AI RESEARCH

Efficient Audio-Visual Speech Separation with Discrete Lip Semantics and Multi-Scale Global-Local Attention

arXiv CS.CV

ArXi:2509.23610v2 Announce Type: replace-cross Audio-visual speech separation (AVSS) methods leverage visual cues to extract target speech and have nstrated strong separation quality in noisy acoustic environments. However, these methods usually involve a large number of parameters and require high computational cost, which is unacceptable in many applications where speech separation serves as only a preprocessing step for further speech processing. To address this issue, we propose an efficient AVSS method, named Dolphin.