Publication:
Random forest-based prediction of Parkinson's disease progression using acoustic, ASR and intelligibility features

dc.affiliation.dptoUC3M. Departamento de Teoría de la Señal y Comunicacioneses
dc.affiliation.grupoinvUC3M. Grupo de Investigación: Procesado Multimediaes
dc.contributor.authorZlotnik, Alexander
dc.contributor.authorMontero Martínez, Juan Manuel
dc.contributor.authorSan Segundo Hernández, Rubén
dc.contributor.authorGallardo Antolín, Ascensión
dc.contributor.funderEuropean Commissionen
dc.contributor.funderMinisterio de Economía y Competitividad (España)es
dc.date.accessioned2021-02-22T13:54:14Z
dc.date.available2021-02-22T13:54:14Z
dc.date.issued2015
dc.descriptionProceeding of: 16th Annual Conference of the International Speech Communication Association (INTERSPEECH 2015), Dresden, Germany, September 6-10, 2015en
dc.description.abstractThe Interspeech ComParE 2015 PC Sub-Challenge consists of automatically determining the degree of Parkinson's condition using exclusively the patient's voice. In this paper, we face this problem as a regression task and in order to succeed, we propose the use of an ensemble learning method, Random Forest (RF), in combination with features of different nature: acoustic characteristics, features derived from the output of an Automatic Speech Recognition system (ASR) and non-intrusive intelligibility measures. The system outperforms the baseline results achieving a relative improvement higher than 19% in the development set.en
dc.description.sponsorshipThe work leading to these results has been partly supported by Spanish Government grants TEC2014-53390-P and DPI2014-53525-C3-2-R, and from the European Union under grant agreement number 287678 (SIMPLE4ALL). Authors also thank all the other members of the Speech Technology Group at UPM and Grupo de Procesado Multimedia at UC3M for the continuous and fruitful discussion on these topics.en
dc.format.extent5es
dc.identifier.bibliographicCitationINTERSPEECH 2015: 16th Annual Conference of the International Speech Communication Association, Dresden, Germany, September 6-10, 2015. ISCA, 2015, Pp. 503-507en
dc.identifier.publicationfirstpage503es
dc.identifier.publicationlastpage507es
dc.identifier.publicationtitleINTERSPEECH 2015: 16th Annual Conference of the International Speech Communication Association, Dresden, Germany, September 6-10, 2015en
dc.identifier.urihttps://hdl.handle.net/10016/31990
dc.identifier.uxxiCC/0000024912
dc.language.isoengen
dc.publisherInternational Speech Communication Association (ISCA)en
dc.relation.eventdate2015-09-06es
dc.relation.eventplaceDresde, ALEMANIAes
dc.relation.eventtitle16th Annual Conference of the International Speech Communication Association (INTERSPEECH 2015)en
dc.relation.projectIDGobierno de España. TEC2014-53390-Pes
dc.relation.projectIDGobierno de España. DPI2014-53525-C3-2-Res
dc.relation.projectIDinfo:eu-repo/grantAgreement/EC/FP7/287678-SIMPLE4ALLen
dc.relation.publisherversionhttps://www.isca-speech.org/archive/interspeech_2015/i15_0503.htmlen
dc.rights© 2015 ISCA.en
dc.rights.accessRightsopen accessen
dc.subject.ecienciaBiología y Biomedicinaes
dc.subject.ecienciaElectrónicaes
dc.subject.ecienciaTelecomunicacioneses
dc.subject.otherRandom foresten
dc.subject.otherRegressionen
dc.subject.otherParkinson's diseaseen
dc.subject.otherASR featuresen
dc.subject.otherIntelligibilityes
dc.titleRandom forest-based prediction of Parkinson's disease progression using acoustic, ASR and intelligibility featuresen
dc.typeconference paper*
dc.type.hasVersionAM*
dspace.entity.typePublication
Files
Original bundle
Now showing 1 - 1 of 1
Loading...
Thumbnail Image
Name:
random_INTERSPEECH_2015_ps.pdf
Size:
225.47 KB
Format:
Adobe Portable Document Format