SLP-L1.5

AV2WAV: DIFFUSION-BASED RE-SYNTHESIS FROM CONTINUOUS SELF-SUPERVISED FEATURES FOR AUDIO-VISUAL SPEECH ENHANCEMENT

Ju-Chieh Chou, Chung-Ming Chien, Karen Livescu, Toyota Technological Institute at Chicago, United States of America

Session:
SLP-L1: Speech enhancement and separation - Diffusion and other probabilistic models Lecture

Track:
Speech and Language Processing

Location:
Room 104

Presentation Time:
Tue, 16 Apr, 14:30 - 14:50 (UTC +9)

Session Co-Chairs:
Timo Gerkmann, Universität Hamburg and Tomohiro Nakatani, NTT Corporation
View Manuscript
Presentation
Discussion
Resources
Contacts