https://scholars.lib.ntu.edu.tw/handle/123456789/607149
標題: | Stabilizing label assignment for speech separation by self-supervised pre-training | 作者: | Huang S.-F Chuang S.-P Liu D.-R Chen Y.-C Yang G.-P HUNG-YI LEE |
關鍵字: | Label Permutation Switch;Self-supervised Pre-train;Speech Enhancement;Speech Separation;Separation;Source separation;Speech analysis;Speech communication;Achievable performance;Convergence speed;Label permutation switch;Pre-training;Self-supervised pre-train;Separation model;Speech separation;Speed performance;Speech enhancement | 公開日期: | 2021 | 卷: | 3 | 起(迄)頁: | 2303-2307 | 來源出版物: | Proceedings of the Annual Conference of the International Speech Communication Association, INTERSPEECH | 摘要: | Speech separation has been well developed, with the very successful permutation invariant training (PIT) approach, although the frequent label assignment switching happening during PIT training remains to be a problem when better convergence speed and achievable performance are desired. In this paper, we propose to perform self-supervised pre-training to stabilize the label assignment in training the speech separation model. Experiments over several types of self-supervised approaches, several typical speech separation models and two different datasets showed that very good improvements are achievable if a proper self-supervised approach is chosen. Copyright ? 2021 ISCA. |
URI: | https://www.scopus.com/inward/record.uri?eid=2-s2.0-85119205277&doi=10.21437%2fInterspeech.2021-763&partnerID=40&md5=ec4477ece29732cedbc0c143ad1eb2da https://scholars.lib.ntu.edu.tw/handle/123456789/607149 |
ISSN: | 2308457X | DOI: | 10.21437/Interspeech.2021-763 |
顯示於: | 電機工程學系 |
在 IR 系統中的文件,除了特別指名其著作權條款之外,均受到著作權保護,並且保留所有的權利。