Perceptual Modeling of Binaural vs. Stereo Music Mixes: A Pairwise Differential Approach with Dimension-wise Attention

Liang J, Wang Y, Zhang H, Li H, Hou Y. Perceptual Modeling of Binaural vs. Stereo Music Mixes: A Pairwise Differential Approach with Dimension-wise Attention. In: AVARIG 2026: Audio for Virtual and Augmented Reality and Immersive Games. Audio Engineering Society; 2026.pp. 10321:1-9. Available from: https://aes.org/publications/elibrary-page/?id=23283

@inproceedings{Liang2026_23283,
  author = {Liang, Jiarui and Wang, Yizhen and Zhang, Haitian and Li, Huanhe and Hou, Yizhen},
  title = {{Perceptual Modeling of Binaural vs. Stereo Music Mixes: A Pairwise Differential Approach with Dimension-wise Attention}},
  booktitle = {AVARIG 2026: Audio for Virtual and Augmented Reality and Immersive Games},
  pages = {10321:1-9},
  year = {2026},
  month = jun,
  publisher = {Audio Engineering Society},
  url = {}
}

TY  - CPAPER
TI  - Perceptual Modeling of Binaural vs. Stereo Music Mixes: A Pairwise Differential Approach with Dimension-wise Attention
AU  - Liang, Jiarui
AU  - Wang, Yizhen
AU  - Zhang, Haitian
AU  - Li, Huanhe
AU  - Hou, Yizhen
T2  - AVARIG 2026: Audio for Virtual and Augmented Reality and Immersive Games
SP  - 1
EP  - 9
M1  - Paper 10321
PY  - 2026
DA  - 2026/06/30
UR  - https://aes.org/publications/elibrary-page/?id=23283
PB  - Audio Engineering Society
LA  - en
AB  - Evaluating binaural rendering against stereo mixes is frequently confounded by "content bias," where listeners' inherent musical preferences obscure spatial quality assessments. To address this, we propose an interpretable predictive model utilizing a pairwise differential approach (Strategy) and a dimension-wise attention neural network. The model achieves a competitive sign accuracy of 68.4%, outperforming traditional baselines. Crucially, the attention mechanism provides retrospective interpretability, revealing fundamental acoustic trade-offs in spatial upmixing: aggressive decorrelation for image widening compromises localization precision and timbral fullness, whereas successful externalization heavily depends on mid-side energy redistribution. This framework offers a robust evaluation tool for spatial algorithms and actionable psychoacoustic guidance for immersive audio production.
ER  -