Optimization of Hidden Markov Model in Speech Recognition Improvment

This paper is how to implement a speech recognition system based on the theory of the Hidden Markov Model (HMM).The work accomplished is by reference to the theory, implementing a MFCC, Mel Frequency Cestrum Coefficient function, a training function, which creates Hidden Markov Models of specific utterances and a testing function, testing utterances on the models created by the training-function. These functions where first created in Matlab. Then the test-function where implemented on the DSK. An evaluation of the implementation is performed.

کلیدواژه ها:

speech signal ، HMM ، DSK ، VAD ، frame length ، speech recognizer