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
Session:
Music Source Separation II: Methods and Architectures
Track:
Audio and Acoustic Signal Processing
Location:
Gather Area L
Presentation Time:
Mon, 9 May, 20:00 - 20:45 China Time (UTC +8)
Mon, 9 May, 12:00 - 12:45 UTC
Mon, 9 May, 12:00 - 12:45 UTC
Session Chair:
Kazuyoshi Yoshii, Kyoto University
Presentation
Discussion
Resources
No resources available.
Session AUD-8
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