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
Session AASP-L5
AASP-L5.1: REAL-TIME LOW-LATENCY MUSIC SOURCE SEPARATION USING HYBRID SPECTROGRAM-TASNET
Satvik Venkatesh, Arthur Benilov, Philip Coleman, Frederic Roskam, L-Acoustics, United Kingdom of Great Britain and Northern Ireland
AASP-L5.2: MUSIC SOURCE SEPARATION WITH BAND-SPLIT ROPE TRANSFORMER
Wei-Tsung Lu, Ju-Chiang Wang, Qiuqiang Kong, Yun-Ning Hung, ByteDance, United States of America
AASP-L5.3: LEVERAGING SOUND LOCALIZATION TO IMPROVE CONTINUOUS SPEAKER SEPARATION
Hassan Taherian, Ohio State University, United States of America; Ashutosh Pandey, Daniel Wong, Buye Xu, Meta, United States of America; DeLiang Wang, Ohio State University, United States of America
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
AASP-L5.5: GASS: GENERALIZING AUDIO SOURCE SEPARATION WITH LARGE-SCALE DATA
Jordi Pons, Xiaoyu Liu, Santiago Pascual, Joan Serrà, Dolby Laboratories, Spain
AASP-L5.6: Audio prompt tuning for universal sound separation
Yuzhuo Liu, ByteDance Inc, China; Xubo Liu, University of Surrey, United Kingdom of Great Britain and Northern Ireland; Yan Zhao, ByteDance Inc, United States of America; Yuanyuan Wang, Tsinghua University, China; Rui Xia, Pingchuan Tain, Yuxuan Wang, ByteDance Inc, United States of America
Contacts