Technical Program

Paper Detail

Paper IDAUD-P2.12
Paper Title TIME-DOMAIN AUDIO SOURCE SEPARATION BASED ON WAVE-U-NET COMBINED WITH DISCRETE WAVELET TRANSFORM
Authors Tomohiko Nakamura, Hiroshi Saruwatari, University of Tokyo, Japan
SessionAUD-P2: Deep Learning for Speech and Audio
LocationOn-Demand
Session Time:Tuesday, 05 May, 11:30 - 13:30
Presentation Time:Tuesday, 05 May, 11:30 - 13:30
Presentation Poster
Topic Audio and Acoustic Signal Processing: [AUD-SEP] Audio and Speech Source Separation
IEEE Xplore Open Preview  Click here to view in IEEE Xplore
Virtual Presentation  Click here to watch in the Virtual Conference