Modeling Spectral Variability for the Classification of Depressed Speech

Nicholas Cummins, Julien Epps, Vidhyasaharan Sethu, Michael Breakspear, Roland GOECKE

Research output: A Conference proceeding or a Chapter in BookConference contribution

29 Citations (Scopus)
2 Downloads (Pure)

Abstract

Quantifying how the spectral content of speech relates to changes in mental state may be crucial in building an objective speech-based depression classification system with clinical utility. This paper investigates the hypothesis that important depression based information can be captured within the covariance structure of a Gaussian Mixture Model (GMM) of recorded speech. Significant negative correlations found between a speaker’s average weighted variance - a GMM-based indicator of speaker variability - and their level of depression support this hypothesis. Further evidence is provided by the comparison of classification accuracies from seven different GMM-UBM systems, each formed by varying different parameter combinations during MAP adaption. This analysis shows that variance-only adaptation either outperforms or matches the de facto standard mean-only adaptation when classifying both the presence and severity of depression. This result is perhaps the first of its kind seen in GMM-UBM speech classification.
Original languageEnglish
Title of host publication14th Annual Conference of the International Speech Communication Association (INTERSPEECH 2013): Speech in Life Sciences and Human Societies
EditorsFrederic Bimbot, Cecile Fougeron, Francois Pellegrino
Place of PublicationLyon, France
PublisherInternational Speech Communication Association
Pages857-861
Number of pages5
Volume2
ISBN (Print)9781629934433
Publication statusPublished - 2013
Event14th Annual Conference of the International Speech Communication Association Interspeech 2013 - Lyon, Lyon, France
Duration: 25 Aug 201329 Aug 2013

Conference

Conference14th Annual Conference of the International Speech Communication Association Interspeech 2013
Abbreviated titleINTERSPEECH 2013
CountryFrance
CityLyon
Period25/08/1329/08/13

Fingerprint Dive into the research topics of 'Modeling Spectral Variability for the Classification of Depressed Speech'. Together they form a unique fingerprint.

  • Cite this

    Cummins, N., Epps, J., Sethu, V., Breakspear, M., & GOECKE, R. (2013). Modeling Spectral Variability for the Classification of Depressed Speech. In F. Bimbot, C. Fougeron, & F. Pellegrino (Eds.), 14th Annual Conference of the International Speech Communication Association (INTERSPEECH 2013): Speech in Life Sciences and Human Societies (Vol. 2, pp. 857-861). International Speech Communication Association. http://www.isca-speech.org/archive/archive_papers/interspeech_2013/i13_0857.pdf