Institutional Repository [SANDBOX]
Technical University of Crete
EN  |  EL

Search

Browse

My Space

Rapid acoustic model development using gaussian mixture clustering and language adaptation

Chatzichrisafis, Nikos, Digalakis Vasilis, Diakoloukas Vasilis, Harizakis Costas

Simple record


URIhttp://purl.tuc.gr/dl/dias/F263561E-F6A7-419B-82CA-71CA2405F2E4-
Identifierhttp://www.mirlab.org/conference_papers/International_Conference/ICSLP%202004/contents/TuA_pdf/TuA1802o/TuA1802o.5_p1069.pdf-
Languageen-
Extent4 pagesen
TitleRapid acoustic model development using gaussian mixture clustering and language adaptationen
CreatorChatzichrisafis, Nikosen
CreatorDigalakis Vasilisen
CreatorΔιγαλακης Βασιληςel
CreatorDiakoloukas Vasilisen
CreatorΔιακολουκας Βασιλeioςel
CreatorHarizakis Costas en
Content SummaryThis work presents techniques for improved cross-language transfer of speech recognition systems to new, previously undeveloped, languages. Such techniques are particularly useful for target languages where minimal amounts of training data are available. We describe a novel method to produce a language-independent system by combining acoustic models from a number of source languages. This intermediate language-independent acoustic model is used to bootstrap a target-language system by applying language adaptation. For our experiments we use acoustic models of seven source languages to develop a target Greek acoustic model. We show that our technique significantly outperforms a system trained from scratch when less than 8 hours of read speech is available.en
Type of ItemΔημοσίευση σε Συνέδριοel
Type of ItemConference Publicationen
Licensehttp://creativecommons.org/licenses/by/4.0/en
Date of Item2015-11-08-
Date of Publication2004-
SubjectGMRFs (Gaussian Markov random fields)en
Subjectgaussian markov random fieldsen
Subjectgmrfs gaussian markov random fieldsen
Bibliographic CitationN. Chatzichrisafis, V. Digalakis, V. Diakoloukas and C. Harizakis, "Rapid acoustic model development using Gaussian mixture clustering and language adaptation," presented at 8th International Conference on Spoken Language Processing, Jeju Island, South Korea, 2004en

Services

Statistics