Full metadata record
DC poleHodnotaJazyk
dc.contributor.authorTrmal, Jan
dc.contributor.authorZelinka, Jan
dc.contributor.authorMüller, Luděk
dc.date.accessioned2015-12-11T10:02:21Z
dc.date.available2015-12-11T10:02:21Z
dc.date.issued2010
dc.identifier.citationTRMAL, Jan; ZELINKA, Jan; MÜLLER, Luděk. Adaptation of a feedforward artificial neural network using a linear transform. In: Text, speech and dialogue. Berlin: Springer, 2010, p. 423-430. (Lecture notes in computer science; 6231). ISBN 3-642-15759-9.en
dc.identifier.isbn3-642-15759-9
dc.identifier.urihttp://www.kky.zcu.cz/cs/publications/TrmalJan_2010_Adaptationof
dc.identifier.urihttp://hdl.handle.net/11025/16968
dc.format8 s.cs
dc.format.mimetypeapplication/pdf
dc.language.isoenen
dc.publisherSpringeren
dc.relation.ispartofseriesLecture notes in computer science; 6231en
dc.rights© Jan Trmal - Jan Zelinka - Luděk Müllercs
dc.subjectMLP ANNcs
dc.subjectaplikace informačních systémůcs
dc.subjecthuman computer interactioncs
dc.titleAdaptation of a feedforward artificial neural network using a linear transformen
dc.title.alternativeAdaptace ANN pomocí LTcs
dc.typečlánekcs
dc.typearticleen
dc.rights.accessopenAccessen
dc.type.versionpublishedVersionen
dc.description.abstract-translatedIn this paper we present a novel method for adaptation of a multi-layer perceptron neural network (MLP ANN). Nowadays, the adaptation of the ANN is usually done as an incremental retraining either of a subset or the complete set of the ANN parameters. However, since sometimes the amount of the adaptation data is quite small, there is a fundamental drawback of such approach – during retraining, the network parameters can be easily overfitted to the new data. There certainly are techniques that can help overcome this problem (earlystopping, cross-validation), however application of such techniques leads to more complex and possibly more data hungry training procedure. The proposed method approaches the problem from a different perspective. We use the fact that in many cases we have an additional knowledge about the problem. Such additional knowledge can be used to limit the dimensionality of the adaptation problem. We applied the proposed method on speaker adaptation of a phoneme recognizer based on traps (Temporal Patterns) parameters. We exploited the fact that the employed traps parameters are constructed using log-outputs of mel-filter bank and by virtue of reformulating the first layer weight matrix adaptation problem as a mel-filter bank output adaptation problem, we were able to significantly limit the number of free variables. Adaptation using the proposed method resulted in a substantial improvement of phoneme recognizer accuracy.en
dc.subject.translatedMLP ANNen
dc.subject.translatedinformation systems applicationsen
dc.subject.translatedhuman computer interactionen
dc.type.statusPeer-revieweden
Vyskytuje se v kolekcích:Články / Articles (KKY)

Soubory připojené k záznamu:
Soubor Popis VelikostFormát 
TrmalJan_2010_Adaptationof.pdfPlný text116,46 kBAdobe PDFZobrazit/otevřít


Použijte tento identifikátor k citaci nebo jako odkaz na tento záznam: http://hdl.handle.net/11025/16968

Všechny záznamy v DSpace jsou chráněny autorskými právy, všechna práva vyhrazena.