AUD-17.2
THE COCKTAIL FORK PROBLEM: THREE-STEM AUDIO SEPARATION FOR REAL-WORLD SOUNDTRACKS
Darius Petermann, Indiana University, United States of America; Gordon Wichern, Jonathan Le Roux, Mitsubishi Electric Research Laboratories (MERL), United States of America; Zhong-Qiu Wang, Carnegie Mellon University, United States of America
Session:
Speech Separation I
Track:
Audio and Acoustic Signal Processing
Location:
Gather Area K
Presentation Time:
Tue, 10 May, 22:00 - 22:45 China Time (UTC +8)
Tue, 10 May, 14:00 - 14:45 UTC
Tue, 10 May, 14:00 - 14:45 UTC
Session Chair:
Scott Wisdom, Google
Session AUD-17
AUD-17.1: EAD-CONFORMER: A CONFORMER-BASED ENCODER-ATTENTION-DECODER-NETWORK FOR MULTI-TASK AUDIO SOURCE SEPARATION
Chenxing Li, Yang Wang, Feng Deng, Zhuo Zhang, Xiaorui Wang, Zhongyuan Wang, Kuai Shou, China
AUD-17.2: THE COCKTAIL FORK PROBLEM: THREE-STEM AUDIO SEPARATION FOR REAL-WORLD SOUNDTRACKS
Darius Petermann, Indiana University, United States of America; Gordon Wichern, Jonathan Le Roux, Mitsubishi Electric Research Laboratories (MERL), United States of America; Zhong-Qiu Wang, Carnegie Mellon University, United States of America
AUD-17.3: PHASE SHIFTED BEDROSIAN FILTERBANK: AN INTERPRETABLE AUDIO FRONT-END FOR TIME-DOMAIN AUDIO SOURCE SEPARATION
Félix Mathieu, Gael Richard, Geoffroy Peeters, Telecom Paris, France; Thomas Courtat, Thales, France
AUD-17.4: HARMONICITY PLAYS A CRITICAL ROLE IN DNN BASED VERSUS IN BIOLOGICALLY-INSPIRED MONAURAL SPEECH SEGREGATION SYSTEMS
Rahil Parikh, Carol Espy-Wilson, Shihab Shamma, University of Maryland College Park, United States of America; Ilya Kavalerov, Google Inc., United States of America
AUD-17.5: MULTI-CHANNEL NARROW-BAND DEEP SPEECH SEPARATION WITH FULL-BAND PERMUTATION INVARIANT TRAINING
Changsheng Quan, Zhejiang University, China; Xiaofei Li, Westlake University, China
AUD-17.6: NEURAL FULL-RANK SPATIAL COVARIANCE ANALYSIS FOR BLIND SOURCE SEPARATION
Yoshiaki Bando, National Institute of Advanced Industrial Science and Technology / RIKEN, Japan; Kouhei Sekiguchi, Aditya Arie Nugraha, Mathieu Fontaine, RIKEN, Japan; Yoshiki Masuyama, National Institute of Advanced Industrial Science and Technology / Tokyo Metropolitan University, Japan; Kazuyoshi Yoshii, RIKEN / Kyoto University, Japan