FoleyMaster: High-Quality Video-to-Audio Synthesis via MLLM-Augmented Prompt Tuning and Joint Semantic-Temporal Adaptation.

Liming Liang, Luo Chen, Yuehan Jin, Xianwei Zhuang, Yuxin Xie, Yongkang Yin, Yuexian Zou

Browse the full Interspeech paper archive.