# Multichannel Speech Separation with Narrow-band Conformer

arXiv: https://arxiv.org/abs/2204.04464 · HTML: https://mlsanity.com/paper/2204.04464/

## Key facts

- Cited by 3 papers in the map (data through 14 Oct 2026).
- First posted on arXiv 9 Apr 2022.

## Built on by (most cited first, 3 of 3)

- [Multi-channel Speech Separation Using Spatially Selective Deep Non-linear Filters](https://mlsanity.com/paper/2304.12023/) (2023)
- [Deep Neural Mel-Subband Beamformer for In-car Speech Separation](https://mlsanity.com/paper/2211.12590/) (2022)
- [Unsupervised Multi-channel Speech Dereverberation via Diffusion](https://mlsanity.com/paper/2508.02071/) (2025)

## Abstract (arXiv)

This work proposes a multichannel speech separation method with narrow-band Conformer (named NBC). The network is trained to learn to automatically exploit narrow-band speech separation information, such as spatial vector clustering of multiple speakers. Specifically, in the short-time Fourier transform (STFT) domain, the network processes each frequency independently, and is shared by all frequencies. For one frequency, the network inputs the STFT coefficients of multichannel mixture signals, and predicts the STFT coefficients of separated speech signals. Clustering of spatial vectors shares a similar principle with the self-attention mechanism in the sense of computing the similarity of vectors and then aggregating similar vectors. Therefore, Conformer would be especially suitable for the present problem. Experiments show that the proposed narrow-band Conformer achieves better speech separation performance than other state-of-the-art methods by a large margin.