AASP-L5.4

BOOSTING UNKNOWN-NUMBER SPEAKER SEPARATION WITH TRANSFORMER DECODER-BASED ATTRACTOR

Younglo Lee, Shukjae Choi, Byeong-Yeol Kim, 42dot Inc., Korea, Republic of; Zhong-Qiu Wang, Shinji Watanabe, Carnegie Mellon University, United States of America

Session:
AASP-L5: Audio and Speech Source Separation Lecture

Track:
Audio and Acoustic Signal Processing

Location:
Room 101

Presentation Time:
Wed, 17 Apr, 14:10 - 14:30 (UTC +9)

Session Co-Chairs:
Scott Wisdom, Google and Reinhold Haeb-umbach, Paderborn University
View Manuscript
Presentation
Discussion
Resources
Contacts