# Non-intrusive Speech Quality Assessment with Diffusion Models Trained on Clean Speech

arXiv: https://arxiv.org/abs/2410.17834 · HTML: https://mlsanity.com/paper/2410.17834/

## Key facts

- Cited by 1 papers in the map (data through 14 Oct 2026).
- Placed in Audio, speech and music, one of 14 directions in Diffusion models.
- Builds on 21 of its 28 references that are in the map.
- First posted on arXiv 23 Oct 2024.

## Placed in

- Diffusion models / [Audio, speech and music](https://mlsanity.com/diffusion/audio-speech-and-music/)

## Builds on (most cited first, 21 of 21)

- [Denoising Diffusion Probabilistic Models](https://mlsanity.com/paper/2006.11239/) (2020)
- [Score-Based Generative Modeling through Stochastic Differential Equations](https://mlsanity.com/paper/2011.13456/) (2020)
- [Diffusion Models Beat GANs on Image Synthesis](https://mlsanity.com/paper/2105.05233/) (2021)
- [Neural Ordinary Differential Equations](https://mlsanity.com/paper/1806.07366/) (2018)
- [Elucidating the Design Space of Diffusion-Based Generative Models](https://mlsanity.com/paper/2206.00364/) (2022)
- [WaveGrad: Estimating Gradients for Waveform Generation](https://mlsanity.com/paper/2009.00713/) (2020)
- [SDR - half-baked or well done?](https://mlsanity.com/paper/1811.02508/) (2018)
- [Analyzing and Improving the Training Dynamics of Diffusion Models](https://mlsanity.com/paper/2312.02696/) (2023)
- [Speech Enhancement and Dereverberation with Diffusion-based Generative Models](https://mlsanity.com/paper/2208.05830/) (2022)
- [NISQA: A Deep CNN-Self-Attention Model for Multidimensional Speech Quality Prediction with Crowdsourced Datasets](https://mlsanity.com/paper/2104.09494/) (2021)
- [DNSMOS P.835: A Non-Intrusive Perceptual Objective Speech Quality Metric to Evaluate Noise Suppressors](https://mlsanity.com/paper/2110.01763/) (2021)
- [Hybrid Transformers for Music Source Separation](https://mlsanity.com/paper/2211.08553/) (2022)
- [ViSQOL v3: An Open Source Production Ready Objective Speech and Audio Metric](https://mlsanity.com/paper/2004.09584/) (2020)
- [EARS: An Anechoic Fullband Speech Dataset Benchmarked for Speech Enhancement and Dereverberation](https://mlsanity.com/paper/2406.06185/) (2024)
- [Solving Audio Inverse Problems with a Diffusion Model](https://mlsanity.com/paper/2210.15228/) (2022)
- [Analysing Diffusion-based Generative Approaches versus Discriminative Approaches for Speech Restoration](https://mlsanity.com/paper/2211.02397/) (2022)
- [SpeechLMScore: Evaluating speech generation using speech language model](https://mlsanity.com/paper/2212.04559/) (2022)
- [Speech Quality Assessment through MOS using Non-Matching References](https://mlsanity.com/paper/2206.12285/) (2022)
- [The PESQetarian: On the Relevance of Goodhart's Law for Speech Enhancement](https://mlsanity.com/paper/2406.03460/) (2024)
- [Self-Supervised Speech Quality Estimation and Enhancement Using Only Clean Speech](https://mlsanity.com/paper/2402.16321/) (2024)
- [On the Behavior of Intrusive and Non-intrusive Speech Enhancement Metrics in Predictive and Generative Settings](https://mlsanity.com/paper/2306.03014/) (2023)

## Built on by (most cited first, 1 of 1)

- [LipDiffuser: Lip-to-Speech Generation with Conditional Diffusion Models](https://mlsanity.com/paper/2505.11391/) (2025)

## Abstract (arXiv)

Diffusion models have found great success in generating high quality, natural samples of speech, but their potential for density estimation for speech has so far remained largely unexplored. In this work, we leverage an unconditional diffusion model trained only on clean speech for the assessment of speech quality. We show that the quality of a speech utterance can be assessed by estimating the likelihood of a corresponding sample in the terminating Gaussian distribution, obtained via a deterministic noising process. The resulting method is purely unsupervised, trained only on clean speech, and therefore does not rely on annotations. Our diffusion-based approach leverages clean speech priors to assess quality based on how the input relates to the learned distribution of clean data. Our proposed log-likelihoods show promising results, correlating well with intrusive speech quality metrics and showing the best correlation with human scores in a listening experiment.