Covariance matrix enhancement approach to train robust Gaussian mixture models of speech data

Show simple item record
dc.contributor.authorVaněk, Jan
dc.contributor.authorMachlica, Lukáš
dc.contributor.authorPsutka, Josef V.
dc.contributor.authorPsutka, Josef
dc.date.accessioned2016-01-07T12:11:29Z
dc.date.available2016-01-07T12:11:29Z
dc.date.issued2013
dc.description.abstract-translatedAn estimation of parameters of a multivariate Gaussian Mixture Model is usually based on a criterion (e.g. Maximum Likelihood) that is focused mostly on training data. Therefore, testing data, which were not seen during the training procedure, may cause problems. Moreover, numerical instabilities can occur (e.g. for low-occupied Gaussians especially when working with full-covariance matrices in high-dimensional spaces). Another question concerns the number of Gaussians to be trained for a specific data set. The approach proposed in this paper can handle all these issues. It is based on an assumption that the training and testing data were generated from the same source distribution. The key part of the approach is to use a criterion based on the source distribution rather than using the training data itself. It is shown how to modify an estimation procedure in order to fit the source distribution better (despite the fact that it is unknown), and subsequently new estimation algorithm for diagonal- as well as full-covariance matrices is derived and tested.en
dc.format8 s.cs
dc.format.mimetypeapplication/pdf
dc.identifier.citationVANĚK, Jan; MACHLICA, Lukáš; PSUTKA, Josef V.; PSUTKA, Josef. Covariance matrix enhancement approach to train robust Gaussian mixture models of speech data. In: Speech and computer. Berlin: Springer, 2013, p. 92-99. (Lectures notes in computer science; 8113). ISBN 978-3-319-01930-7.en
dc.identifier.doi10.1007/978-3-319-01931-4_13
dc.identifier.isbn978-3-319-01930-7
dc.identifier.urihttp://www.kky.zcu.cz/cs/publications/JanVanek_2013_CovarianceMatrix
dc.identifier.urihttp://hdl.handle.net/11025/17161
dc.language.isoenen
dc.publisherSpringeren
dc.relation.ispartofseriesLectures notes in computer; 8113en
dc.rights© Jan Vaněk - Lukáš Machlica - Josef V. Psutka - Josef Psutkacs
dc.rights.accessopenAccessen
dc.subjectsměsi Gaussovských modelůcs
dc.subjectplná kovariancecs
dc.subjectplná kovarianční maticecs
dc.subjectregularizacecs
dc.subjectautomatické rozpoznávání řečics
dc.subject.translatedGaussian mixture modelsen
dc.subject.translatedfull covarianceen
dc.subject.translatedfull covariance matrixen
dc.subject.translatedregularizationen
dc.subject.translatedautomatic speech recognitionen
dc.titleCovariance matrix enhancement approach to train robust Gaussian mixture models of speech dataen
dc.typečlánekcs
dc.typearticleen
dc.type.statusPeer-revieweden
dc.type.versionpublishedVersionen

Files

Original bundle
Showing 1 - 1 out of 1 results
No Thumbnail Available
Name:
JanVanek_2013_CovarianceMatrix.pdf
Size:
253.94 KB
Format:
Adobe Portable Document Format
Description:
Plný text
Download
License bundle
Showing 1 - 1 out of 1 results
No Thumbnail Available
Name:
license.txt
Size:
1.71 KB
Format:
Item-specific license agreed upon to submission
Description:
Download

Collections

Articles (KKY)
 Articles (KIV)