# FaSNet: Low-latency Adaptive Beamforming for Multi-microphone Audio Processing

arXiv: https://arxiv.org/abs/1909.13387 · HTML: https://mlsanity.com/paper/1909.13387/

## Key facts

- Cited by 23 papers in the map (data through 14 Oct 2026).
- First posted on arXiv 29 Sep 2019.

## Built on by (most cited first, 23 of 23)

- [Insights Into Deep Non-linear Filters for Improved Multi-channel Speech Enhancement](https://mlsanity.com/paper/2206.13310/) (2022)
- [Many-Speakers Single Channel Speech Separation with Optimal Permutation Training](https://mlsanity.com/paper/2104.08955/) (2021)
- [Learning Audio-Visual Dynamics Using Scene Graphs for Audio Source Separation](https://mlsanity.com/paper/2210.16472/) (2022)
- [L3DAS22 Challenge: Learning 3D Audio Sources in a Real Office Environment](https://mlsanity.com/paper/2202.10372/) (2022)
- [L3DAS21 Challenge: Machine Learning for 3D Audio Signal Processing](https://mlsanity.com/paper/2104.05499/) (2021)
- [Effective Low-Cost Time-Domain Audio Separation Using Globally Attentive Locally Recurrent Networks](https://mlsanity.com/paper/2101.05014/) (2021)
- [Hybrid Neural Networks for On-device Directional Hearing](https://mlsanity.com/paper/2112.05893/) (2021)
- [ESPnet-SE++: Speech Enhancement for Robust Speech Recognition, Translation, and Understanding](https://mlsanity.com/paper/2207.09514/) (2022)
- [Implicit Neural Spatial Filtering for Multichannel Source Separation in the Waveform Domain](https://mlsanity.com/paper/2206.15423/) (2022)
- [Learning to Separate Voices by Spatial Regions](https://mlsanity.com/paper/2207.04203/) (2022)
- [Multi-Channel End-to-End Neural Diarization with Distributed Microphones](https://mlsanity.com/paper/2110.04694/) (2021)
- [RTFS-Net: Recurrent Time-Frequency Modelling for Efficient Audio-Visual Speech Separation](https://mlsanity.com/paper/2309.17189/) (2023)
- [Learning Filterbanks for End-to-End Acoustic Beamforming](https://mlsanity.com/paper/2111.04614/) (2021)
- [A Time-domain Real-valued Generalized Wiener Filter for Multi-channel Neural Separation Systems](https://mlsanity.com/paper/2112.03533/) (2021)
- [Guided Speech Enhancement Network](https://mlsanity.com/paper/2303.07486/) (2023)
- [Binaural Angular Separation Network](https://mlsanity.com/paper/2401.08864/) (2024)
- [Frequency-Weighted Training Losses for Phoneme-Level DNN-based Speech Enhancement](https://mlsanity.com/paper/2506.18714/) (2025)
- [Mutual Learning of Single- and Multi-Channel End-to-End Neural Diarization](https://mlsanity.com/paper/2210.03459/) (2022)
- [Attention-Driven Multichannel Speech Enhancement in Moving Sound Source Scenarios](https://mlsanity.com/paper/2312.10756/) (2023)
- [Joint Beamforming and Speaker-Attributed ASR for Real Distant-Microphone Meeting Transcription](https://mlsanity.com/paper/2410.21849/) (2024)
- [End-to-End Multi-Microphone Speaker Extraction Using Relative Transfer Functions](https://mlsanity.com/paper/2502.06285/) (2025)
- [CaSNet: Compress-and-Send Network Based Multi-Device Speech Enhancement Model for Distributed Microphone Arrays](https://mlsanity.com/paper/2601.17711/) (2026)
- [EgoAdapt: Enhancing Robustness in Egocentric Interactive Speaker Detection Under Missing Modalities](https://mlsanity.com/paper/2603.18082/) (2026)

## Abstract (arXiv)

Beamforming has been extensively investigated for multi-channel audio processing tasks. Recently, learning-based beamforming methods, sometimes called textitneural beamformers, have achieved significant improvements in both signal quality (e.g. signal-to-noise ratio (SNR)) and speech recognition (e.g. word error rate (WER)). Such systems are generally non-causal and require a large context for robust estimation of inter-channel features, which is impractical in applications requiring low-latency responses. In this paper, we propose filter-and-sum network (FaSNet), a time-domain, filter-based beamforming approach suitable for low-latency scenarios. FaSNet has a two-stage system design that first learns frame-level time-domain adaptive beamforming filters for a selected reference channel, and then calculate the filters for all remaining channels. The filtered outputs at all channels are summed to generate the final output. Experiments show that despite its small model size, FaSNet is able to outperform several traditional oracle beamformers with respect to scale-invariant signal-to-noise ratio (SI-SNR) in reverberant speech enhancement and separation tasks. Moreover, when trained with a frequency-domain objective function on the CHiME-3 dataset, FaSNet achieves 14.3% relative word error rate reduction (RWERR) compared with the baseline model. These results show the efficacy of FaSNet particularly in reverberant and noisy signal conditions.