Learning Acoustic Biomarkers in Depression Speech Using a Fractional Kolmogorov–Arnold Network
Fractal and Fractional · 11.07.2026 · 10 (7) · 469
DOI: 10.3390/fractalfract10070469 ↗Kurz gefasst
Fachartikel in der Zeitschrift Fractal and Fractional, online erschienen am 11.07.2026. Verfasst von Junkang Yang und 2 weiteren Autor:innen. Die Arbeit nennt 37 Literaturangaben. Der Volltext ist frei zugänglich (Open Access, CC BY 4.0).
Themen: Depression
Abstract (Originalsprache)
Speech-based depression detection provides a non-invasive and low-cost approach for supporting mental health screening. However, existing deep models often learn acoustic representations through fixed nonlinear transformations, which limits their ability to characterise gradual, nonlocal, and depression-related time–frequency variations in speech. To address this issue, this paper proposes a Fractional Kolmogorov–Arnold Network (FKAN) for learning acoustic biomarkers from mel-spectrograms. The proposed FKAN introduces fractional coordinate encoding to describe non-integer-order temporal–frequency responses, fractional-gated RBF-KAN blocks to learn adaptive edge-wise functional mappings, and a prototype-based classifier to construct a depression-related acoustic state space. In this way, the model not only improves classification performance but also provides functional and geometric evidence for interpreting acoustic biomarkers. Experiments on two public depression speech datasets demonstrate the effectiveness of the proposed method. The FKAN achieves an accuracy of 0.95 and an average F1-score of 0.94 on DAIC-WOZ, and an accuracy of 0.94 and an average F1-score of 0.94 on MODMA. Ablation studies, parameter sensitivity analysis, cross-dataset evaluation, and visualisation results further confirm that the fractional components and prototype-based state representation contribute to both robust depression detection and interpretable acoustic pattern analysis.
Zitieren
APA
Yang, J., Lu, Y., & Zhang, Y. (2026). Learning Acoustic Biomarkers in Depression Speech Using a Fractional Kolmogorov–Arnold Network. Fractal and Fractional, 10(7), 469. https://doi.org/10.3390/fractalfract10070469
Vancouver
Yang J, Lu Y, Zhang Y. Learning Acoustic Biomarkers in Depression Speech Using a Fractional Kolmogorov–Arnold Network. Fractal and Fractional. 2026;10(7):469. doi:10.3390/fractalfract10070469
BibTeX
@article{Yang2026,
author = {Yang, Junkang and Lu, Yuchen and Zhang, Yuxuan},
title = {Learning Acoustic Biomarkers in Depression Speech Using a Fractional Kolmogorov–Arnold Network},
journal = {Fractal and Fractional},
year = {2026},
volume = {10},
number = {7},
pages = {469},
doi = {10.3390/fractalfract10070469}
}
EUVIMED