Xiaosu Su
Timeline
Legend:
Book In proceedings Article PhD thesis Dataset OtherLinks
On csauthors.net:
Bibliography
2025
GAID: Frame-Level Gated Audio-Visual Integration with Directional Perturbation for Text-Video Retrieval.
CoRR, August, 2025
DiffEmotionVC: A Dual-Granularity Disentangled Diffusion Framework for Any-to-Any Emotional Voice Conversion.
Proceedings of the 26th Annual Conference of the International Speech Communication Association, 2025