Detecting Depression Using Voice Signal Extracted by Chatbots: A Feasibility Study

Alexandros Roniotis; Manolis Tsiknakis

Interactivity, Game Creation, Design, Learning, and Innovation. 6th International Conference, ArtsIT 2017, and Second International Conference, DLI 2017, Heraklion, Crete, Greece, October 30–31, 2017, Proceedings

Research Article

Detecting Depression Using Voice Signal Extracted by Chatbots: A Feasibility Study

Download

396 downloads

Cite: BibTeX Plain Text

@INPROCEEDINGS{10.1007/978-3-319-76908-0_37,
    author={Alexandros Roniotis and Manolis Tsiknakis},
    title={Detecting Depression Using Voice Signal Extracted by Chatbots: A Feasibility Study},
    proceedings={Interactivity, Game Creation, Design, Learning, and Innovation. 6th International Conference, ArtsIT 2017, and Second International Conference, DLI 2017, Heraklion, Crete, Greece, October 30--31, 2017, Proceedings},
    proceedings_a={ARTSIT \& DLI},
    year={2018},
    month={3},
    keywords={Virtual coach Cancer Detecting depression Machine learning MFCCs},
    doi={10.1007/978-3-319-76908-0_37}
}

Alexandros Roniotis
Manolis Tsiknakis
Year: 2018
Detecting Depression Using Voice Signal Extracted by Chatbots: A Feasibility Study
ARTSIT & DLI
Springer
DOI: 10.1007/978-3-319-76908-0_37

Alexandros Roniotis¹^,*, Manolis Tsiknakis¹^,*

1: Technological Educational Institute of Crete

*Contact email: alexandros.roniotis@gmail.com, tsiknaki@staff.teicrete.gr

Abstract

This work aims at proposing a novel framework for detecting depression, like commonly met in cancer patients, using prosodic and statistical features extracted by voice signal. This work presents the first results of extracting these features on test and training sets extracted from the AVEC2016 dataset using MATLAB. The results indicate that voice can be used for extracting depression indicators and developing a mobile application for integrating this new knowledge could be the next step.

Keywords: Virtual coach Cancer Detecting depression Machine learning MFCCs

Published: 2018-03-08
Appears in: SpringerLink

: http://dx.doi.org/10.1007/978-3-319-76908-0_37