Using speech recognition technology to investigate the association between timing-related speech features and...

Area of Science:

• Psychiatry and Behavioral Sciences
• Computational Linguistics
• Biomarker Discovery

Background:

• Current depression severity assessment lacks reliable objective biomarkers.
• Timing-related speech features are being explored as potential objective measures.

Purpose of the Study:

• To investigate the association between depression severity and timing-related speech features.
• To determine if speech features can serve as objective biomarkers for depression.

Main Methods:

• Speech recognition technology was used to measure speech rate, pause time, and response time in individuals with major depressive disorder (MDD), bipolar disorder (BP), and healthy controls (HC).
• Depression severity was assessed using the Hamilton Depression Rating Scale (HAMD-17).
• Statistical analyses examined differences among groups and correlations between speech features and depression severity.

Main Results:

• Significant differences in speech features were observed among MDD, BP, and HC groups.
• Depressed patients exhibited slower speech rate, longer pause time, and longer response time compared to HC.
• All measured timing-related speech features were significantly associated with HAMD-17 scores, and changes in speech rate correlated with changes in depression severity.

Conclusions:

• Speech features, including slower speech rate, longer pause time, and longer response time, are indicative of psychomotor retardation in depressed individuals.
• Timing-related speech features show potential as objective biomarkers for assessing depression severity.