Psychoacoustically inspired optimization framework for neural binaural synthesis
The Journal of the Acoustical Society of America · 01.08.2026 · 160 (2) · 1521-1534
DOI: 10.1121/10.0044589 ↗Kurz gefasst
Fachartikel in der Zeitschrift The Journal of the Acoustical Society of America, online erschienen am 14.08.2026. Verfasst von Xikun Lu und 4 weiteren Autor:innen. Beteiligte Einrichtung: Shanghai Institute of Artificial Intelligence for Education, East China Normal University, Shanghai, China. Hauptthemen laut MEDLINE: Sound Localization, Psychoacoustics, Auditory Perception, Models, Neurological. Die Arbeit nennt 39 Literaturangaben. Gefördert von: interdisciplinary talent training special fund for AI empowering psychology/education at East China Normal University.
Abstract (Originalsprache)
Neural binaural synthesis is a promising technique for immersive audio reproduction. However, current methods rely on signal-oriented optimization objectives that treat all time-frequency regions uniformly. This approach conflicts with the selective nature of human auditory perception, as it may overemphasize perceptually masked or sub-threshold components, resulting in audible artifacts in reverberant sound fields. To address this, a perceptual optimization framework inspired by human spatial hearing is introduced. It includes a coherence-gated spatial loss that uses interaural coherence to weight spatial cues according to their reliability. By reducing the contribution of low-coherence regions associated with diffuse reverberation, this mechanism forces the model to prioritize the reconstruction of direct sound and early reflections critical for localization. A multi-scale wavelet loss is also incorporated to measure reconstruction errors across multiple wavelet decomposition levels, addressing the fixed resolution trade-off of the short-time Fourier transform and helping preserve fine-grained temporal transients. The framework was validated on three distinct backbone architectures. Extensive objective evaluations and subjective listening tests under non-head-tracked binaural playback show consistent improvements over state-of-the-art baselines, demonstrating its effectiveness as a model-agnostic training strategy for improving both signal fidelity and spatial accuracy.
Schlagwörter
MeSH-Schlagwörter (MEDLINE)
Autor:innen und Institutionen
- Shanghai Institute of Artificial Intelligence for Education, East China Normal University, Shanghai, China.
- School of Computer Science and Technology, East China Normal University, Shanghai, China.
ORCID-Profile: Xikun Lu, Jinqiu Sang
Förderung
- interdisciplinary talent training special fund for AI empowering psychology/education at East China Normal University
Zitieren
APA
Lu, X., Liu, F., Xie, X., Na, R., & Sang, J. (2026). Psychoacoustically inspired optimization framework for neural binaural synthesis. The Journal of the Acoustical Society of America, 160(2), 1521-1534. https://doi.org/10.1121/10.0044589
Vancouver
Lu X, Liu F, Xie X, Na R, Sang J. Psychoacoustically inspired optimization framework for neural binaural synthesis. The Journal of the Acoustical Society of America. 2026;160(2):1521-1534. doi:10.1121/10.0044589
BibTeX
@article{Lu2026,
author = {Lu, Xikun and Liu, Fang and Xie, Xinni and Na, Ruohan and Sang, Jinqiu},
title = {Psychoacoustically inspired optimization framework for neural binaural synthesis},
journal = {The Journal of the Acoustical Society of America},
year = {2026},
volume = {160},
number = {2},
pages = {1521--1534},
doi = {10.1121/10.0044589}
}
EUVIMED