Back to Search Start Over

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

Authors :
de Oliveira, Danilo
Richter, Julius
Lemercier, Jean-Marie
Welker, Simon
Gerkmann, Timo
Publication Year :
2024

Abstract

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 such as POLQA and SI-SDR.

Details

Database :
arXiv
Publication Type :
Report
Accession number :
edsarx.2410.17834
Document Type :
Working Paper