# Robust Generative Audio Quality Assessment: Disentangling Quality from Spurious Correlations

arXiv: https://arxiv.org/abs/2603.16201 · HTML: https://mlsanity.com/paper/2603.16201/

## Key facts

- No citing papers in the map yet (data through 14 Oct 2026).
- Builds on 18 of its 22 references that are in the map.
- First posted on arXiv 17 Mar 2026.

## Builds on (most cited first, 18 of 18)

- [Domain-Adversarial Training of Neural Networks](https://mlsanity.com/paper/1505.07818/) (2015)
- [Unsupervised Domain Adaptation by Backpropagation](https://mlsanity.com/paper/1409.7495/) (2014)
- [XLS-R: Self-supervised Cross-lingual Speech Representation Learning at Scale](https://mlsanity.com/paper/2111.09296/) (2021)
- [UTMOS: UTokyo-SaruLab System for VoiceMOS Challenge 2022](https://mlsanity.com/paper/2204.02152/) (2022)
- [Exploring Video Quality Assessment on User Generated Contents from Aesthetic and Technical Perspectives](https://mlsanity.com/paper/2211.04894/) (2022)
- [Meta Audiobox Aesthetics: Unified Automatic Quality Assessment for Speech, Music, and Sound](https://mlsanity.com/paper/2502.05139/) (2025)
- [Generalization Ability of MOS Prediction Networks](https://mlsanity.com/paper/2110.02635/) (2021)
- [Domain Adversarial Training for Accented Speech Recognition](https://mlsanity.com/paper/1806.02786/) (2018)
- [Deep Learning-based Non-Intrusive Multi-Objective Speech Assessment Model with Cross-Domain Features](https://mlsanity.com/paper/2111.02363/) (2021)
- [Domain Adversarial for Acoustic Emotion Recognition](https://mlsanity.com/paper/1804.07690/) (2018)
- [PAM: Prompting Audio-Language Models for Audio Quality Assessment](https://mlsanity.com/paper/2402.00282/) (2024)
- [Disentangling Voice and Content with Self-Supervision for Speaker Recognition](https://mlsanity.com/paper/2310.01128/) (2023)
- [The AudioMOS Challenge 2025](https://mlsanity.com/paper/2509.01336/) (2025)
- [The Efficacy of Self-Supervised Speech Models for Audio Representations](https://mlsanity.com/paper/2209.12900/) (2022)
- [QAMRO: Quality-aware Adaptive Margin Ranking Optimization for Human-aligned Assessment of Audio Generation Systems](https://mlsanity.com/paper/2508.08957/) (2025)
- [Multivariate Probabilistic Assessment of Speech Quality](https://mlsanity.com/paper/2506.04890/) (2025)
- [DRASP: A Dual-Resolution Attentive Statistics Pooling Framework for Automatic MOS Prediction](https://mlsanity.com/paper/2508.21407/) (2025)
- [Improving Perceptual Audio Aesthetic Assessment via Triplet Loss and Self-Supervised Embeddings](https://mlsanity.com/paper/2509.03292/) (2025)

## Abstract (arXiv)

The rapid proliferation of AI-Generated Content (AIGC) has necessitated robust metrics for perceptual quality assessment. However, automatic Mean Opinion Score (MOS) prediction models are often compromised by data scarcity, predisposing them to learn spurious correlations-- such as dataset-specific acoustic signatures-- rather than generalized quality features. To address this, we leverage domain adversarial training (DAT) to disentangle true quality perception from these nuisance factors. Unlike prior works that rely on static domain priors, we systematically investigate domain definition strategies ranging from explicit metadata-driven labels to implicit data-driven clusters. Our findings reveal that there is no "one-size-fits-all" domain definition; instead, the optimal strategy is highly dependent on the specific MOS aspect being evaluated. Experimental results demonstrate that our aspect-specific domain strategy effectively mitigates acoustic biases, significantly improving correlation with human ratings and achieving superior generalization on unseen generative scenarios.