# A neural network-supported two-stage algorithm for lightweight dereverberation on hearing devices

arXiv: https://arxiv.org/abs/2204.02978 · HTML: https://mlsanity.com/paper/2204.02978/

## Key facts

- No citing papers in the map yet (data through 14 Oct 2026).
- Builds on 9 of its 46 references that are in the map.
- First posted on arXiv 6 Apr 2022.

## Builds on (most cited first, 9 of 9)

- [WHAMR!: Noisy and Reverberant Single-Channel Speech Separation](https://mlsanity.com/paper/1910.10279/) (2019)
- [ICASSP 2022 Deep Noise Suppression Challenge](https://mlsanity.com/paper/2202.13288/) (2022)
- [MIMO-SPEECH: End-to-End Multi-Channel Multi-Speaker Speech Recognition](https://mlsanity.com/paper/1910.06522/) (2019)
- [Glance and Gaze: A Collaborative Learning Framework for Single-channel Speech Enhancement](https://mlsanity.com/paper/2106.11789/) (2021)
- [Speech Dereverberation Using Fully Convolutional Networks](https://mlsanity.com/paper/1803.08243/) (2018)
- [End-to-End Dereverberation, Beamforming, and Speech Recognition with Improved Numerical Stability and Advanced Frontend](https://mlsanity.com/paper/2102.11525/) (2021)
- [Coherent-to-Diffuse Power Ratio Estimation for Dereverberation](https://mlsanity.com/paper/1502.03784/) (2015)
- [Convolutive Prediction for Monaural Speech Dereverberation and Noisy-Reverberant Speaker Separation](https://mlsanity.com/paper/2108.07376/) (2021)
- [ICASSP 2021 Deep Noise Suppression Challenge: Decoupling Magnitude and Phase Optimization with a Two-Stage Deep Network](https://mlsanity.com/paper/2102.04198/) (2021)

## Abstract (arXiv)

A two-stage lightweight online dereverberation algorithm for hearing devices is presented in this paper. The approach combines a multi-channel multi-frame linear filter with a single-channel single-frame post-filter. Both components rely on power spectral density (PSD) estimates provided by deep neural networks (DNNs). By deriving new metrics analyzing the dereverberation performance in various time ranges, we confirm that directly optimizing for a criterion at the output of the multi-channel linear filtering stage results in a more efficient dereverberation as compared to placing the criterion at the output of the DNN to optimize the PSD estimation. More concretely, we show that training this stage end-to-end helps further remove the reverberation in the range accessible to the filter, thus increasing the textitearly-to-moderate reverberation ratio. We argue and demonstrate that it can then be well combined with a post-filtering stage to efficiently suppress the residual late reverberation, thereby increasing the textitearly-to-final reverberation ratio. This proposed two stage procedure is shown to be both very effective in terms of dereverberation performance and computational demands, as compared to e.g. recent state-of-the-art DNN approaches. Furthermore, the proposed two-stage system can be adapted to the needs of different types of hearing-device users by controlling the amount of reduction of early reflections.