Full metadata record
DC Field | Value | Language |
---|---|---|
dc.contributor.author | Trmal, Jan | |
dc.contributor.author | Zelinka, Jan | |
dc.contributor.author | Müller, Luděk | |
dc.date.accessioned | 2015-12-11T09:09:28Z | |
dc.date.available | 2015-12-11T09:09:28Z | |
dc.date.issued | 2010 | |
dc.identifier.citation | TRMAL, 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.issn | 1990-9772 | |
dc.identifier.uri | http://www.kky.zcu.cz/cs/publications/TrmalJan_2010_OnSpeakerAdaptive | |
dc.identifier.uri | http://hdl.handle.net/11025/16965 | |
dc.format | 4 s. | cs |
dc.format.mimetype | application/pdf | |
dc.language.iso | en | en |
dc.publisher | ISCA | cs |
dc.rights | © Jan Trmal - Jan Zelinka - Luděk Müller | cs |
dc.subject | speaker adaptive training | cs |
dc.subject | TRAPS | cs |
dc.subject | VTLN | cs |
dc.subject | neuronové sítě | cs |
dc.subject | rozpoznávání | cs |
dc.title | On speaker adaptive training of artificial neural networks | en |
dc.title.alternative | Speaker adaptive training pro ANN | cs |
dc.type | článek | cs |
dc.type | article | en |
dc.rights.access | openAccess | en |
dc.type.version | publishedVersion | en |
dc.description.abstract-translated | In 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.translated | speaker adaptive training | en |
dc.subject.translated | TRAPS | en |
dc.subject.translated | VTLN | en |
dc.subject.translated | neural networks | en |
dc.subject.translated | recognition | en |
dc.type.status | Peer-reviewed | en |
Appears in Collections: | Články / Articles (KKY) |
Files in This Item:
File | Description | Size | Format | |
---|---|---|---|---|
TrmalJan_2010_OnSpeakerAdaptive.pdf | Plný text | 391,88 kB | Adobe PDF | View/Open |
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.