Automatic detection of depressive states from speech

Mendiratta, A., Scibelli, F., Esposito, A. M., Capuano, V., Likforman-Sulem, L., Maldonato, M. N., Vinciarelli, A. and Esposito, A. (2018) Automatic detection of depressive states from speech. In: Esposito, A., Faudez-Zanuy, M., Carlo Morabito, F. and Pasero, E. (eds.) Multidisciplinary Approaches to Neural Computing. Series: Smart innovation, systems, and technologies, 69 (69). Springer: Cham, pp. 301-314. ISBN 9783319569031 (doi:10.1007/978-3-319-56904-8_29)

Full text not currently available from Enlighten.

Abstract

This paper investigates the acoustical and perceptual speech features that differentiate a depressed individual from a healthy one. The speech data gathered was a collection from both healthy and depressed subjects in the Italian language, each comprising of a read and spontaneous narrative. The pre-processing of this dataset was done using Mel Frequency Cepstral Coefficient (MFCC). The speech samples were further processed using Principal Component Analysis (PCA) for correlation and dimensionality reduction. It was found that both groups differed with respect to the extracted speech features. To distinguish the depressed group from the healthy one on the basis the proposed speech processing algorithm the Self Organizing Map (SOM) algorithm was used. The clustering accuracy given by SOM’s was 80.67%.

Item Type:Book Sections
Status:Published
Glasgow Author(s) Enlighten ID:Vinciarelli, Professor Alessandro
Authors: Mendiratta, A., Scibelli, F., Esposito, A. M., Capuano, V., Likforman-Sulem, L., Maldonato, M. N., Vinciarelli, A., and Esposito, A.
College/School:College of Science and Engineering > School of Computing Science
Publisher:Springer
ISSN:2190-3018
ISBN:9783319569031
Published Online:30 August 2017

University Staff: Request a correction | Enlighten Editors: Update this record