Speech Recognition Using Hidden Markov Model with MFCC-Subband Technique

This paper presents an approach to the recognition of speech signal using frequency spectral information with mel frequency for the improvement of speech feature representation in a HMM based recognition approach. The mel frequency approach exploits the frequency observation for speech signal in a given resolution which results in resolution feature overlapping resulting in recognition limit. Resolution decomposition with frequency mapping approach for a HMM based speech recognition system. The Simulation results show a improvement in the quality metrics of speech recognition wrt. to computational time, learning accuracy for a speech recognition system.