HINDI SPEECH RECOGNITION SYSTEM USING MFCC AND HTK TOOLKIT

This paper presents the approach for Hindi fruit name recognizer system. Every person has its uniqueness in his speech. So in this approach the database speech samples are collected from different 20 speakers with two iterations. These recordings are used to train by acoustic model.  This model is trained on 20 speaker database having vocabulary size is 45 words. HTK toolkit is used to train the input data and evaluation of the results. The proposed system gives a recognition rate of 94.28% for sentence and 98.09 for word level.