# DiffVQE: Hybrid Diffusion Voice Quality Enhancement Under Acoustic Echo and Noise

arXiv: https://arxiv.org/abs/2605.08189 · HTML: https://mlsanity.com/paper/2605.08189/

## 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 28 of its 44 references that are in the map.
- First posted on arXiv 5 May 2026.

## 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, 28 of 28)

- [Score-Based Generative Modeling through Stochastic Differential Equations](https://mlsanity.com/paper/2011.13456/) (2020)
- [Elucidating the Design Space of Diffusion-Based Generative Models](https://mlsanity.com/paper/2206.00364/) (2022)
- [Common Voice: A Massively-Multilingual Speech Corpus](https://mlsanity.com/paper/1912.06670/) (2019)
- [Real-Time Single Image and Video Super-Resolution Using an Efficient Sub-Pixel Convolutional Neural Network](https://mlsanity.com/paper/1609.05158/) (2016)
- [UTMOS: UTokyo-SaruLab System for VoiceMOS Challenge 2022](https://mlsanity.com/paper/2204.02152/) (2022)
- [DNSMOS: A Non-Intrusive Perceptual Objective Speech Quality metric to evaluate Noise Suppressors](https://mlsanity.com/paper/2010.15258/) (2020)
- [NISQA: A Deep CNN-Self-Attention Model for Multidimensional Speech Quality Prediction with Crowdsourced Datasets](https://mlsanity.com/paper/2104.09494/) (2021)
- [Speech Enhancement and Dereverberation with Diffusion-based Generative Models](https://mlsanity.com/paper/2208.05830/) (2022)
- [Pyroomacoustics: A Python package for audio room simulations and array processing algorithms](https://mlsanity.com/paper/1710.04196/) (2017)
- [StoRM: A Diffusion-based Stochastic Regeneration Model for Speech Enhancement and Dereverberation](https://mlsanity.com/paper/2212.11851/) (2022)
- [Speech Enhancement with Score-Based Generative Models in the Complex STFT Domain](https://mlsanity.com/paper/2203.17004/) (2022)
- [Adversarial score matching and improved sampling for image generation](https://mlsanity.com/paper/2009.05475/) (2020)
- [TorchAudio-Squim: Reference-less Speech Quality and Intelligibility measures in TorchAudio](https://mlsanity.com/paper/2304.01448/) (2023)
- [URGENT Challenge: Universality, Robustness, and Generalizability For Speech Enhancement](https://mlsanity.com/paper/2406.04660/) (2024)
- [A consolidated view of loss functions for supervised deep learning-based speech enhancement](https://mlsanity.com/paper/2009.12286/) (2020)
- [Universal Score-based Speech Enhancement with High Content Preservation](https://mlsanity.com/paper/2406.12194/) (2024)
- [ICASSP 2024 Speech Signal Improvement Challenge](https://mlsanity.com/paper/2401.14444/) (2024)
- [Interspeech 2025 URGENT Speech Enhancement Challenge](https://mlsanity.com/paper/2505.23212/) (2025)
- [AECMOS: A speech quality assessment metric for echo impairment](https://mlsanity.com/paper/2110.03010/) (2021)
- [DeepVQE: Real Time Deep Voice Quality Enhancement for Joint Acoustic Echo Cancellation, Noise Suppression and Dereverberation](https://mlsanity.com/paper/2306.03177/) (2023)
- [ICASSP 2023 Acoustic Echo Cancellation Challenge](https://mlsanity.com/paper/2309.12553/) (2023)
- [Low-Complexity Acoustic Echo Cancellation with Neural Kalman Filtering](https://mlsanity.com/paper/2207.11388/) (2022)
- [A Hybrid Approach for Low-Complexity Joint Acoustic Echo and Noise Reduction](https://mlsanity.com/paper/2408.15746/) (2024)
- [End-To-End Deep Learning-based Adaptation Control for Linear Acoustic Echo Cancellation](https://mlsanity.com/paper/2306.02450/) (2023)
- [Neural Kalman Filters for Acoustic Echo Cancellation](https://mlsanity.com/paper/2501.16367/) (2025)
- [P.808 Multilingual Speech Enhancement Testing: Approach and Results of URGENT 2025 Challenge](https://mlsanity.com/paper/2507.11306/) (2025)
- [EchoFree: Towards Ultra Lightweight and Efficient Neural Acoustic Echo Cancellation](https://mlsanity.com/paper/2508.06271/) (2025)
- [Efficient High-Performance Bark-Scale Neural Network for Residual Echo and Noise Suppression](https://mlsanity.com/paper/2404.11621/) (2024)

## Abstract (arXiv)

Acoustic echo and background noise pose challenges on speech enhancement in hands-free systems and speakerphones. Discriminatively trained end-to-end methods represent a powerful solution for joint acoustic echo control (AEC) and denoising. However, with the advent of generative methods, diffusion-based approaches have seen remarkable performance in speech enhancement tasks. In this work, to the best of our knowledge, we provide the first (still non-causal) diffusion-based AEC model (DiffVQE) that is reproducible in terms of topology, training data, and training framework. So far, without employing diffusion, Microsoft's discriminative DeepVQE model has been shown to excel any of the ICASSP 2023 AEC Challenge entries achieving remarkable performance. Using data from the Interspeech 2025 URGENT Challenge for a diverse, high-quality training dataset, our DiffVQE excels DeepVQE both in echo and noise control performance, as well as in computational complexity and model size.