Semantic Visually-Guided Acoustic Highlighting with Large Vision-Language Models

Submitted to ICASSP 2026 (Sep 17, 2025).

Recommended citation: Junhua Huang, Chao Huang, Chenliang Xu. (2025). "Semantic Visually-Guided Acoustic Highlighting with Large Vision-Language Models." Submitted to ICASSP 2026.
Download Paper