Full metadata record
DC pole | Hodnota | Jazyk |
---|---|---|
dc.contributor.author | Trmal, Jan | |
dc.contributor.author | Zelinka, Jan | |
dc.contributor.author | Müller, Luděk | |
dc.date.accessioned | 2015-12-11T10:02:21Z | |
dc.date.available | 2015-12-11T10:02:21Z | |
dc.date.issued | 2010 | |
dc.identifier.citation | TRMAL, 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.isbn | 3-642-15759-9 | |
dc.identifier.uri | http://www.kky.zcu.cz/cs/publications/TrmalJan_2010_Adaptationof | |
dc.identifier.uri | http://hdl.handle.net/11025/16968 | |
dc.format | 8 s. | cs |
dc.format.mimetype | application/pdf | |
dc.language.iso | en | en |
dc.publisher | Springer | en |
dc.relation.ispartofseries | Lecture notes in computer science; 6231 | en |
dc.rights | © Jan Trmal - Jan Zelinka - Luděk Müller | cs |
dc.subject | MLP ANN | cs |
dc.subject | aplikace informačních systémů | cs |
dc.subject | human computer interaction | cs |
dc.title | Adaptation of a feedforward artificial neural network using a linear transform | en |
dc.title.alternative | Adaptace ANN pomocí LT | cs |
dc.type | článek | cs |
dc.type | article | en |
dc.rights.access | openAccess | en |
dc.type.version | publishedVersion | en |
dc.description.abstract-translated | In 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.translated | MLP ANN | en |
dc.subject.translated | information systems applications | en |
dc.subject.translated | human computer interaction | en |
dc.type.status | Peer-reviewed | en |
Vyskytuje se v kolekcích: | Články / Articles (KKY) |
Soubory připojené k záznamu:
Soubor | Popis | Velikost | Formát | |
---|---|---|---|---|
TrmalJan_2010_Adaptationof.pdf | Plný text | 116,46 kB | Adobe PDF | Zobrazit/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.