Repository logo
 
Publication

Low band continuous speech system for voice pathologies identification

2018Conference object Restricted access
Simple item page
dc.contributor.authorCordeiro, Hugo
dc.contributor.authorMeneses, Carlos
dc.date.accessioned2019-04-29T11:34:42Z
dc.date.available2019-04-29T11:34:42Z
dc.date.issued2018
dc.description.abstractThis paper describes the impact of the signal bandwidth reduction in the identification of voice pathologies. The implemented systems evaluate the identification of 3 classes divided by healthy subjects, subjects diagnosed with physiological larynx pathologies and subjects diagnosed with neuromuscular larynx pathologies. Continuous speech signals are down-sampled to 4 kHz and the extracted spectral parameters are applied to a GMM classifier. No significant change in accuracy occurs, being possible to conclude that the low frequencies contain sufficient information to allow the classification of pathologies. A second objective is to test the effects of suppressing the voice activity detection and the increasing the analysis window length. In both cases the accuracy increases. In conclusion, a pathological voice identification system based on signals sampled at 4 kHz, without voice activity detection and with an analysis window length of 40 ms is proposed, getting 81.8% accuracy. The proposed system has also the advantage of reduces the storage memory and the processing time.pt_PT
dc.description.versioninfo:eu-repo/semantics/publishedVersionpt_PT
dc.identifier.citationCORDEIRO, Hugo; MENESES, Carlos – Low band continuous speech system for voice pathologies identification. In 2018 Signal Processing: Algorithms, Architectures, Arrangements, and Applications (SPA). Poznan, Poland: IEEE, 2018. ISSN 2326-0262. Pp. 315-320pt_PT
dc.identifier.issn2326-0262
dc.identifier.urihttp://hdl.handle.net/10400.21/9903
dc.language.isoengpt_PT
dc.publisherInstitute of Electrical and Electronics Engineerspt_PT
dc.subjectVoice pathologies identificationpt_PT
dc.subjectLow band speech analysispt_PT
dc.subjectSpectral parameterspt_PT
dc.subjectVoice activity detectionpt_PT
dc.titleLow band continuous speech system for voice pathologies identificationpt_PT
dc.typeconference object
dspace.entity.typePublication
oaire.citation.conferencePlaceSep 19-21, 2018 - Poznan, Polandpt_PT
oaire.citation.endPage320pt_PT
oaire.citation.startPage315pt_PT
oaire.citation.title2018 Signal Processing - Algorithms, Architectures, Arrangements, and Applications (SPA)pt_PT
person.familyNameCordeiro
person.familyNameMeneses
person.givenNameHugo
person.givenNameCarlos
person.identifier.ciencia-idA81E-0891-9E9C
person.identifier.ciencia-id531B-D2F8-2544
person.identifier.orcid0000-0001-5559-7746
person.identifier.orcid0000-0002-7770-7093
person.identifier.ridQ-4604-2019
person.identifier.scopus-author-id15833754300
rcaap.rightsclosedAccesspt_PT
rcaap.typeconferenceObjectpt_PT
relation.isAuthorOfPublicationd89b5aa9-55f3-4087-80d4-ab6a005906d6
relation.isAuthorOfPublication97333978-1ce6-4d9a-9639-dc014f9e4ff3
relation.isAuthorOfPublication.latestForDiscoveryd89b5aa9-55f3-4087-80d4-ab6a005906d6

Files

Original bundle
Now showing 1 - 1 of 1
No Thumbnail Available
Name:
Low band_CMeneses.pdf
Size:
689.15 KB
Format:
Adobe Portable Document Format
Download
License bundle
Now showing 1 - 1 of 1
No Thumbnail Available
Name:
license.txt
Size:
1.71 KB
Format:
Item-specific license agreed upon to submission
Description:
Download

Collections

ISEL - Eng. Elect. Tel. Comp. - Comunicações