GENERAL ENQUIRIES: Tel: + 27 12 841 2911 | Email: callcentre@csir.co.za

Show simple item record

dc.contributor.author Martirosian, O
dc.contributor.author Barnard, E
dc.date.accessioned 2008-01-24T13:56:13Z
dc.date.available 2008-01-24T13:56:13Z
dc.date.issued 2007-11
dc.identifier.citation Martirosian, O and Barnard, E. 2007. Speech-based emotion detection in a resource-scarce environment. 18th Annual Symposium of the Pattern Recognition Association of South Africa (PRASA), Pietermaritzburg, Kwazulu-Natal, South Africa, 28-30 November 2007, pp 5 en
dc.identifier.isbn 978-1-86840-656-2
dc.identifier.uri http://hdl.handle.net/10204/1975
dc.identifier.uri http://search.sabinet.co.za/WebZ/images/ejour/comp/comp_v40_a5.pdf:sessionid=0:bad=http://search.sabinet.co.za/ejour/ejour_badsearch.html:portal=ejournal:
dc.description 2007: PRASA en
dc.description This paper is published in the South African Computer Journal, Vol 40, pp 18-22
dc.description.abstract The authors explore the construction of a system to classify the dominant emotion in spoken utterances, in an environment where resources such as labelled utterances are scarce. The research addresses two issues relevant to detecting emotion in speech: (a) compensating for the lack of resources and (b) finding features of speech which best characterise emotional expression in the cultural environment being studied (South African telephone speech). Emotional speech was divided into three classes: active, neutral and passive emotion. An emotional speech corpus was created by naive annotators using recordings of telephone speech from a customer service call centre. Features were extracted from the emotional speech samples and the most suitable features selected by sequential forward selection (SFS). A consistency check was performed to compensate for the lack of experienced annotators and emotional speech samples. The classification accuracy achieved is 76.9%, with 95% classification accuracy for active emotion en
dc.language.iso en en
dc.publisher 18th Annual Symposium of the Pattern Recognition Association of South Africa (PRASA) en
dc.subject Emotion recognition en
dc.subject Resource creation en
dc.subject Cultural factors en
dc.subject SFS en
dc.subject Sequential forward selection en
dc.title Speech-based emotion detection in a resource-scarce environment en
dc.type Presentation en


Files in this item

This item appears in the following Collection(s)

Show simple item record

Search ResearchSpace


Advanced Search

Browse

My Account