# Real-time speech enhancement with dynamic attention span

arXiv: https://arxiv.org/abs/2302.10377 · HTML: https://mlsanity.com/paper/2302.10377/

## Key facts

- No citing papers in the map yet (data through 19 Oct 2026).
- Placed in Speech enhancement and noise suppression, one of 11 directions in Speech and audio language models.
- Builds on 13 of its 25 references that are in the map.
- First posted on arXiv 21 Feb 2023.

## Placed in

- Speech and audio language models / [Speech enhancement and noise suppression](https://mlsanity.com/speech/speech-enhancement-and-noise-suppression/)

## Builds on (most cited first, 13 of 13)

- [Batch Normalization: Accelerating Deep Network Training by Reducing Internal Covariate Shift](https://mlsanity.com/paper/1502.03167/) (2015)
- [Delving Deep into Rectifiers: Surpassing Human-Level Performance on ImageNet Classification](https://mlsanity.com/paper/1502.01852/) (2015)
- [DNSMOS: A Non-Intrusive Perceptual Objective Speech Quality metric to evaluate Noise Suppressors](https://mlsanity.com/paper/2010.15258/) (2020)
- [Adaptive Attention Span in Transformers](https://mlsanity.com/paper/1905.07799/) (2019)
- [ICASSP 2022 Deep Noise Suppression Challenge](https://mlsanity.com/paper/2202.13288/) (2022)
- [AECMOS: A speech quality assessment metric for echo impairment](https://mlsanity.com/paper/2110.03010/) (2021)
- [ICASSP 2022 Acoustic Echo Cancellation Challenge](https://mlsanity.com/paper/2202.13290/) (2022)
- [Low-Complexity, Real-Time Joint Neural Echo Control and Speech Enhancement Based On PercepNet](https://mlsanity.com/paper/2102.05245/) (2021)
- [Acoustic echo cancellation with the dual-signal transformation LSTM network](https://mlsanity.com/paper/2010.14337/) (2020)
- [End-to-End Complex-Valued Multidilated Convolutional Neural Network for Joint Acoustic Echo Cancellation and Noise Suppression](https://mlsanity.com/paper/2110.00745/) (2021)
- [F-T-LSTM based Complex Network for Joint Acoustic Echo Cancellation and Speech Enhancement](https://mlsanity.com/paper/2106.07577/) (2021)
- [Joint Echo Cancellation and Noise Suppression based on Cascaded Magnitude and Complex Mask Estimation](https://mlsanity.com/paper/2107.09298/) (2021)
- [NeuralEcho: A Self-Attentive Recurrent Neural Network For Unified Acoustic Echo Suppression And Speech Enhancement](https://mlsanity.com/paper/2205.10401/) (2022)

## Abstract (arXiv)

For real-time speech enhancement (SE) including noise suppression, dereverberation and acoustic echo cancellation, the time-variance of the audio signals becomes a severe challenge. The causality and memory usage limit that only the historical information can be used for the system to capture the time-variant characteristics. We propose to adaptively change the receptive field according to the input signal in deep neural network based SE model. Specifically, in an encoder-decoder framework, a dynamic attention span mechanism is introduced to all the attention modules for controlling the size of historical content used for processing the current frame. Experimental results verify that this dynamic mechanism can better track time-variant factors and capture speech-related characteristics, benefiting to both interference removing and speech quality retaining.