SG-Mamba: Sparse Graph-Guided Mamba for Audio-Visual Speech Enhancement

arXiv:2609.18009 · eess.AS, cs.CL, cs.SD · Submitted 2026-09-16 · Read on arXiv

eess.AS, cs.CL, cs.SD

Submitted: 2026-09-16

Updated: 2026-09-18

Comments: Accepted to IEEE SLT 2026

Code: https://github.com/0u5gary/SG-Mamba

License: http://creativecommons.org/licenses/by/4.0/

The gist: Lightweight audio-visual speech enhancement (AVSE) models face a critical trade-off between computational efficiency and cross-modal alignment accuracy.

Terminology

Abstract

Lightweight audio-visual speech enhancement (AVSE) models face a critical trade-off between computational efficiency and cross-modal alignment accuracy. While simple concatenation lacks relational expressiveness, dense cross-attention incurs computational overhead and is prone to unreliable cross-modal correspondence under strong acoustic interference. We propose Sparse Graph-Guided Mamba (SG-Mamba), a lightweight AVSE framework that integrates a sparse heterogeneous graph with a linear-complexity Mamba backbone. The graph explicitly models modality-specific relations through content-adaptive attention and cross-frame audio-visual connections, while Mamba captures long-range temporal context. We further introduce an audio skip connection to preserve spectral detail without sacrificing noise suppression. Evaluated on LRS3, SG-Mamba achieves competitive or superior performance against strong lightweight baselines and reaches 13.091 dB SI-SDR under noise-only condition. It also remains robust in cluttered multi-speaker conditions with a competitive cost of 3.45 G MACs (or 6.90 G FLOPs). Results on VoxCeleb2 further suggest that explicit structural priors improve robustness, generalizability, and computational efficiency in lightweight AVSE.

Sources

Related papers