training, knowledge distillation, and mutual learning with the same network architecture.

原文???core.languages.en_GB???
主出版物標題2022 IEEE International Conference on Acoustics, Speech, and Signal Processing, ICASSP 2022 - Proceedings
發行者Institute of Electrical and Electronics Engineers Inc.
頁面3678-3682
頁數5
ISBN(電子)9781665405409
DOIs
出版狀態已出版 - 2022
事件47th IEEE International Conference on Acoustics, Speech, and Signal Processing, ICASSP 2022 - Virtual, Online, Singapore
持續時間: 23 5月 202227 5月 2022

出版系列

名字ICASSP, IEEE International Conference on Acoustics, Speech and Signal Processing - Proceedings
2022-May
ISSN(列印)1520-6149

???event.eventtypes.event.conference???

???event.eventtypes.event.conference???47th IEEE International Conference on Acoustics, Speech, and Signal Processing, ICASSP 2022
國家/地區Singapore
城市Virtual, Online
期間23/05/2227/05/22

指紋

深入研究「SELECTIVE MUTUAL LEARNING: AN EFFICIENT APPROACH FOR SINGLE CHANNEL SPEECH SEPARATION」主題。共同形成了獨特的指紋。

引用此