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

Search

Browse

My Space

Adaptation of hidden markov models using multiple stochastic transformations

Diakoloukas Vasilis, Digalakis Vasilis

Simple record


URIhttp://purl.tuc.gr/dl/dias/41612105-128F-4174-8DF7-F2E148F004D9-
Identifierhttps://www.researchgate.net/publication/221488645_Adaptation_of_hidden_Markov_models_using_multiple_stochastic_transformations-
Languageen-
TitleAdaptation of hidden markov models using multiple stochastic transformationsen
CreatorDiakoloukas Vasilisen
CreatorΔιακολουκας Βασιλeioςel
CreatorDigalakis Vasilisen
CreatorΔιγαλακης Βασιληςel
Content SummaryThe recognition accuracy in recent large vocabulary Automatic Speech Recognition (ASR) systems is highly related to the existing mismatch between the training and test sets. For example, dialect differences across the training and testing speakers result to a significant degradation in recognition performance. Some popular adaptation approaches improve the recognition performance of speech recognizers based on hidden Markov models with continuous mixture densities by using linear transforms to adapt the means, and possibly the covariances of the mixture Gaussians. In this paper, we propose a novel adaptation technique that adapts the means and, optionally, the covariances of the mixture Gaussians by using multiple stochastic transformations. We perform both speaker and dialect adaptation experiments, and we show that our method significantly improves the recognition accuracy and the robustness of our system. The experiments are carried out with SRI's DECIPHER TM speech recognition. 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 Publication1997-
SubjectHMMs (Hidden Markov models)en
Subjecthidden markov modelsen
Subjecthmms hidden markov modelsen
Bibliographic CitationV. Diakoloukas and V. V. Digalakis, "Adaptation of hidden Markov models using multiple stochastic transformations," presented at Fifth European Conference on Speech Communication and Technology, Rhodes, Greece, 1997.en

Services

Statistics