Compositional model for speech denoising based on source/filter speech representation and smoothness/sparseness noise constraints
详细信息 查看全文
- 作者：P. Cabañ ; as-Molero ; pcabanas@ujaen.es" class="auth_mail" title="E-mail the corresponding author ; D. Martí ; nez-Muñ ; oz damian@ujaen.es" class="auth_mail" title="E-mail the corresponding author ; P. Vera-Candeas pvera@ujaen.es" class="auth_mail" title="E-mail the corresponding author ; F.J. Cañ ; adas-Quesada fcanadas@ujaen.es" class="auth_mail" title="E-mail the corresponding author ; N. Ruiz-Reyes nicolas@ujaen.es" class="auth_mail" title="E-mail the corresponding author
- 关键词：Audio source separation ; Speech separation ; Speech enhancement ; Non-negative matrix factorization ; Compositional models
- 刊名：Speech Communication
- 出版年：2016
- 出版时间：April 2016
- 年：2016
- 卷：78
- 期：Complete
- 页码：84-99
- 全文大小：1258 K
文摘
- •
Semi-supervised NMF with source/filter speech model and constrained noise parameters.
- •
Evaluated on the 3rd CHiME and SiSEC 2013 datasets for speech and noise separation.
- •
Proposed noise constraints help to improve the isolation of speech with real noises.
- •
All tested environments but one could be modeled by the constraints.
- •
Better separation results than conventional semi-supervised sparse NMF.