Author/Authors :
Jiang, Haihua Faculty of Information Technology - Beijing University of Technology - Beijing, China , Hu, Bin Faculty of Information Technology - Beijing University of Technology - Beijing, China , Liu, Zhenyu School of Information Science and Engineering - Lanzhou University - Lanzhou, China , Wang, Gang Beijing Anding Hospital of Capital Medical University - Beijing, China , Zhang, Lan Lanzhou University Second Hospital - Lanzhou, China , Li, Xiaoyu School of Information Science and Engineering - Lanzhou University - Lanzhou, China , Kang, Huanyu School of Information Science and Engineering - Lanzhou University - Lanzhou, China
Abstract :
Early intervention for depression is very important to ease the disease burden, but current diagnostic methods are still limited.
(is study investigated automatic depressed speech classification in a sample of 170 native Chinese subjects (85 healthy controls
and 85 depressed patients). (e classification performances of prosodic, spectral, and glottal speech features were analyzed in
recognition of depression. We proposed an ensemble logistic regression model for detecting depression (ELRDD) in speech. (e
logistic regression, which was superior in recognition of depression, was selected as the base classifier. (is ensemble model
extracted many speech features from different aspects and ensured diversity of the base classifier. ELRDD provided better
classification results than the other compared classifiers. A technique for identifying depression based on ELRDD, ELRDD-E, was
here suggested and tested. It offered encouraging outcomes, revealing a high accuracy level of 75.00% for females and 81.82% for
males, as well as an advantageous sensitivity/specificity ratio of 79.25%/70.59% for females and 78.13%/85.29% for males.
