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

arXiv: https://arxiv.org/abs/2609.18009 · HTML: https://mlsanity.com/paper/2609.18009/

## Key facts

- No citing papers in the map yet (data through 14 Oct 2026).
- Placed in Speech and audio SSMs, one of 10 directions in State-space sequence models (S4, Mamba).
- Builds on 27 of its 38 references that are in the map.
- First posted on arXiv 16 Sep 2026.

## Placed in

- State-space sequence models (S4, Mamba) / [Speech and audio SSMs](https://mlsanity.com/ssm/speech-and-audio-ssms/)

## Builds on (most cited first, 27 of 27)

- [Attention Is All You Need](https://mlsanity.com/paper/1706.03762/) (2017)
- [Transformers are RNNs: Fast Autoregressive Transformers with Linear Attention](https://mlsanity.com/paper/2006.16236/) (2020)
- [VoxCeleb2: Deep Speaker Recognition](https://mlsanity.com/paper/1806.05622/) (2018)
- [How Attentive are Graph Attention Networks?](https://mlsanity.com/paper/2105.14491/) (2021)
- [SDR - half-baked or well done?](https://mlsanity.com/paper/1811.02508/) (2018)
- [LRS3-TED: a large-scale dataset for visual speech recognition](https://mlsanity.com/paper/1809.00496/) (2018)
- [Supervised Speech Separation Based on Deep Learning: An Overview](https://mlsanity.com/paper/1708.07524/) (2017)
- [The INTERSPEECH 2020 Deep Noise Suppression Challenge: Datasets, Subjective Testing Framework, and Challenge Results](https://mlsanity.com/paper/2005.13981/) (2020)
- [Is Someone Speaking? Exploring Long-term Temporal Features for Audio-visual Active Speaker Detection](https://mlsanity.com/paper/2107.06592/) (2021)
- [The Conversation: Deep Audio-Visual Speech Enhancement](https://mlsanity.com/paper/1804.04121/) (2018)
- [Visual Speech Recognition for Multiple Languages in the Wild](https://mlsanity.com/paper/2202.13084/) (2022)
- [An Overview of Deep-Learning-Based Audio-Visual Speech Enhancement and Separation](https://mlsanity.com/paper/2008.09586/) (2020)
- [Robust Self-Supervised Audio-Visual Speech Recognition](https://mlsanity.com/paper/2201.01763/) (2022)
- [An Investigation of Incorporating Mamba for Speech Enhancement](https://mlsanity.com/paper/2405.06573/) (2024)
- [Mamba in Speech: Towards an Alternative to Self-Attention](https://mlsanity.com/paper/2405.12609/) (2024)
- [Audio-Visual Speech Enhancement Using Multimodal Deep Convolutional Neural Networks](https://mlsanity.com/paper/1709.00944/) (2017)
- [LoCoNet: Long-Short Context Network for Active Speaker Detection](https://mlsanity.com/paper/2301.08237/) (2023)
- [FlowAVSE: Efficient Audio-Visual Speech Enhancement with Conditional Flow Matching](https://mlsanity.com/paper/2406.09286/) (2024)
- [Audio-Visual Speech Enhancement with Score-Based Generative Models](https://mlsanity.com/paper/2306.01432/) (2023)
- [Mamba-SEUNet: Mamba UNet for Monaural Speech Enhancement](https://mlsanity.com/paper/2412.16626/) (2024)
- [LA-VocE: Low-SNR Audio-visual Speech Enhancement using Neural Vocoders](https://mlsanity.com/paper/2211.10999/) (2022)
- [Diffusion-based Unsupervised Audio-visual Speech Enhancement](https://mlsanity.com/paper/2410.05301/) (2024)
- [SAV-SE: Scene-aware Audio-Visual Speech Enhancement with Selective State Space Model](https://mlsanity.com/paper/2411.07751/) (2024)
- [AV2Wav: Diffusion-Based Re-synthesis from Continuous Self-supervised Features for Audio-Visual Speech Enhancement](https://mlsanity.com/paper/2309.08030/) (2023)
- [AlignVSR: Audio-Visual Cross-Modal Alignment for Visual Speech Recognition](https://mlsanity.com/paper/2410.16438/) (2024)
- [Real-Time Audio-Visual Speech Enhancement Using Pre-trained Visual Representations](https://mlsanity.com/paper/2507.21448/) (2025)
- [AUREXA-SE: Audio-Visual Unified Representation Exchange Architecture with Cross-Attention and Squeezeformer for Speech Enhancement](https://mlsanity.com/paper/2510.05295/) (2025)

## Abstract (arXiv)

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.