From Joyous to Clinically Depressed: Mood Detection Using Spontaneous Speech

Sharifa Alghowinem, Roland Goecke, Michael Wagner, Julien Epps, Michael Breakspear, Gordon Parker

    Research output: A Conference proceeding or a Chapter in BookConference contributionpeer-review

    72 Citations (Scopus)

    Abstract

    Depression and other mood disorders are common and disabling disorders. We present work towards an objective diagnostic aid supporting clinicians using affective sensing technology with a focus on acoustic and statistical features from spontaneous speech. This work investigates differences in expressing positive and negative emotions in depressed and healthy control subjects as well as whether initial gender classification increases the recognition rate. To this end, spontaneous speech from interviews of 30 subjects of each depressed and controls was analysed, with a focus on questions eliciting positive and negative emotions. Using HMMs with GMMs for classification with 30-fold cross-validation, we found that MFCC, energy and intensity features gave highest recognition rates when female and male subjects were analysed together. When the dataset was first split by gender, log energy and shimmer features, respectively, were found to give the highest recognition rates in females, while it was loudness for males. Overall, correct recognition rates from acoustic features for depressed female subjects were higher than for male subjects. Using temporal features, we found that the response time and average syllable duration were longer in depressed subjects, while the interaction involvement and articulation rate wesre higher in control subjects.
    Original languageEnglish
    Title of host publicationProceedings of the Twenty-Fifth International Florida Artificial Intelligence Research Society Conference
    EditorsG.M Youngblood, P.M McCarthy
    Place of PublicationFlorida
    PublisherAAAI Press
    Pages141-146
    Number of pages6
    ISBN (Electronic)9781577355595
    ISBN (Print)9781577355588
    Publication statusPublished - 2012
    EventInternational Florida Artificial Intelligence Research Society Conference (FLAIRS 2012) - Marco Island, Marco Island, United States
    Duration: 23 May 201225 May 2012
    http://projects.ict.usc.edu/flairs-25/

    Conference

    ConferenceInternational Florida Artificial Intelligence Research Society Conference (FLAIRS 2012)
    Abbreviated titleFLAIRS 2012
    Country/TerritoryUnited States
    CityMarco Island
    Period23/05/1225/05/12
    Internet address

    Fingerprint

    Dive into the research topics of 'From Joyous to Clinically Depressed: Mood Detection Using Spontaneous Speech'. Together they form a unique fingerprint.

    Cite this