# Distributed Asynchronous Device Speech Enhancement via Windowed Cross-Attention

arXiv: https://arxiv.org/abs/2507.16104 · HTML: https://mlsanity.com/paper/2507.16104/

## Key facts

- No citing papers in the map yet (data through 19 Oct 2026).
- Placed in Speech enhancement and noise suppression, one of 11 directions in Speech and audio language models.
- Builds on 20 of its 44 references that are in the map.
- First posted on arXiv 21 Jul 2025.

## Placed in

- Speech and audio language models / [Speech enhancement and noise suppression](https://mlsanity.com/speech/speech-enhancement-and-noise-suppression/)

## Builds on (most cited first, 20 of 20)

- [DNSMOS P.835: A Non-Intrusive Perceptual Objective Speech Quality Metric to Evaluate Noise Suppressors](https://mlsanity.com/paper/2110.01763/) (2021)
- [Dual-path RNN: efficient long sequence modeling for time-domain single-channel speech separation](https://mlsanity.com/paper/1910.06379/) (2019)
- [ICASSP 2023 Deep Noise Suppression Challenge](https://mlsanity.com/paper/2303.11510/) (2023)
- [End-to-end Microphone Permutation and Number Invariant Multi-channel Speech Separation](https://mlsanity.com/paper/1910.14104/) (2019)
- [Generative Pre-training for Speech with Flow Matching](https://mlsanity.com/paper/2310.16338/) (2023)
- [Towards efficient models for real-time deep noise suppression](https://mlsanity.com/paper/2101.09249/) (2021)
- [FaSNet: Low-latency Adaptive Beamforming for Multi-microphone Audio Processing](https://mlsanity.com/paper/1909.13387/) (2019)
- [A consolidated view of loss functions for supervised deep learning-based speech enhancement](https://mlsanity.com/paper/2009.12286/) (2020)
- [Distillation and Pruning for Scalable Self-Supervised Representation-Based Speech Quality Assessment](https://mlsanity.com/paper/2502.05356/) (2025)
- [VarArray: Array-Geometry-Agnostic Continuous Speech Separation](https://mlsanity.com/paper/2110.05745/) (2021)
- [Continuous Speech Separation with Ad Hoc Microphone Arrays](https://mlsanity.com/paper/2103.02378/) (2021)
- [Effect of noise suppression losses on speech distortion and ASR performance](https://mlsanity.com/paper/2111.11606/) (2021)
- [DeepVQE: Real Time Deep Voice Quality Enhancement for Joint Acoustic Echo Cancellation, Noise Suppression and Dereverberation](https://mlsanity.com/paper/2306.03177/) (2023)
- [Time-domain Ad-hoc Array Speech Enhancement Using a Triple-path Network](https://mlsanity.com/paper/2110.11844/) (2021)
- [Deep Ad-hoc Beamforming](https://mlsanity.com/paper/1811.01233/) (2018)
- [Microphone Subset Selection for MVDR Beamformer Based Noise Reduction](https://mlsanity.com/paper/1705.08255/) (2017)
- [Towards Real-Time Single-Channel Speech Separation in Noisy and Reverberant Environments](https://mlsanity.com/paper/2303.07569/) (2023)
- [PickNet: Real-Time Channel Selection for Ad Hoc Microphone Arrays](https://mlsanity.com/paper/2201.09586/) (2022)
- [SAMbA: Speech enhancement with Asynchronous ad-hoc Microphone Arrays](https://mlsanity.com/paper/2307.16582/) (2023)
- [Enhanced Deep Speech Separation in Clustered Ad Hoc Distributed Microphone Environments](https://mlsanity.com/paper/2406.09819/) (2024)

## Abstract (arXiv)

The increasing number of microphone-equipped personal devices offers great flexibility and potential using them as ad-hoc microphone arrays in dynamic meeting environments. However, most existing approaches are designed for time-synchronized microphone setups, a condition that may not hold in real-world meeting scenarios, where time latency and clock drift vary across devices. Under such conditions, we found transform-average-concatenate (TAC), a popular module for neural multi-microphone processing, insufficient in handling time-asynchronous microphones. In response, we propose a windowed cross-attention module capable of dynamically aligning features between all microphones. This module is invariant to both the permutation and the number of microphones and can be easily integrated into existing models. Furthermore, we propose an optimal training target for multi-talker environments. We evaluated our approach in a multi-microphone noisy reverberant setup with unknown time latency and clock drift of each microphone. Experimental results show that our method outperforms TAC on both iFaSNet and CRUSE models, offering faster convergence and improved learning, demonstrating the efficacy of the windowed cross-attention module for asynchronous microphone setups.