Paper ID | SPE-L8.5 |
Paper Title |
F0-CONSISTENT MANY-TO-MANY NON-PARALLEL VOICE CONVERSION VIA CONDITIONAL AUTOENCODER |
Authors |
Kaizhi Qian, University of Illinois at Urbana-Champaign, United States; Zeyu Jin, Adobe, United States; Mark Hasegawa-Johnson, University of Illinois at Urbana-Champaign, United States; Gautham Mysore, Adobe, United States |
Session | SPE-L8: Speech Synthesis and Voice Conversion II |
Location | On-Demand |
Session Time: | Wednesday, 06 May, 11:30 - 13:30 |
Presentation Time: | Wednesday, 06 May, 12:50 - 13:10 |
Presentation |
Lecture
|
Topic |
Speech Processing: [SPE-SYNT] Speech Synthesis and Generation |
IEEE Xplore Open Preview |
Click here to view in IEEE Xplore |
Virtual Presentation |
Click here to watch in the Virtual Conference |