hh.sePublikasjoner
Endre søk
RefereraExporteraLink to record
Permanent link

Direct link
Referera
Referensformat
  • apa
  • ieee
  • modern-language-association-8th-edition
  • vancouver
  • Annet format
Fler format
Språk
  • de-DE
  • en-GB
  • en-US
  • fi-FI
  • nn-NO
  • nn-NB
  • sv-SE
  • Annet språk
Fler språk
Utmatningsformat
  • html
  • text
  • asciidoc
  • rtf
Exploring Kernels in SVM-Based Classification of Larynx Pathology from Human Voice
Kaunas University of Technology.
Kaunas University of Technology.
Kaunas University of Technology.
Högskolan i Halmstad, Akademin för informationsteknologi, Halmstad Embedded and Intelligent Systems Research (EIS), Laboratoriet för intelligenta system.ORCID-id: 0000-0003-2185-8973
Vise andre og tillknytning
2010 (engelsk)Inngår i: Proceedings of the 5th International Conference on Electrical and Control Technologies ECT-2010, May 6-7, 2010, Kaunas, Lithuania, Kaunas: KUT , 2010, s. 67-72Konferansepaper, Publicerat paper (Fagfellevurdert)
Abstract [en]

In this paper identification of laryngeal disorders using cepstral parameters of human voice is investigated. Mel-frequency cepstral coefficients (MFCC), extracted from audio recordings, are further approximated, using 3 strategies: sampling, averaging, and estimation. SVM and LS-SVM categorize pre-processed data into normal, nodular, and diffuse classes. Since it is a three-class problem, various combination schemes are explored.  Constructed custom kernels outperformed a popular non-linear RBF kernel. Features, estimated with GMM, and SVM kernels, designed to exploit this information, is an interesting fusion of probabilistic and discriminative models for human voice-based classification of larynx pathology.

sted, utgiver, år, opplag, sider
Kaunas: KUT , 2010. s. 67-72
Emneord [en]
Laryngeal disorder, Pathological voice, Voice processing, Mel-frequency cepstral coefficients, Sequence kernel, Principal canonical correlation, Monte-Carlo sampling, Kullback-Leibler divergence, Earth mover’s distance, GMM, SVM
HSV kategori
Identifikatorer
URN: urn:nbn:se:hh:diva-5961Scopus ID: 2-s2.0-84941687065OAI: oai:DiVA.org:hh-5961DiVA, id: diva2:352842
Konferanse
The 5th International Conference on Electrical and Control Technologies 6-7 May 2010, Kaunas, Lithuania
Tilgjengelig fra: 2010-09-23 Laget: 2010-09-22 Sist oppdatert: 2018-09-05bibliografisk kontrollert

Open Access i DiVA

fulltekst(308 kB)708 nedlastinger
Filinformasjon
Fil FULLTEXT01.pdfFilstørrelse 308 kBChecksum SHA-512
4acd6fa1c2d20c99e6d0abfd2e293423dbdda3b6b116b7d7d32fd59d1423f6789946b72347b414126af3cc80b9bf1c2bbe85b007ec46cc3ce1a838363098ef87
Type fulltextMimetype application/pdf

Scopus

Personposter BETA

Verikas, Antanas

Søk i DiVA

Av forfatter/redaktør
Verikas, Antanas
Av organisasjonen

Søk utenfor DiVA

GoogleGoogle Scholar
Totalt: 708 nedlastinger
Antall nedlastinger er summen av alle nedlastinger av alle fulltekster. Det kan for eksempel være tidligere versjoner som er ikke lenger tilgjengelige

urn-nbn

Altmetric

urn-nbn
Totalt: 343 treff
RefereraExporteraLink to record
Permanent link

Direct link
Referera
Referensformat
  • apa
  • ieee
  • modern-language-association-8th-edition
  • vancouver
  • Annet format
Fler format
Språk
  • de-DE
  • en-GB
  • en-US
  • fi-FI
  • nn-NO
  • nn-NB
  • sv-SE
  • Annet språk
Fler språk
Utmatningsformat
  • html
  • text
  • asciidoc
  • rtf