Domain adversarial training for speech enhancement

The performance of deep learning approaches to speech enhancement degrades significantly in face of mismatch between training and testing. In this paper, we propose a domain adversarial training technique for unsupervised domain transfer, that 1) overcomes domain mismatch, and 2) provides a solution...

全面介紹

Saved in:
書目詳細資料
Main Authors: Hou, Nana, Xu, Chenglin, Chng, Eng Siong, Li, Haizhou
其他作者: School of Computer Science and Engineering
格式: Conference or Workshop Item
語言:English
出版: 2020
主題:
在線閱讀:https://hdl.handle.net/10356/144786
標簽: 添加標簽
沒有標簽, 成為第一個標記此記錄!