Evaluation of wavelet measures on automatic detection of emotion in noisy and telephony speech signals

Vista sencilla de ítem
dc.contributor.authorVasquez-Correa, J. C.
dc.contributor.authorGarcia, N.
dc.contributor.authorVargas-Bonilla, J. F.
dc.contributor.authorOrozco-Arroyave, J. R.
dc.contributor.authorArias-Londono, J. D.
dc.contributor.authorLucia Quintero M, O.
dc.contributor.departmentUniversidad EAFIT. Departamento de Cienciasspa
dc.contributor.researchgroupModelado Matemáticospa
dc.creatorVasquez-Correa, J. C.
dc.creatorGarcia, N.
dc.creatorVargas-Bonilla, J. F.
dc.creatorOrozco-Arroyave, J. R.
dc.creatorArias-Londono, J. D.
dc.creatorLucia Quintero M, O.
dc.date.accessioned2021-04-12T14:11:46Z
dc.date.available2021-04-12T14:11:46Z
dc.date.issued2014-01-01
dc.description.abstractDetection of emotion in humans from speech signals is a recent research field. One of the scenarios where this field has been applied is in situations where the human integrity and security are at risk. In this paper we are propossing a set of features based on the Teager energy operator, and several entropy measures obtained from the decomposition signals from discrete wavelet transform to characterize different types of negative emotions such as anger, anxiety, disgust, and desperation. The features are measured in three different conditions: (1) the original speech signals, (2) the signals that are contaminated with noise, or are affected by the presence of a phone channel, and (3) the signals that are obtained after processing using an algorithm for Speech Enhancement based on Karhunen-Love Transform. According to the results, when the speech enhancement is applied, the detection of emotion in speech is increased in up to 22% compared to results obtained when the speech signal is highly contaminated with noise. © 2014 IEEE.eng
dc.identifierhttps://eafit.fundanetsuite.com/Publicaciones/ProdCientif/PublicacionFrw.aspx?id=2210
dc.identifier.doi10.1109/CCST.2014.6986981
dc.identifier.issn10716572
dc.identifier.otherWOS;000369865000015
dc.identifier.otherSCOPUS;2-s2.0-84931080053
dc.identifier.urihttp://hdl.handle.net/10784/27883
dc.language.isoengeng
dc.publisherIEEE
dc.relation.urihttps://www.scopus.com/inward/record.uri?eid=2-s2.0-84931080053&doi=10.1109%2fCCST.2014.6986981&partnerID=40&md5=dd7a7b1229b364613c7fa3cae6b07047
dc.rightsIEEE
dc.sourceInternational Carnahan Conference On Security Technology Proceedings
dc.subject.keywordDiscrete wavelet transformseng
dc.subject.keywordRisk perceptioneng
dc.subject.keywordSignal detectioneng
dc.subject.keywordSignal processingeng
dc.subject.keywordSpeecheng
dc.subject.keywordSpeech communicationeng
dc.subject.keywordSpeech enhancementeng
dc.subject.keywordSpeech processingeng
dc.subject.keywordTelephone setseng
dc.subject.keywordWavelet decompositioneng
dc.subject.keywordWavelet transformseng
dc.subject.keywordAutomatic detection of emotioneng
dc.subject.keywordEntropy measureeng
dc.subject.keywordHuman integrityeng
dc.subject.keywordKarhunen-Love transformeng
dc.subject.keywordRecent researcheseng
dc.subject.keywordSpeech emotion recognitioneng
dc.subject.keywordTeager energy operatorseng
dc.subject.keywordTelephone speecheng
dc.subject.keywordSpeech recognitioneng
dc.titleEvaluation of wavelet measures on automatic detection of emotion in noisy and telephony speech signalseng
dc.typeinfo:eu-repo/semantics/conferencePapereng
dc.typeconferencePapereng
dc.typeinfo:eu-repo/semantics/publishedVersioneng
dc.typepublishedVersioneng
dc.type.localDocumento de conferenciaspa

Archivos

Colecciones

Documentos de conferencia