Binaural rendering of microphone array captures based on source separation
详细信息 查看全文
- 作者：Joonas Nikunena ; 1 ; joonas.nikunen@tut.fi" class="auth_mail" title="E-mail the corresponding author ; Aleksandr Dimenta ; 1 ; aleksandr.diment@tut.fi" class="auth_mail" title="E-mail the corresponding author ; Tuomas Virtanena ; 1 ; tuomas.virtanen@tut.fi" class="auth_mail" title="E-mail the corresponding author ; Miikka Vilermob ; miikka.vilermo@nokia.com" class="auth_mail" title="E-mail the corresponding author
- 关键词：Binaural processing ; Source separation ; Speech intelligibility ; Non-negative matrix factorization
- 刊名：Speech Communication
- 出版年：2016
- 出版时间：February 2016
- 年：2016
- 卷：76
- 期：Complete
- 页码：157-169
- 全文大小：1829 K
文摘
- •
A method for binaural rendering of sound scene recordings is proposed.
- •
Source signals and their direction of arrival is estimated using a microphone array.
- •
A low-rank NMF model for separation of sound sources is used.
- •
Speech intelligibility test with overlapping speech is conducted.
- •
The speech intelligibility by binaural processing is shown to increase over stereo.