mlsanityData to 7 Oct 2026

FADI-AEC: Fast Score Based Diffusion Model Guided by Far-end Signal for Acoustic Echo Cancellation

arXiv 2401.04283 ↗First posted 8 Jan 2024eess.AS cs.SDcited by 0

On the map: Diffusion models → Audio, speech and music

Abstract (arXiv)

Despite the potential of diffusion models in speech enhancement, their deployment in Acoustic Echo Cancellation (AEC) has been restricted. In this paper, we propose DI-AEC, pioneering a diffusion-based stochastic regeneration approach dedicated to AEC. Further, we propose FADI-AEC, fast score-based diffusion AEC framework to save computational demands, making it favorable for edge devices. It stands out by running the score model once per frame, achieving a significant surge in processing efficiency. Apart from that, we introduce a novel noise generation technique where far-end signals are utilized, incorporating both far-end and near-end signals to refine the score model's accuracy. We test our proposed method on the ICASSP2023 Microsoft deep echo cancellation challenge evaluation dataset, where our method outperforms some of the end-to-end methods and other diffusion based echo cancellation methods.

Key facts. No citing papers in the map yet (data through 7 Oct 2026). Placed in Audio, speech and music, one of 14 directions in Diffusion models. Builds on 14 of its 19 references that are in the map. First posted on arXiv 8 Jan 2024.

Builds on

14 of 19 references.

Closest ancestors · 2

Same direction, newest first

  1. 2022StoRM: A Diffusion-based Stochastic Regeneration Model for Speech Enhancement and Dereverberation22 Dec
  2. 2022Conditional Diffusion Probabilistic Model for Speech Enhancement10 Feb

Other references · 12

  1. 2020Score-Based Generative Modeling through Stochastic Differential Equationscited by 8,964
  2. 2015Deep Unsupervised Learning using Nonequilibrium Thermodynamicscited by 7,005
  3. 2022Generative Adversarial Networkscited by 5,603
  4. 2021A Variational Perspective on Diffusion-Based Generative Models and Score Matchingcited by 182
  5. 2020DCCRN: Deep Complex Convolution Recurrent Network for Phase-Aware Speech Enhancementcited by 133
  6. 2022Universal Speech Enhancement with Score-based Diffusioncited by 75
  7. 2022ICASSP 2022 Deep Noise Suppression Challengecited by 57
  8. 2022ICASSP 2022 Acoustic Echo Cancellation Challengecited by 6
  9. 2021F-T-LSTM based Complex Network for Joint Acoustic Echo Cancellation and Speech Enhancementcited by 3
  10. 2022SCA: Streaming Cross-attention Alignment for Echo Cancellationcited by 2
  11. 2022LCSM: A Lightweight Complex Spectral Mapping Framework for Stereophonic Acoustic Echo Cancellationcited by 1
  12. 2023Two-step Band-split Neural Network Approach for Full-band Residual Echo Suppressioncited by 1

Built on by

Not cited yet.

Similar, not cited

Close in wording, no citation either way

  1. 2026DiffVQE2: An Efficient Low-delay Diffusion Model for Acoustic Echo and Noise Control
  2. 2021A Study on Speech Enhancement Based on Diffusion Probabilistic Model
  3. 2024Thunder : Unified Regression-Diffusion Speech Enhancement with a Single Reverse Step using Brownian Bridge
  4. 2023Single and Few-step Diffusion for Generative Speech Enhancement
  5. 2023Reducing the Prior Mismatch of Stochastic Differential Equations for Diffusion-based Speech Enhancement
  6. 2024GALD-SE: Guided Anisotropic Lightweight Diffusion for Efficient Speech Enhancement
  7. 2025GDiffuSE: Diffusion-based speech enhancement with noise model guidance
  8. 2023Investigating the Design Space of Diffusion Models for Speech Enhancement