AUD-1.4
Don't Separate, Learn to Remix: End-to-End Neural Remixing with Joint Optimization
Haici Yang, Shivani Firodiya, Minje Kim, Indiana University, United States of America; Nicholas Bryan, Adobe Research, United States of America
Session:
Music Source Separation I: Interactive, Conditioned, and Informed Models
Track:
Audio and Acoustic Signal Processing
Location:
Gather Area L
Presentation Time:
Sun, 8 May, 20:00 - 20:45 China Time (UTC +8)
Sun, 8 May, 12:00 - 12:45 UTC
Sun, 8 May, 12:00 - 12:45 UTC
Session Chair:
Yanfeng Lu, Institute for Infocomm Research, A*STAR
Session AUD-1
AUD-1.1: SPAIN-NET: SPATIALLY-INFORMED STEREOPHONIC MUSIC SOURCE SEPARATION
Darius Petermann, Minje Kim, Indiana University, United States of America
AUD-1.2: PHONEME LEVEL LYRICS ALIGNMENT AND TEXT-INFORMED SINGING VOICE SEPARATION
Kilian Schulze-Forster, Gaël Richard, Roland Badeau, Telecom Paris, Institut polytechnique de Paris, France; Clément Doire, Sonos, France
AUD-1.3: IMPROVED SINGING VOICE SEPARATION WITH CHROMAGRAM-BASED PITCH-AWARE REMIXING
Siyuan Yuan, Stanford University, United States of America; Zhepei Wang, UIUC, United States of America; Umut Isik, Ritwik Giri, Jean-Marc Valin, Michael M. Goodwin, Arvindh Krishnaswamy, Amazon Web Services, United States of America
AUD-1.4: Don't Separate, Learn to Remix: End-to-End Neural Remixing with Joint Optimization
Haici Yang, Shivani Firodiya, Minje Kim, Indiana University, United States of America; Nicholas Bryan, Adobe Research, United States of America
AUD-1.5: FEW-SHOT MUSICAL SOURCE SEPARATION
Yu Wang, Juan Pablo Bello, New York University, United States of America; Daniel Stoller, Rachel M. Bittner, Spotify, United States of America
AUD-1.6: SOURCE SEPARATION BY STEERING PRETRAINED MUSIC MODELS
Ethan Manilow, Patrick O'Reilly, Bryan Pardo, Northwestern University, United States of America; Prem Seetharaman, Descript, Inc., United States of America