# Towards Array-Invariant Speech Enhancement via Geometry-Aware Dynamic Convolution

arXiv: https://arxiv.org/abs/2607.18658 · HTML: https://mlsanity.com/paper/2607.18658/

## 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 15 of its 22 references that are in the map.
- First posted on arXiv 21 Jul 2026.

## 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, 15 of 15)

- [DNSMOS P.835: A Non-Intrusive Perceptual Objective Speech Quality Metric to Evaluate Noise Suppressors](https://mlsanity.com/paper/2110.01763/) (2021)
- [TF-GridNet: Integrating Full- and Sub-Band Modeling for Speech Separation](https://mlsanity.com/paper/2211.12433/) (2022)
- [Music Source Separation with Band-split RNN](https://mlsanity.com/paper/2209.15174/) (2022)
- [End-to-end Microphone Permutation and Number Invariant Multi-channel Speech Separation](https://mlsanity.com/paper/1910.14104/) (2019)
- [Learning Neural Acoustic Fields](https://mlsanity.com/paper/2204.00628/) (2022)
- [SpatialNet: Extensively Learning Spatial Information for Multichannel Joint Speech Separation, Denoising and Dereverberation](https://mlsanity.com/paper/2307.16516/) (2023)
- [AnyEnhance: A Unified Generative Model with Prompt-Guidance and Self-Critic for Voice Enhancement](https://mlsanity.com/paper/2501.15417/) (2025)
- [TPARN: Triple-path Attentive Recurrent Network for Time-domain Multichannel Speech Enhancement](https://mlsanity.com/paper/2110.10757/) (2021)
- [Closing the Gap Between Time-Domain Multi-Channel Speech Enhancement on Real and Simulation Conditions](https://mlsanity.com/paper/2110.14139/) (2021)
- [RealMAN: A Real-Recorded and Annotated Microphone Array Dataset for Dynamic Speech Enhancement and Localization](https://mlsanity.com/paper/2406.19959/) (2024)
- [Improving Design of Input Condition Invariant Speech Enhancement](https://mlsanity.com/paper/2401.14271/) (2024)
- [SenSE: Semantic-Aware High-Fidelity Universal Speech Enhancement](https://mlsanity.com/paper/2509.24708/) (2025)
- [A Study of the Scale Invariant Signal to Distortion Ratio in Speech Separation with Noisy References](https://mlsanity.com/paper/2508.14623/) (2025)
- [AmbiDrop: Array-Agnostic Speech Enhancement Using Ambisonics Encoding and Dropout-Based Learning](https://mlsanity.com/paper/2509.14855/) (2025)
- [UniArray: Unified Spectral-Spatial Modeling for Array-Geometry-Agnostic Speech Separation](https://mlsanity.com/paper/2503.05110/) (2025)

## Abstract (arXiv)

Multi-channel speech enhancement (SE) systems exhibit superior performance over single-channel methods but are constrained to fixed microphone array configurations. This restricts their real-world deployment across devices with diverse array geometries. While recent array-agnostic SE methods address variable microphone numbers and permutations, they largely fail to exploit explicit array geometry priors when available, missing a crucial cue for optimal spatial filtering. A Geometry-Aware Dynamic Convolution (Geo-DConv) framework is proposed, which explicitly leverages microphone coordinates to transform standard fixed-array SE models into robust array-invariant systems. Experiments are conducted on the recent real-recorded RealMAN multi-channel speech dataset. Results demonstrate that the proposed architecture enables two widely used fixed-array models to adapt to array-invariant settings, with consistent performance improvements across diverse array topologies.