# Enhanced Generative Machine Listener

arXiv: https://arxiv.org/abs/2509.21463 · HTML: https://mlsanity.com/paper/2509.21463/

## Key facts

- Cited by 1 papers in the map (data through 14 Oct 2026).
- Builds on 14 of its 36 references that are in the map.
- First posted on arXiv 25 Sep 2025.

## Builds on (most cited first, 14 of 14)

- [High Fidelity Neural Audio Compression](https://mlsanity.com/paper/2210.13438/) (2022)
- [High-Fidelity Audio Compression with Improved RVQGAN](https://mlsanity.com/paper/2306.06546/) (2023)
- [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)
- [ViSQOL v3: An Open Source Production Ready Objective Speech and Audio Metric](https://mlsanity.com/paper/2004.09584/) (2020)
- [Quality-Net: An End-to-End Non-intrusive Speech Quality Assessment Model based on BLSTM](https://mlsanity.com/paper/1808.05344/) (2018)
- [ConferencingSpeech 2022 Challenge: Non-intrusive Objective Speech Quality Assessment (NISQA) Challenge for Online Conferencing Applications](https://mlsanity.com/paper/2203.16032/) (2022)
- [Objective Measures of Perceptual Audio Quality Reviewed: An Evaluation of Their Application Domain Dependence](https://mlsanity.com/paper/2110.11438/) (2021)
- [Audio Codec Enhancement with Generative Adversarial Networks](https://mlsanity.com/paper/2001.09653/) (2020)
- [Source coding of audio signals with a generative model](https://mlsanity.com/paper/2001.09847/) (2020)
- [Generative Machine Listener](https://mlsanity.com/paper/2308.09493/) (2023)
- [ODAQ: Open Dataset of Audio Quality](https://mlsanity.com/paper/2401.00197/) (2023)
- [Stereo InSE-NET: Stereo Audio Quality Predictor Transfer Learned from Mono InSE-NET](https://mlsanity.com/paper/2209.11666/) (2022)
- [RF-GML: Reference-Free Generative Machine Listener](https://mlsanity.com/paper/2409.10210/) (2024)

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

- [Multichannel Audio Quality Assessment: Extending Pretrained Perceptual Models to Spatial Audio](https://mlsanity.com/paper/2609.37116/) (2026)

## Abstract (arXiv)

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.