# MambAttention: Mamba with Multi-Head Attention for Generalizable Single-Channel Speech Enhancement arXiv: https://arxiv.org/abs/2507.00966 ยท HTML: https://mlsanity.com/paper/2507.00966/ ## Key facts - Cited by 2 papers in the map (data through 14 Oct 2026). - Placed in Speech and audio SSMs, one of 10 directions in State-space sequence models (S4, Mamba). - Builds on 63 of its 96 references that are in the map. - First posted on arXiv 1 Jul 2025. ## 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, 30 of 63) - [Attention Is All You Need](https://mlsanity.com/paper/1706.03762/) (2017) - [Mamba: Linear-Time Sequence Modeling with Selective State Spaces](https://mlsanity.com/paper/2312.00752/) (2023) - [FlashAttention: Fast and Memory-Efficient Exact Attention with IO-Awareness](https://mlsanity.com/paper/2205.14135/) (2022) - [Delving Deep into Rectifiers: Surpassing Human-Level Performance on ImageNet Classification](https://mlsanity.com/paper/1502.01852/) (2015) - [FlashAttention-2: Faster Attention with Better Parallelism and Work Partitioning](https://mlsanity.com/paper/2307.08691/) (2023) - [Efficiently Modeling Long Sequences with Structured State Spaces](https://mlsanity.com/paper/2111.00396/) (2021) - [Conformer: Convolution-augmented Transformer for Speech Recognition](https://mlsanity.com/paper/2005.08100/) (2020) - [Vision Mamba: Efficient Visual Representation Learning with Bidirectional State Space Model](https://mlsanity.com/paper/2401.09417/) (2024) - [AST: Audio Spectrogram Transformer](https://mlsanity.com/paper/2104.01778/) (2021) - [FlashAttention-3: Fast and Accurate Attention with Asynchrony and Low-precision](https://mlsanity.com/paper/2407.08608/) (2024) - [SDR - half-baked or well done?](https://mlsanity.com/paper/1811.02508/) (2018) - [xLSTM: Extended Long Short-Term Memory](https://mlsanity.com/paper/2405.04517/) (2024) - [Speech Enhancement and Dereverberation with Diffusion-based Generative Models](https://mlsanity.com/paper/2208.05830/) (2022) - [Samba: Simple Hybrid State Space Models for Efficient Unlimited Context Language Modeling](https://mlsanity.com/paper/2406.07522/) (2024) - [DNSMOS P.835: A Non-Intrusive Perceptual Objective Speech Quality Metric to Evaluate Noise Suppressors](https://mlsanity.com/paper/2110.01763/) (2021) - [SEGAN: Speech Enhancement Generative Adversarial Network](https://mlsanity.com/paper/1703.09452/) (2017) - [WHAM!: Extending Speech Separation to Noisy Environments](https://mlsanity.com/paper/1907.01160/) (2019) - [The INTERSPEECH 2020 Deep Noise Suppression Challenge: Datasets, Subjective Testing Framework, and Challenge Results](https://mlsanity.com/paper/2005.13981/) (2020) - [Conditional Diffusion Probabilistic Model for Speech Enhancement](https://mlsanity.com/paper/2202.05256/) (2022) - [MetricGAN+: An Improved Version of MetricGAN for Speech Enhancement](https://mlsanity.com/paper/2104.03538/) (2021) - [StoRM: A Diffusion-based Stochastic Regeneration Model for Speech Enhancement and Dereverberation](https://mlsanity.com/paper/2212.11851/) (2022) - [MetricGAN: Generative Adversarial Networks based Black-box Metric Scores Optimization for Speech Enhancement](https://mlsanity.com/paper/1905.04874/) (2019) - [Speech Enhancement with Score-Based Generative Models in the Complex STFT Domain](https://mlsanity.com/paper/2203.17004/) (2022) - [Demystify Mamba in Vision: A Linear Attention Perspective](https://mlsanity.com/paper/2405.16605/) (2024) - [FullSubNet: A Full-Band and Sub-Band Fusion Model for Real-Time Single-Channel Speech Enhancement](https://mlsanity.com/paper/2010.15508/) (2020) - [EARS: An Anechoic Fullband Speech Dataset Benchmarked for Speech Enhancement and Dereverberation](https://mlsanity.com/paper/2406.06185/) (2024) - [An Investigation of Incorporating Mamba for Speech Enhancement](https://mlsanity.com/paper/2405.06573/) (2024) - [MP-SENet: A Speech Enhancement Model with Parallel Denoising of Magnitude and Phase Spectra](https://mlsanity.com/paper/2305.13686/) (2023) - [Vision-LSTM: xLSTM as Generic Vision Backbone](https://mlsanity.com/paper/2406.04303/) (2024) - [SELM: Speech Enhancement Using Discrete Tokens and Language Models](https://mlsanity.com/paper/2312.09747/) (2023) ## Built on by (most cited first, 2 of 2) - [Real-Time Streamable Generative Speech Restoration with Flow Matching](https://mlsanity.com/paper/2512.19442/) (2025) - [An overview of neural architectures for self-supervised audio representation learning from masked spectrograms](https://mlsanity.com/paper/2509.18691/) (2025) ## Abstract (arXiv) With new sequence models like Mamba and xLSTM, several studies have shown that these models match or outperform the state-of-the-art in single-channel speech enhancement and audio representation learning. However, prior research has demonstrated that sequence models like LSTM and Mamba tend to overfit to the training set. To address this, previous works have shown that adding self-attention to LSTMs substantially improves generalization performance for single-channel speech enhancement. Nevertheless, neither the concept of hybrid Mamba and time-frequency attention models nor their generalization performance have been explored for speech enhancement. In this paper, we propose a novel hybrid architecture, MambAttention, which combines Mamba and shared time- and frequency-multi-head attention modules for generalizable single-channel speech enhancement. To train our model, we introduce VB-DemandEx, a dataset inspired by VoiceBank+Demand but with more challenging noise types and lower signal-to-noise ratios. Trained on VB-DemandEx, MambAttention significantly outperforms existing state-of-the-art discriminative LSTM-, xLSTM-, Mamba-, and Conformer-based systems of similar complexity across all reported metrics on two out-of-domain datasets: DNS 2020 without reverberation and EARS-WHAM_v2. MambAttention also matches or outperforms generative diffusion models in generalization performance while being competitive with language model baselines. Ablation studies highlight the importance of weight sharing between time- and frequency-multi-head attention modules for generalization performance. Finally, we explore integrating the shared time- and frequency-multi-head attention modules with LSTM and xLSTM, which yields a notable performance improvement on the out-of-domain datasets. Yet, MambAttention remains superior for cross-corpus generalization across all reported evaluation metrics.