Depression markers in speech: An approach based on tract variables dynamics

2026/07/01 by Sahar Altalhi, Tanaya Guha, Alessandro Vinciarelli
Computer Science · Engineering · Medicine · Psychology · #Emotion and Mood Recognition #Mental Health via Writing #Voice and Speech Disorders #cs.AI #eess.AS

paper · pdf · doi:10.1121/10.0044193

openalex publication_date 2026/07/01 · openalex created_date 2026/07/03 · openalex updated_date 2026/07/07

Abstract

This study identifies new depression biomarkers based on the dynamical properties of tract variables, which represent geometric features describing the configuration of the speech articulators. A key advantage of this approach lies in its ability to quantify aspects of the articulatory process that have not been previously explored in the context of depression, namely, predictability, complexity, and randomness. These properties are respectively characterised using the Largest Lyapunov Exponent, the Correlation Dimension, and the Sample Entropy. Thorough experiments were conducted on the Androids Corpus, a publicly available dataset comprising 64 speakers diagnosed with depression by clinicians and 54 control speakers with no reported history of mental health conditions. The results indicate that the proposed biomarkers effectively discriminate between the depressed and control speakers, as evidenced by the high Cliff's delta values across both read and spontaneous speech.

Citations

• Improving Speech Inversion Through Self-Supervised Embeddings and Enhanced Tract Variables
• Explainable Depression Detection via Head Motion Patterns
• WhisperX: Time-Accurate Speech Transcription of Long-Form Audio
• Selecting embedding delays: An overview of embedding techniques and a new method using persistent homology
• Audio Data Augmentation for Acoustic-to-articulatory Speech Inversion using Bidirectional Gated RNNs
• Physiological time-series analysis using approximate entropy and sample entropy
• Practical method for determining the minimum embedding dimension of a scalar time series
• A practical method for calculating largest Lyapunov exponents from small data sets
• Independent coordinates for strange attractors from mutual information

Related

• The Relationship Between Speech Features Changes When You Get Depressed: Feature Correlations for Improving Speed and Performance of Depression Detection
• Cost-effective Models for Detecting Depression from Speech
• Speech and the n-Back task as a lens into depression. How combining both may allow us to isolate different core symptoms of depression
• Robust and Explainable Depression Identification from Speech Using Vowel-Based Ensemble Learning Approaches
• Detecting the Severity of Major Depressive Disorder from Speech: A Novel HARD-Training Methodology