# Multichannel Audio Quality Assessment: Extending Pretrained Perceptual Models to Spatial Audio

arXiv: https://arxiv.org/abs/2609.37116 · HTML: https://mlsanity.com/paper/2609.37116/

## Key facts

- No citing papers in the map yet (data through 14 Oct 2026).
- Builds on 6 of its 19 references that are in the map.
- First posted on arXiv 29 Sep 2026.

## Builds on (most cited first, 6 of 6)

- [ViSQOL v3: An Open Source Production Ready Objective Speech and Audio Metric](https://mlsanity.com/paper/2004.09584/) (2020)
- [Zimtohrli: An Efficient Psychoacoustic Audio Similarity Metric](https://mlsanity.com/paper/2509.26133/) (2025)
- [Generative Machine Listener](https://mlsanity.com/paper/2308.09493/) (2023)
- [Stereo InSE-NET: Stereo Audio Quality Predictor Transfer Learned from Mono InSE-NET](https://mlsanity.com/paper/2209.11666/) (2022)
- [Binamix -- A Python Library for Generating Binaural Audio Datasets](https://mlsanity.com/paper/2505.01369/) (2025)
- [Enhanced Generative Machine Listener](https://mlsanity.com/paper/2509.21463/) (2025)

## Abstract (arXiv)

Accurate perceptual quality assessment is essential for evaluating and optimizing spatial audio, where perceived quality depends on both signal fidelity and inter-channel spatial relationships. However, subjective evaluation is costly, while existing perceptual models are often trained for limited channel configurations and cannot be directly applied to higher-channel-count audio. This raises the question: how can pretrained perceptual knowledge be effectively reused for multichannel spatial audio? Using 5.1-channel audio, we study four levels of multichannel integration: signal, prediction, latent, and feature and propose two learned approaches: latent-level aggregation of spatial-group representations and the feature-level Feature-Band Group Attention (FGAtt), which adaptively fuses spatial groups at the feature level before perceptual processing. Across five 5.1-channel test sets, FGAtt achieves the strongest over- all performance, demonstrating the effectiveness of feature-level adaptation for reusing pretrained perceptual knowledge