Speech-based Evaluation of Emotions-Depression Correlation

Cited by: 0

Access paper here

Abstract: Early detection of depression symptoms is fundamental to limit the onset of further associated behavioural disorders, such as psychomotor or social withdrawal. The combination of Artificial Intelligence and speech analysis revealed the existence of objectively measurable physical manifestations for early detection of depressive symptoms, constituting a valid support to evaluate these signals. To push forward the research state-of-art, this aim of this paper is to understand quantitative correlations between emotional states and depression by proposing a study across different datasets containing speech of both depressed/non-depressed people and emotional-related samples. The relationship between affective measures and depression can, in fact, a support to evaluate the presence of depression state. This work constitutes a preliminary step of a study whose final aim is to pursue AI-powered personalized medicine by building sophisticated Clinical Decision Support Systems for depression, as well as other psychological disorders. © 2022 IEEE.

Author Keywords: Clinical Decision Support Systems; Early Depression Detection; Emotional State Analysis; Non-verbal speech analysis; Support Vector Machine

Bibtex citation:

@CONFERENCE{Verde2022,
    author = "Verde, Laura and Campanile, Lelio and Marulli, Fiammetta and Marrone, Stefano",
    title = "Speech-based Evaluation of Emotions-Depression Correlation",
    year = "2022",
    journal = "Proceedings of the 2022 IEEE International Conference on Dependable, Autonomic and Secure Computing, International Conference on Pervasive Intelligence and Computing, International Conference on Cloud and Big Data Computing, International Conference on Cyber Science and Technology Congress, DASC/PiCom/CBDCom/CyberSciTech 2022",
    doi = "10.1109/DASC/PiCom/CBDCom/Cy55231.2022.9927758",
    type = "Conference paper"
}

Download .bib file