EUVIMEDEUVIMED entdecken
Crossref

Acoustics of depression

Sri Harsha Dumpala, Katerina Dikaios, Ross Langley, Amy Lowery, Sageev Oore, Rudolf Uher

Journal of Affective Disorders · 2026-10 · 410 · 121958

DOI: 10.1016/j.jad.2026.121958 ↗

Kurz gefasst

Fachartikel in der Zeitschrift Journal of Affective Disorders, 2026-10. Verfasst von Sri Harsha Dumpala und 5 weiteren Autor:innen. Beteiligte Einrichtung: Nova Scotia Health Authority, Halifax, Nova Scotia, Canada; Dalhousie University, Department of Psychiatry, Halifax, Nova Scotia, Canada. Hauptthemen laut MEDLINE: Major Depressive Disorder, Speech Acoustics. Die Arbeit wurde bisher 2-mal zitiert (Crossref) und nennt 49 Literaturangaben. Gefördert von: Ontario Brain Institute, Janssen Canada, Canadian Institutes of Health Research.

AbstractSchlagwörterBibliografische AngabenZitierenVerwandte Studien

Abstract (Originalsprache)

BACKGROUND: The sound of speech reflects the speaker's mood in a way that may enable objective measurement of depression from speech audio recordings. As previous studies relied on volunteers without a diagnosis or selected subsets of acoustic features, it is unknown which acoustic features measure clinically relevant depression. METHODS: We examined a comprehensive set of 77 system, source, spectral, and prosodic features of speech in 239 adults, including 147 with major depressive disorder, who spoke following neutral, positive, and negative prompts. We randomly divided the participants into an analysis set of 176 and a test set of 63 individuals. In the training set, we quantified the relationships between acoustic features and depression severity on the Montgomery Åsberg Depression Rating Scale (MADRS). We built XGBoost machine learning models to differentiate depression severity levels (none, mild, moderate, severe) and validated them in the unseen test set. RESULTS: Multiple acoustic features discriminated depression severity levels with prosodic features contributing the most information. Speech energy velocity, intensity variation, voiced rate, pause duration (prosodic features) and the third formant variance (a system feature) predicted depression severity consistently across prompts. Intensity, energy, pause duration, and harmonic difference contributed the most to XGBoost models that discriminated severity levels in the test set. LIMITATIONS: The analysis is limited to speech in English. CONCLUSIONS: Acoustic, in particular prosodic, features can discriminate clinically relevant levels of depression among diagnosed patients. The robustness of these predictors across emotional contexts suggests a potential for application in a variety of settings.

Schlagwörter

MeSH-Schlagwörter (MEDLINE)

Major Depressive DisorderSpeech AcousticsHumansAdultFemaleMaleSeverity of Illness IndexBoosting Machine Learning AlgorithmsMiddle AgedMachine LearningPsychiatric Status Rating Scales

Stichwörter der Autor:innen

Acoustic features of speechDepressive symptom severityMachine learningMajor depressive disorderSpeech analysis

Autor:innen und Institutionen

  • Nova Scotia Health Authority, Halifax, Nova Scotia, Canada; Dalhousie University, Department of Psychiatry, Halifax, Nova Scotia, Canada.
  • McMaster University, Department of Psychiatry and Behavioural Neurosciences, Hamilton, Ontario, Canada.
  • Dalhousie University, Department of Psychiatry, Halifax, Nova Scotia, Canada.
  • Nova Scotia Health Authority, Halifax, Nova Scotia, Canada.
  • Dalhousie University, Faculty of Computer Science, Halifax, Nova Scotia, Canada.
  • Nova Scotia Health Authority, Halifax, Nova Scotia, Canada; Dalhousie University, Department of Psychiatry, Halifax, Nova Scotia, Canada. Electronic address: uher@dal.ca.

Förderung

  • Ontario Brain Institute
  • Janssen Canada
  • Canadian Institutes of Health Research

Zitieren

APA

Dumpala, S. H., Dikaios, K., Langley, R., Lowery, A., Oore, S., & Uher, R. (2026). Acoustics of depression. Journal of Affective Disorders, 410, 121958. https://doi.org/10.1016/j.jad.2026.121958

Vancouver

Dumpala SH, Dikaios K, Langley R, Lowery A, Oore S, Uher R. Acoustics of depression. Journal of Affective Disorders. 2026;410:121958. doi:10.1016/j.jad.2026.121958

BibTeX
@article{Dumpala2026,
  author = {Dumpala, Sri Harsha and Dikaios, Katerina and Langley, Ross and Lowery, Amy and Oore, Sageev and Uher, Rudolf},
  title = {Acoustics of depression},
  journal = {Journal of Affective Disorders},
  year = {2026},
  volume = {410},
  pages = {121958},
  doi = {10.1016/j.jad.2026.121958}
}
Kostenlos starten →