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
Session SLP-L1
SLP-L1.1: DIFFUSION-BASED SPEECH ENHANCEMENT IN MATCHED AND MISMATCHED CONDITIONS USING A HEUN-BASED SAMPLER
Philippe Gonzalez, Technical University of Denmark, Denmark; Zheng-Hua Tan, Jan Østergaard, Jesper Jensen, Aalborg University, Denmark; Tommy Sonne Alstrøm, Tobias May, Technical University of Denmark, Denmark
SLP-L1.2: Unsupervised Speech Enhancement with Diffusion-based Generative Models
Berné Nortier, Mostafa Sadeghi, Romain Serizel, Inria, France
SLP-L1.3: BOOSTING SPEECH ENHANCEMENT WITH CLEAN SELF-SUPERVISED FEATURES VIA CONDITIONAL VARIATIONAL AUTOENCODERS
Yoonhyung Lee, Kyomin Jung, Seoul National University, Korea, Republic of
SLP-L1.4: Diffusion-based Speech Enhancement with a Weighted Generative-Supervised Learning Loss
Jean-Eudes Ayilo, Mostafa Sadeghi, Romain Serizel, Inria, France
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
SLP-L1.6: SEEING THROUGH THE CONVERSATION: AUDIO-VISUAL SPEECH SEPARATION BASED ON DIFFUSION MODEL
Suyeon Lee, Chaeyoung Jung, Youngjoon Jang, Jaehun Kim, Joon Son Chung, Korea Advanced Institute of Science and Technology, Korea, Republic of
Contacts