Title :
Detection of depression in adolescents based on statistical modeling of emotional influences in parent-adolescent conversations
Author :
Stolar, Melissa N. ; Lech, Margaret ; Allen, Nicholas B.
Author_Institution :
Sch. of Electr. & Comput. Eng., RMIT Univ., Melbourne, VIC, Australia
Abstract :
The current benchmark speech-based depression detection techniques rely on acoustic speech parameters collected from large sets of representative speech recordings. This study for the first time investigates depression detection based on the higher order influence model (HOIM) coefficients and emotional transition parameters derived from a relatively small set of conversational speech recordings representing 63 different parent-adolescent conversations of time duration 20 minutes each. The adolescents included 29 (24 female and 5 male) individuals diagnosed with major depressive disorder and 34 (24 female and 8 male) healthy individuals. The mental state of parents was not assessed. The model-based depression diagnosis was compared with benchmark techniques based on acoustic speech parameters (mel frequency cepstral coefficients (MFCC) and Teager energy operator (TEO)). The classification into depressed on non-depressed categories was performed using the Gaussian Mixture Model (GMM) for the acoustic parameters and the support vector machine (SVM) for the HOIM features. The model based technique led to the highest average classification accuracy of 94% of for the HOIM of order 4, whereas the best benchmark techniques scored 70% for the optimized MFCCs and 71% for the optimized TEO features.
Keywords :
Gaussian processes; acoustic signal detection; emotion recognition; medical disorders; mixture models; optimisation; signal classification; speech processing; statistical analysis; support vector machines; GMM; Gaussian mixture model; HOIM coefficient; MFCC optimisation; SVM; TEO feature optimisation; acoustic parameters; acoustic speech parameter; conversational speech recording; depressed category classification; emotional influence; emotional transition parameter; higher order influence model; model based technique; nondepressed category classification; parent-adolescent conversation; representative speech recording; speech-based depression detection technique; statistical modeling; support vector machine; Accuracy; Conferences; Feature extraction; Mel frequency cepstral coefficient; Speech; Speech processing; Depression diagnosis; conversation modeling; emotional influence model; speech classification;
Conference_Titel :
Acoustics, Speech and Signal Processing (ICASSP), 2015 IEEE International Conference on
Conference_Location :
South Brisbane, QLD
DOI :
10.1109/ICASSP.2015.7178117