STATIC DICTIONARY FOR PRONUNCIATION MODELING

K.Subramanyam, D.Arun Kumar

Abstract: Speech Recognition is the process by which a computer can recognize spoken words. Basically it means talking to your computer and having it correctly recognize what you are saying. This work is to improve the speech recognition accuracy for Telugu language using pronunciation model. Speech Recognizers based upon Hidden Markov Model have achieved a high level of performance in controlled environments. One naive approach for robust speech recognition in order to handle the mismatch between training and testing environments, many techniques have been proposed. some methods work on acoustic model and some methods work on Language model. Pronunciation dictionary is the most important component of the Speech Recognition system. New pronunciations for the words will be considered for speech recognition accuracy

Keywords: PRONUNCIATION MODELING

DOI: https://doi.org/10.15623/ijret.2012.0102017