Academic Journal
Psychoacoustically inspired optimization framework for neural binaural synthesis.
| Τίτλος: | Psychoacoustically inspired optimization framework for neural binaural synthesis. |
|---|---|
| Συγγραφείς: | Lu X; Shanghai Institute of Artificial Intelligence for Education, East China Normal University, Shanghai, China., Liu F; School of Computer Science and Technology, East China Normal University, Shanghai, China., Xie X; School of Computer Science and Technology, East China Normal University, Shanghai, China., Na R; School of Computer Science and Technology, East China Normal University, Shanghai, China., Sang J; School of Computer Science and Technology, East China Normal University, Shanghai, China. |
| Πηγή: | The Journal of the Acoustical Society of America [J Acoust Soc Am] 2026 Aug 01; Vol. 160 (2), pp. 1521-1534. |
| Τύπος έκδοσης: | Journal Article |
| Γλώσσα: | English |
| Στοιχεία περιοδικού: | Publisher: American Institute of Physics Country of Publication: United States NLM ID: 7503051 Publication Model: Print Cited Medium: Internet ISSN: 1520-8524 (Electronic) Linking ISSN: 00014966 NLM ISO Abbreviation: J Acoust Soc Am Subsets: MEDLINE |
| Imprint Name(s): | Publication: Melville, NY : American Institute of Physics Original Publication: Lancaster, Pa. [etc.] : American Institute of Physics for the Acoustical Society of America |
| Ιατρικοί όροι (MeSH): | Sound Localization*/physiology , Psychoacoustics* , Auditory Perception* , Models, Neurological*, Auditory Pathways/physiology ; Humans ; Cues ; Acoustic Stimulation ; Wavelet Analysis ; Fourier Analysis ; Perceptual Masking ; Signal Processing, Computer-Assisted ; Time Factors |
| Περίληψη: | 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. (© 2026 Acoustical Society of America.) |
| Entry Date(s): | Date Created: 20260814 Date Completed: 20260814 Latest Revision: 20260814 |
| Update Code: | 20260814 |
| DOI: | 10.1121/10.0044589 |
| PMID: | 42599064 |
| Βάση Δεδομένων: | MEDLINE |
| ISSN: | 1520-8524 |
|---|---|
| DOI: | 10.1121/10.0044589 |