A simple but efficient voice activity detection algorithm through Hilbert transform and dynamic threshold for speech pathologies

Vista sencilla de ítem
dc.contributor.authorOrtiz, P.D.
dc.contributor.authorVilla, L.F.
dc.contributor.authorSalazar, C.
dc.contributor.authorQuintero, O.L.
dc.contributor.departmentUniversidad EAFIT. Departamento de Cienciasspa
dc.contributor.researchgroupModelado Matemáticospa
dc.creatorOrtiz, P.D.
dc.creatorVilla, L.F.
dc.creatorSalazar, C.
dc.creatorQuintero, O.L.
dc.date.accessioned2021-04-12T14:11:48Z
dc.date.available2021-04-12T14:11:48Z
dc.date.issued2016-01-01
dc.description.abstractA simple but efficient voice activity detector based on the Hilbert transform and a dynamic threshold is presented to be used on the pre-processing of audio signals. The algorithm to define the dynamic threshold is a modification of a convex combination found in literature. This scheme allows the detection of prosodic and silence segments on a speech in presence of non-ideal conditions like a spectral overlapped noise. The present work shows preliminary results over a database built with some political speech. The tests were performed adding artificial noise to natural noises over the audio signals, and some algorithms are compared. Results will be extrapolated to the field of adaptive filtering on monophonic signals and the analysis of speech pathologies on futures works.eng
dc.identifierhttps://eafit.fundanetsuite.com/Publicaciones/ProdCientif/PublicacionFrw.aspx?id=4291
dc.identifier.doi10.1088/1742-6596/705/1/012037
dc.identifier.issn17426596
dc.identifier.otherSCOPUS;2-s2.0-84978113430
dc.identifier.urihttp://hdl.handle.net/10784/27893
dc.language.isoengeng
dc.publisherIOP PUBLISHING LTD
dc.relation.urihttps://www.scopus.com/inward/record.uri?eid=2-s2.0-84978113430&doi=10.1088%2f1742-6596%2f705%2f1%2f012037&partnerID=40&md5=f61baca7983192e82e40e180b53edf36
dc.rightshttps://v2.sherpa.ac.uk/id/publication/issn/1742-6596
dc.sourceJournal Of Physics: Conference Series
dc.subject.keywordAcoustic noiseeng
dc.subject.keywordAdaptive filterseng
dc.subject.keywordAlgorithmseng
dc.subject.keywordAudio acousticseng
dc.subject.keywordBiomedical engineeringeng
dc.subject.keywordMathematical transformationseng
dc.subject.keywordPathologyeng
dc.subject.keywordSignal detectioneng
dc.subject.keywordSignal processing, Artificial noiseeng
dc.subject.keywordConvex combinationseng
dc.subject.keywordDynamic thresholdeng
dc.subject.keywordHilbert transformeng
dc.subject.keywordMonophonic signalseng
dc.subject.keywordNon-ideal conditionseng
dc.subject.keywordVoice activity detection algorithmseng
dc.subject.keywordVoice activity detectors, Speech recognitioneng
dc.titleA simple but efficient voice activity detection algorithm through Hilbert transform and dynamic threshold for speech pathologieseng
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