AASP-L3.4
MTDIFFUSION: MULTI-TASK DIFFUSION MODEL WITH DUAL-UNET FOR FOLEY SOUND GENERATION
Anbin Qi, Xiang Xie, Jing Wang, Beijing Institute of Technology, China
Session:
AASP-L3: Environmental Sound Synthesis and Generation Lecture
Track:
Audio and Acoustic Signal Processing
Location:
Room E2
Presentation Time:
Tue, 16 Apr, 17:30 - 17:50 (UTC +9)
Session Co-Chairs:
Francois Germain, Mitsubishi Electric Research Laboratories and Prem Seetharaman, Adobe Research
Session AASP-L3
AASP-L3.1: Environmental sound synthesis from vocal imitations and sound event labels
Yuki Okamoto, Ritsumeikan University, Japan; Keisuke Imoto, Doshisha University, Japan; Shinnosuke Takamichi, The University of Tokyo, Japan; Ryotaro Nagase, Takahiro Fukumori, Yoichi Yamashita, Ritsumeikan University, Japan
AASP-L3.2: RETRIEVAL-AUGMENTED TEXT-TO-AUDIO GENERATION
Yi Yuan, Haohe Liu, Xubo Liu, Qiushi Huang, Mark D. Plumbley, Wenwu Wang, University of Surrey, United Kingdom of Great Britain and Northern Ireland
AASP-L3.3: SOUNDLOCD: AN EFFICIENT CONDITIONAL DISCRETE CONTRASTIVE LATENT DIFFUSION MODEL FOR TEXT-TO-SOUND GENERATION
Xinlei Niu, Jing Zhang, Australian National University, Australia; Christian Walder, Google DeepMind, Canada; Charles Patrick Martin, Australian National University, Australia
AASP-L3.4: MTDIFFUSION: MULTI-TASK DIFFUSION MODEL WITH DUAL-UNET FOR FOLEY SOUND GENERATION
Anbin Qi, Xiang Xie, Jing Wang, Beijing Institute of Technology, China
AASP-L3.5: GENERATION OR REPLICATION: AUSCULTATING AUDIO LATENT DIFFUSION MODELS
Dimitrios Bralios, University of Illinois Urbana-Champaign, United States of America; Gordon Wichern, François Germain, Zexu Pan, Sameer Khurana, Chiori Hori, Jonathan Le Roux, Mitsubishi Electric Research Laboratories (MERL), United States of America
AASP-L3.6: ADAPTING FRECHET AUDIO DISTANCE FOR GENERATIVE MUSIC EVALUATION
Azalea (Yijie) Gui, University of Toronto, Canada; Hannes Gamper, Sebastian Braun, Dimitra Emmanouilidou, Microsoft, United States of America
Contacts