mlsanityData to 19 Oct 2026

Real-time speech enhancement with dynamic attention span

arXiv 2302.10377 ↗First posted 21 Feb 2023eess.AS cs.SDcited by 0

On the map: Speech and audio language models → Speech enhancement and noise suppression

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framework, a dynamic attention span mechanism is introduced to all the attention modules for controlling the size of historical content used for processing the current frame.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.

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.

Builds on

13 of 25 references.

Closest ancestors · 3

Same direction, newest first

  1. 2022NeuralEcho: A Self-Attentive Recurrent Neural Network For Unified Acoustic Echo Suppression And Speech Enhancement20 May
  2. 2022ICASSP 2022 Acoustic Echo Cancellation Challenge27 Feb
  3. 2021Low-Complexity, Real-Time Joint Neural Echo Control and Speech Enhancement Based On PercepNet10 Feb

Other references · 10

  1. 2015Batch Normalization: Accelerating Deep Network Training by Reducing Internal Covariate Shiftcited by 7,093
  2. 2015Delving Deep into Rectifiers: Surpassing Human-Level Performance on ImageNet Classificationcited by 3,653
  3. 2020DNSMOS: A Non-Intrusive Perceptual Objective Speech Quality metric to evaluate Noise Suppressorscited by 356
  4. 2019Adaptive Attention Span in Transformerscited by 156
  5. 2022ICASSP 2022 Deep Noise Suppression Challengecited by 107
  6. 2021AECMOS: A speech quality assessment metric for echo impairmentcited by 15
  7. 2020Acoustic echo cancellation with the dual-signal transformation LSTM networkcited by 11
  8. 2021End-to-End Complex-Valued Multidilated Convolutional Neural Network for Joint Acoustic Echo Cancellation and Noise Suppressioncited by 8
  9. 2021F-T-LSTM based Complex Network for Joint Acoustic Echo Cancellation and Speech Enhancementcited by 7
  10. 2021Joint Echo Cancellation and Noise Suppression based on Cascaded Magnitude and Complex Mask Estimationcited by 3

Built on by

Not cited yet.

Similar, not cited

Close in wording, no citation either way

  1. 2023Attention does not guarantee best performance in speech enhancement
  2. 2023Efficient Encoder-Decoder and Dual-Path Conformer for Comprehensive Feature Learning in Speech Enhancement
  3. 2023Time-Variance Aware Real-Time Speech Enhancement
  4. 2022MANNER: Multi-view Attention Network for Noise Erasure
  5. 2023BASEN: Time-Domain Brain-Assisted Speech Enhancement Network with Convolutional Cross Attention in Multi-talker Conditions
  6. 2021Towards efficient models for real-time deep noise suppression
  7. 2024Modulating State Space Model with SlowFast Framework for Compute-Efficient Ultra Low-Latency Speech Enhancement
  8. 2025A Two-Stage Hierarchical Deep Filtering Framework for Real-Time Speech Enhancement