Takashi Shibuya
Scholar

Takashi Shibuya

Google Scholar ID: XCRO260AAAAJ
Sony
Generative AIMultimodal LearningAudio Signal Processing
Google Scholar↗
Citations & Impact
All-time
Citations
753
 
H-index
13
 
i10-index
15
 
Publications
20
 
Co-authors
3
list available
Contact
No contact links provided.
Publications
24 items
Echoes Over Time: Unlocking Length Generalization in Video-to-Audio Generation Models
2026
Cited
0
Schrodinger Audio-Visual Editor: Object-Level Audiovisual Removal
2025
Cited
0
AutoRefiner: Improving Autoregressive Video Diffusion Models via Reflective Refinement Over the Stochastic Sampling Path
2025
Cited
0
Coherent Audio-Visual Editing via Conditional Audio Generation Following Video Edits
2025
Cited
0
StereoSync: Spatially-Aware Stereo Audio Generation from Video
2025
Cited
0
SONA: Learning Conditional, Unconditional, and Mismatching-Aware Discriminator
2025
Cited
0
SoundReactor: Frame-level Online Video-to-Audio Generation
2025
Cited
0
TITAN-Guide: Taming Inference-Time AligNment for Guided Text-to-Video Diffusion Models
2025
Cited
0
Resume (English only)
Co-authors
3 total
Yuki Mitsufuji
Yuki Mitsufuji
Distinguished Engineer, Sony
Tatsuya Harada
Tatsuya Harada
The University of Tokyo
Eduard Hovy
Eduard Hovy
University of Melbourne, CMU