# Run-Time Adaptation of Neural Beamforming for Robust Speech Dereverberation and Denoising

arXiv: https://arxiv.org/abs/2410.22805 · HTML: https://mlsanity.com/paper/2410.22805/

## Key facts

- No citing papers in the map yet (data through 14 Oct 2026).
- Builds on 10 of its 28 references that are in the map.
- First posted on arXiv 30 Oct 2024.

## Builds on (most cited first, 10 of 10)

- [SDR - half-baked or well done?](https://mlsanity.com/paper/1811.02508/) (2018)
- [SpeechBrain: A General-Purpose Speech Toolkit](https://mlsanity.com/paper/2106.04624/) (2021)
- [Supervised Speech Separation Based on Deep Learning: An Overview](https://mlsanity.com/paper/1708.07524/) (2017)
- [SEGAN: Speech Enhancement Generative Adversarial Network](https://mlsanity.com/paper/1703.09452/) (2017)
- [Pyroomacoustics: A Python package for audio room simulations and array processing algorithms](https://mlsanity.com/paper/1710.04196/) (2017)
- [Conditional Diffusion Probabilistic Model for Speech Enhancement](https://mlsanity.com/paper/2202.05256/) (2022)
- [TorchAudio-Squim: Reference-less Speech Quality and Intelligibility measures in TorchAudio](https://mlsanity.com/paper/2304.01448/) (2023)
- [End-to-End Far-Field Speech Recognition with Unified Dereverberation and Beamforming](https://mlsanity.com/paper/2005.10479/) (2020)
- [A unified convolutional beamformer for simultaneous denoising and dereverberation](https://mlsanity.com/paper/1812.08400/) (2018)
- [Direction-Aware Adaptive Online Neural Speech Enhancement with an Augmented Reality Headset in Real Noisy Conversational Environments](https://mlsanity.com/paper/2207.07296/) (2022)

## Abstract (arXiv)

This paper describes speech enhancement for realtime automatic speech recognition (ASR) in real environments. A standard approach to this task is to use neural beamforming that can work efficiently in an online manner. It estimates the masks of clean dry speech from a noisy echoic mixture spectrogram with a deep neural network (DNN) and then computes a enhancement filter used for beamforming. The performance of such a supervised approach, however, is drastically degraded under mismatched conditions. This calls for run-time adaptation of the DNN. Although the ground-truth speech spectrogram required for adaptation is not available at run time, blind dereverberation and separation methods such as weighted prediction error (WPE) and fast multichannel nonnegative matrix factorization (FastMNMF) can be used for generating pseudo groundtruth data from a mixture. Based on this idea, a prior work proposed a dual-process system based on a cascade of WPE and minimum variance distortionless response (MVDR) beamforming asynchronously fine-tuned by block-online FastMNMF. To integrate the dereverberation capability into neural beamforming and make it fine-tunable at run time, we propose to use weighted power minimization distortionless response (WPD) beamforming, a unified version of WPE and minimum power distortionless response (MPDR), whose joint dereverberation and denoising filter is estimated using a DNN. We evaluated the impact of run-time adaptation under various conditions with different numbers of speakers, reverberation times, and signal-to-noise ratios (SNRs).