# On the Role of Spatial, Spectral, and Temporal Processing for DNN-based Non-linear Multi-channel Speech Enhancement

arXiv: https://arxiv.org/abs/2206.11181 · HTML: https://mlsanity.com/paper/2206.11181/

## Key facts

- Cited by 6 papers in the map (data through 14 Oct 2026).
- Builds on 5 of its 25 references that are in the map.
- First posted on arXiv 22 Jun 2022.

## Builds on (most cited first, 5 of 5)

- [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)
- [Channel-Attention Dense U-Net for Multichannel Speech Enhancement](https://mlsanity.com/paper/2001.11542/) (2020)
- [DF-Conformer: Integrated architecture of Conv-TasNet and Conformer using linear complexity self-attention for speech enhancement](https://mlsanity.com/paper/2106.15813/) (2021)
- [Nonlinear Spatial Filtering in Multichannel Speech Enhancement](https://mlsanity.com/paper/2104.11033/) (2021)

## Built on by (most cited first, 6 of 6)

- [Insights Into Deep Non-linear Filters for Improved Multi-channel Speech Enhancement](https://mlsanity.com/paper/2206.13310/) (2022)
- [Multi-channel Speech Separation Using Spatially Selective Deep Non-linear Filters](https://mlsanity.com/paper/2304.12023/) (2023)
- [Spatially Selective Deep Non-linear Filters for Speaker Extraction](https://mlsanity.com/paper/2211.02420/) (2022)
- [xLSTM-SENet: xLSTM for Single-Channel Speech Enhancement](https://mlsanity.com/paper/2501.06146/) (2025)
- [MambAttention: Mamba with Multi-Head Attention for Generalizable Single-Channel Speech Enhancement](https://mlsanity.com/paper/2507.00966/) (2025)
- [Self-Steering Deep Non-Linear Spatially Selective Filters for Efficient Extraction of Moving Speakers under Weak Guidance](https://mlsanity.com/paper/2507.02791/) (2025)

## Abstract (arXiv)

Employing deep neural networks (DNNs) to directly learn filters for multi-channel speech enhancement has potentially two key advantages over a traditional approach combining a linear spatial filter with an independent tempo-spectral post-filter: 1) non-linear spatial filtering allows to overcome potential restrictions originating from a linear processing model and 2) joint processing of spatial and tempo-spectral information allows to exploit interdependencies between different sources of information. A variety of DNN-based non-linear filters have been proposed recently, for which good enhancement performance is reported. However, little is known about the internal mechanisms which turns network architecture design into a game of chance. Therefore, in this paper, we perform experiments to better understand the internal processing of spatial, spectral and temporal information by DNN-based non-linear filters. On the one hand, our experiments in a difficult speech extraction scenario confirm the importance of non-linear spatial filtering, which outperforms an oracle linear spatial filter by 0.24 POLQA score. On the other hand, we demonstrate that joint processing results in a large performance gap of 0.4 POLQA score between network architectures exploiting spectral versus temporal information besides spatial information.