INFORMATICAInformatica0868-49520868-4952VUinf1510710.15388/Informatica.2004.048Research articleSpecifics of Hidden Markov Model Modifications for Large Vocabulary Continuous Speech RecognitionŠilingasDariusi5dasi@vaidila.vdu.ltDepartment of Applied Informatics, Vytautas Magnus University, Vileikos 8, LT‐3035 Kaunas, LithuaniaTelksnysLaimutistelksnys@ktl.mii.ltDepartment of Applied Informatics, Vytautas Magnus University, Recognition Processes Department, Institute of Mathematics and Informatics, Goštauto 12–205, 08663 Vilnius, Lithuania010120041519311001072003

Specifics of hidden Markov model‐based speech recognition are investigated. Influence of modeling simple and context‐dependent phones, using simple Gaussian, two and three‐component Gaussian mixture probability density functions for modeling feature distribution, and incorporating language model are discussed. Word recognition rates and model complexity criteria are used for evaluating suitability of these modifications for practical applications. Development of large vocabulary continuous speech recognition system using HTK toolkit and WSJCAM0 English speech corpus is described. Results of experimental investigations are presented.

large vocabulary continuous speech recognitionhidden Markov modelViterbi recognitionbeam searchcontext‐dependent phonesGaussian mixturelanguage modelingHTKWSJCAM0