Maximum-likelihood stochastic-transformation adaptation of hidden Markov modelsMaximum-likelihood stochastic-transformation adaptation of hidden Markov models Peer-Reviewed Journal Publication Δημοσίευση σε Περιοδικό με Κριτές 2015-11-021999enThe recognition accuracy in previous large vocabulary automatic speech recognition (ASR) systems is highly related to the existing mismatch between the training and testing sets. For example, dialect differences across the training and testing speakers result in 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 transformations to adapt the means, and possibly the covariances of the mixture Gaussians. The linear assumption, however, is too restrictive, and 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 speech recognition systemhttp://creativecommons.org/licenses/by/4.0/IEEE Transactions Speech and Audio Processing72177-187 Diakoloukas Vasilis Διακολουκας Βασιλeioς Digalakis Vasilis Διγαλακης Βασιλης Institute of Electrical and Electronics Engineers Speech recognition