Enhanced Generative Machine Listener
Abstract
We present GMLv2, a reference-based model designed for the prediction of subjective audio quality as measured by MUSHRA scores. GMLv2 introduces a Beta distribution-based loss to model the listener ratings and incorporates additional neural audio coding (NAC) subjective datasets to extend its generalization and applicability. Extensive evaluations on diverse testset demonstrate that proposed GMLv2 consistently outperforms widely used metrics, such as PEAQ and ViSQOL, both in terms of correlation with subjective scores and in reliably predicting these scores across diverse content types and codec configurations. Consequently, GMLv2 offers a scalable and automated framework for perceptual audio quality evaluation, poised to accelerate research and development in modern audio coding technologies.
Keywords
Cite
@article{arxiv.2509.21463,
title = {Enhanced Generative Machine Listener},
author = {Vishnu Raj and Gouthaman KV and Shiv Gehlot and Lars Villemoes and Arijit Biswas},
journal= {arXiv preprint arXiv:2509.21463},
year = {2026}
}
Comments
Accepted to the 51st IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP), Barcelona, Spain, 4-8 May 2026