Xiaosu Su

According to our database, Xiaosu Su authored at least 3 papers between 2025 and 2026.

Collaborative distances:

• Dijkstra number of five.
• Erdős number of five.

2026

CapTalk: Unified Voice Design for Single-Utterance and Dialogue Speech Generation.

Xiaosu Su, Zihan Sun, Peilei Jia, Jun Gao

CoRR, April, 2026

2025

GAID: Frame-Level Gated Audio-Visual Integration with Directional Perturbation for Text-Video Retrieval.

Bowen Yang, Yun Cao, Chen He, Xiaosu Su

CoRR, August, 2025

DiffEmotionVC: A Dual-Granularity Disentangled Diffusion Framework for Any-to-Any Emotional Voice Conversion.

Xiaosu Su, Bowen Yang, Xiaowei Yi, Yun Cao

Proceedings of the 26th Annual Conference of the International Speech Communication Association, 2025