DNN-Based Linear Prediction Residual Enhancement for Speech Dereverberation

Xinyang Feng*, Nuo Li, Zunwen He, Yan Zhang, Wancheng Zhang

*此作品的通讯作者

科研成果: 书/报告/会议事项章节会议稿件同行评审

3 引用 (Scopus)

摘要

In daily-life scenarios, reverberation inevitably caus-es a decrease in speech recognizability and speech quality. Exploring methods to eliminate reverberation will benefit both human perception and other speech technology applications such as identity authentication and speech recognition. This paper proposes a speech dereverberation algorithm based on linear prediction (LP) residual processing using deep neural network (DNN). The amplitude spectrum of the LP residual of short-term speech is used as a speech feature to train the DNN, and the mapping relationship between LP residual of the reverberant speech and that of the clean speech is learned. Comparative ex-periments under different reverberation conditions have verified the effectiveness and robustness of the algorithm.

源语言英语
主期刊名2021 Asia-Pacific Signal and Information Processing Association Annual Summit and Conference, APSIPA ASC 2021 - Proceedings
出版商Institute of Electrical and Electronics Engineers Inc.
541-545
页数5
ISBN(电子版)9789881476890
出版状态已出版 - 2021
活动2021 Asia-Pacific Signal and Information Processing Association Annual Summit and Conference, APSIPA ASC 2021 - Tokyo, 日本
期限: 14 12月 202117 12月 2021

出版系列

姓名2021 Asia-Pacific Signal and Information Processing Association Annual Summit and Conference, APSIPA ASC 2021 - Proceedings

会议

会议2021 Asia-Pacific Signal and Information Processing Association Annual Summit and Conference, APSIPA ASC 2021
国家/地区日本
Tokyo
时期14/12/2117/12/21

指纹

探究 'DNN-Based Linear Prediction Residual Enhancement for Speech Dereverberation' 的科研主题。它们共同构成独一无二的指纹。

引用此