Show simple item record

dc.contributor.authorBozkurt, E.
dc.contributor.authorErzin, E.
dc.contributor.authorEroğlu Erdem, Ç.
dc.contributor.authorErdem, Tanju
dc.date.accessioned2012-08-15T13:27:18Z
dc.date.available2012-08-15T13:27:18Z
dc.date.issued2011
dc.identifier.issn0092-2102
dc.identifier.urihttp://hdl.handle.net/10679/235
dc.identifier.urihttp://www.sciencedirect.com/science/article/pii/S0167639311000641
dc.description.abstractIn this paper, we propose novel spectrally weighted mel-frequency cepstral coefficient (WMFCC) features for emotion recognition from speech. The idea is based on the fact that formant locations carry emotion-related information, and therefore critical spectral bands around formant locations can be emphasized during the calculation of MFCC features. The spectral weighting is derived from the normalized inverse harmonic mean function of the line spectral frequency (LSF) features, which are known to be localized around formant frequencies. The above approach can be considered as an early data fusion of spectral content and formant location information. We also investigate methods for late decision fusion of unimodal classifiers. We evaluate the proposed WMFCC features together with the standard spectral and prosody features using HMM based classifiers on the spontaneous FAU Aibo emotional speech corpus. The results show that unimodal classifiers with the WMFCC features perform significantly better than the classifiers with standard spectral features. Late decision fusion of classifiers provide further significant performance improvements.en_US
dc.description.sponsorshipTÜBİTAK
dc.language.isoengen_US
dc.publisherElsevieren_US
dc.relationinfo:turkey/grantAgreement/TUBITAK/106E201en_US
dc.relationinfo:turkey/grantAgreement/TUBITAK/110E056en_US
dc.relation.ispartofSpeech Communication
dc.rightsrestrictedAccess
dc.titleFormant position based weighted spectral features for emotion recognitionen_US
dc.typeArticleen_US
dc.peerreviewedyesen_US
dc.publicationstatuspublisheden_US
dc.contributor.departmentÖzyeğin University
dc.contributor.authorID45777
dc.contributor.authorID0000-0002-8841-1642
dc.contributor.ozuauthorErdem, Tanju
dc.identifier.volume53
dc.identifier.issue9-10
dc.identifier.startpage1186
dc.identifier.endpage1197
dc.identifier.wosWOS:000294104000010
dc.identifier.doi10.1016/j.specom.2011.04.003
dc.subject.keywordsEmotion recognitionen_US
dc.subject.keywordsEmotional speech classificationen_US
dc.subject.keywordsSpectral featuresen_US
dc.identifier.scopusSCOPUS:2-s2.0-79960848203


Files in this item

FilesSizeFormatView

There are no files associated with this item.

This item appears in the following Collection(s)

Show simple item record


Share this page