Modeling Harmonic Structure and Spectral Complexity in Speech for the Analysis of Depression and Emotional Expression
Acta Acustica · 09.11.2026
DOI: 10.1051/aacus/2026121 ↗Kurz gefasst
Fachartikel in der Zeitschrift Acta Acustica, online erschienen am 09.11.2026. Verfasst von Junkang Yang und 4 weiteren Autor:innen. Gefördert von: JSPS KAKENHI.
Themen: Depression
Abstract (Originalsprache)
Major depressive disorder (MDD) is a common mental health condition that requires scalable and objective detection methods. Speech is a promising non-invasive digital biomarker, but many existing approaches rely on binary classification, lack interpretable acoustic modeling, and ignore demographic differences that affect speech patterns. This work proposes HEAR-Net, a unified speech-based framework for depression detection and emotion recognition that integrates acoustic features and demographic context. We propose a harmonic block to capture long-range harmonic patterns related to voice quality, a spectro-temporal orthogonal gating mechanism to model time and frequency information, and an entropy-aware pooling to reflect changes in expressive variability. We incorporate age and sex information to provide demographic context alongside acoustic features. Experiments on DAIC-WOZ and MODMA achieve average F1-scores of 0.93 and 0.92, with accuracies of 0.94 and 0.92, respectively. On CASIA and EmoDB, HEAR-Net reaches accuracies of 0.89 and 0.91 without external pre-trained models.
Förderung
- JSPS KAKENHI
Zitieren
APA
Yang, J., Nishizaki, H., Leow, C. S., Gan, L., & Liu, H. (2026). Modeling Harmonic Structure and Spectral Complexity in Speech for the Analysis of Depression and Emotional Expression. Acta Acustica. https://doi.org/10.1051/aacus/2026121
Vancouver
Yang J, Nishizaki H, Leow CS, Gan L, Liu H. Modeling Harmonic Structure and Spectral Complexity in Speech for the Analysis of Depression and Emotional Expression. Acta Acustica. 2026. doi:10.1051/aacus/2026121
BibTeX
@article{Yang2026,
author = {Yang, Junkang and Nishizaki, Hiromitsu and Leow, Chee Siang and Gan, Lu and Liu, Hongqing},
title = {Modeling Harmonic Structure and Spectral Complexity in Speech for the Analysis of Depression and Emotional Expression},
journal = {Acta Acustica},
year = {2026},
doi = {10.1051/aacus/2026121}
}
EUVIMED