# Leveraging Mamba with Full-Face Vision for Audio-Visual Speech Enhancement Source: [Leveraging Mamba with Full-Face Vision for Audio-Visual Speech Enhancement]() Collection index: [llms.txt]() Data updated: 2025-10-26T05:48:24.291Z Authors: Rong Chao, Wenze Ren, You-Jin Li, Kuo-Hsuan Hung, Sung-Feng Huang, Szu-Wei Fu, Wen-Huang Cheng, Yu Tsao Published: 2025-08-19T08:34:57.000Z ## Abstract Recent Mamba-based models have shown promise in speech enhancement by efficiently modeling long-range temporal dependencies. However, models like Speech Enhancement Mamba (SEMamba) remain limited to single-speaker scenarios and struggle in complex multi-speaker environments such as the cocktail party problem. To overcome this, we introduce AVSEMamba, an audio-visual speech enhancement model that integrates full-face visual cues with a Mamba-based temporal backbone. By leveraging spatiotemporal visual information, AVSEMamba enables more accurate extraction of target speech in challenging conditions. Evaluated on the AVSEC-4 Challenge development and blind test sets, AVSEMamba outperforms other monaural baselines in speech intelligibility (STOI), perceptual quality (PESQ), and non-intrusive quality (UTMOS), and achieves \\textbf{1st place} on the monaural leaderboard. ## Recorded benchmark results A research result applies to its stated dataset, split, metric and evaluation configuration. Compare like-for-like settings, preserve the metric's unit and direction, and distinguish paper-reported results from independent reproduction. The best result recorded here is not a claim of exhaustive, current global coverage. - [Speech Enhancement on AVSEC-2](): Speech Enhancement; AVSEC-2; PESQ: 2.178. - [Speech Enhancement on AVSEC-2 200 (test)](): Speech Enhancement; AVSEC-2 200 (test); PESQ: 2.37. - [Speech Enhancement on AVSEC2-Gaze](): Speech Enhancement; AVSEC2-Gaze; PESQ: 1.488. ## Original sources and implementation [Original paper]() [PDF]()