IEEE ICASSP 2022

2022 IEEE International Conference on Acoustics, Speech and Signal Processing

7-13 May 2022
  • Virtual (all paper presentations)
22-27 May 2022
  • Main Venue: Marina Bay Sands Expo & Convention Center, Singapore
27-28 October 2022
  • Satellite Venue: Crowne Plaza Shenzhen Longgang City Centre, Shenzhen, China

ICASSP 2022
AUD-8: Music Source Separation II: Methods and Architectures
Mon, 9 May, 20:00 - 20:45 China Time (UTC +8)
Mon, 9 May, 12:00 - 12:45 UTC
Location: Gather Area L
Session Chair: Kazuyoshi Yoshii, Kyoto University
Track: Audio and Acoustic Signal Processing

AUD-8.1: IMPROVING SOURCE SEPARATION BY EXPLICITLY MODELING DEPENDENCIES BETWEEN SOURCES
Ethan Manilow, Bryan Pardo, Northwestern University, United States of America; Curtis Hawthorne, Cheng-Zhi Anna Huang, Jesse Engel, Google, United States of America

AUD-8.2: MUSIC SOURCE SEPARATION WITH DEEP EQUILIBRIUM MODELS
Yuichiro Koyama, Naoki Murata, Shusuke Takahashi, Yuki Mitsufuji, Sony Group Corporation, Japan; Stefan Uhlich, Giorgio Fabbro, Sony Europe B.V., Germany

AUD-8.3: TIME-DOMAIN AUDIO SOURCE SEPARATION WITH NEURAL NETWORKS BASED ON MULTIRESOLUTION ANALYSIS
Tomohiko Nakamura, Shihori Kozuka, Hiroshi Saruwatari, University of Tokyo, Japan

AUD-8.4: HARMONIC AND PERCUSSIVE SOUND SEPARATION BASED ON MIXED PARTIAL DERIVATIVE OF PHASE SPECTROGRAM
Natsuki Akaishi, Kohei Yatabe, Yasuhiro Oikawa, Waseda University, Japan

AUD-8.5: ON LOSS FUNCTIONS AND EVALUATION METRICS FOR MUSIC SOURCE SEPARATION
Enric Gusó, Universitat Pompeu Fabra, Spain; Jordi Pons, Santiago Pascual, Joan Serrà, Dolby Laboratories, Spain

AUD-8.6: FifthNet: Structured Compact Neural Networks for Automatic Chord Recognition
Ken O'Hanlon, Mark Sandler, Queen Mary University of London, United Kingdom of Great Britain and Northern Ireland