# Direction-Preserving MIMO Speech Enhancement Using a Neural Covariance Estimator

arXiv: https://arxiv.org/abs/2604.11179 · HTML: https://mlsanity.com/paper/2604.11179/

## 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 11 of its 24 references that are in the map.
- First posted on arXiv 13 Apr 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, 11 of 11)

- [Adam: A Method for Stochastic Optimization](https://mlsanity.com/paper/1412.6980/) (2014)
- [Retentive Network: A Successor to Transformer for Large Language Models](https://mlsanity.com/paper/2307.08621/) (2023)
- [SDR - half-baked or well done?](https://mlsanity.com/paper/1811.02508/) (2018)
- [Pyroomacoustics: A Python package for audio room simulations and array processing algorithms](https://mlsanity.com/paper/1710.04196/) (2017)
- [ICASSP 2022 Deep Noise Suppression Challenge](https://mlsanity.com/paper/2202.13288/) (2022)
- [Multichannel Long-Term Streaming Neural Speech Enhancement for Static and Moving Speakers](https://mlsanity.com/paper/2403.07675/) (2024)
- [NICE-Beam: Neural Integrated Covariance Estimators for Time-Varying Beamformers](https://mlsanity.com/paper/2112.04613/) (2021)
- [Attention-Driven Multichannel Speech Enhancement in Moving Sound Source Scenarios](https://mlsanity.com/paper/2312.10756/) (2023)
- [Decoupled Spatial and Temporal Processing for Resource Efficient Multichannel Speech Enhancement](https://mlsanity.com/paper/2401.07879/) (2024)
- [Blind Identification of Binaural Room Impulse Responses from Smart Glasses](https://mlsanity.com/paper/2403.19217/) (2024)
- [Controlling the Parameterized Multi-channel Wiener Filter using a tiny neural network](https://mlsanity.com/paper/2507.13863/) (2025)

## Abstract (arXiv)

Multichannel speech enhancement is widely used as a front-end in microphone array processing systems. While most existing approaches produce a single enhanced signal, direction-preserving multiple-input multiple-output (MIMO) methods instead aim to provide enhanced multichannel signals that retain directional properties, enabling downstream applications such as beamforming, binaural rendering, and direction-of-arrival estimation. In this work, we propose a fully blind, direction-preserving MIMO speech enhancement method based on neural estimation of the spatial noise covariance matrix. A lightweight OnlineSpatialNet estimates a scale-normalized Cholesky factor of the frequency-domain noise covariance, which is combined with a direction-preserving MIMO Wiener filter to enhance speech while preserving the spatial characteristics of both target and residual noise. In contrast to prior approaches relying on oracle information or mask-based covariance estimation for single-output systems, the proposed method directly targets accurate multichannel covariance estimation with low computational complexity. Experimental results show improved speech enhancement, covariance estimation capability, and performance in downstream tasks over a mask-based baseline, approaching oracle performance with significantly fewer parameters and computational cost.