Full metadata record
DC FieldValueLanguage
dc.contributor.authorTrmal, Jan
dc.contributor.authorZelinka, Jan
dc.contributor.authorMüller, Luděk
dc.date.accessioned2015-12-11T09:09:28Z
dc.date.available2015-12-11T09:09:28Z
dc.date.issued2010
dc.identifier.citationTRMAL, Jan; ZELINKA, Jan; MÜLLER, Luděk. On speaker adaptive training of artificial neural networks. In: Proceedings of ICSPL 2010: 11th Annual Conference of the International Speech Communication Association 2010, 26-30 September 2010, Makuhari, Chiba, Japan. [Baixas]: ISCA, 2010, p. [1-4]. ISSN 1990-9772.en
dc.identifier.issn1990-9772
dc.identifier.urihttp://www.kky.zcu.cz/cs/publications/TrmalJan_2010_OnSpeakerAdaptive
dc.identifier.urihttp://hdl.handle.net/11025/16965
dc.format4 s.cs
dc.format.mimetypeapplication/pdf
dc.language.isoenen
dc.publisherISCAcs
dc.rights© Jan Trmal - Jan Zelinka - Luděk Müllercs
dc.subjectspeaker adaptive trainingcs
dc.subjectTRAPScs
dc.subjectVTLNcs
dc.subjectneuronové sítěcs
dc.subjectrozpoznávánícs
dc.titleOn speaker adaptive training of artificial neural networksen
dc.title.alternativeSpeaker adaptive training pro ANNcs
dc.typečlánekcs
dc.typearticleen
dc.rights.accessopenAccessen
dc.type.versionpublishedVersionen
dc.description.abstract-translatedIn the paper we present two techniques improving the recognition accuracy of multilayer perceptron neural networks (MLP ANN) by means of adopting Speaker Adaptive Training. The use of the MLP ANN, usually in combination with the TRAPS parametrization, includes applications in speech recognition tasks, discriminative features production for GMM-HMM and other. In the first SAT experiments, we used the VTLN as a speaker normalization technique. Moreover, we developed a novel speaker normalization technique called Minimum Error Linear Transform (MELT) that resembles the cMLLR/fMLLR method \cite{gales96variance} with respect to the possible application either on the model or features. We tested these two methods extensively on telephone speech corpus SpeechDat-East. The results obtained in these experiments suggest that incorporation of SAT into MLP ANN training process is beneficial and depending on the setup leads to significant decrease of phoneme error rate (3% -- 8% absolute, 12% -- 25% relative).en
dc.subject.translatedspeaker adaptive trainingen
dc.subject.translatedTRAPSen
dc.subject.translatedVTLNen
dc.subject.translatedneural networksen
dc.subject.translatedrecognitionen
dc.type.statusPeer-revieweden
Appears in Collections:Články / Articles (KKY)

Files in This Item:
File Description SizeFormat 
TrmalJan_2010_OnSpeakerAdaptive.pdfPlný text391,88 kBAdobe PDFView/Open
Show simple item record


Please use this identifier to cite or link to this item: http://hdl.handle.net/11025/16965

Items in DSpace are protected by copyright, with all rights reserved, unless otherwise indicated.

search
navigation
  1. DSpace at University of West Bohemia
  2. Publikační činnost / Publications
  3. Fakulta aplikovaných věd / Faculty of Applied Sciences
  4. Katedra kybernetiky / Department of Cybernetics
  5. Články / Articles (KKY)