SPEECH SYNTHESIS USING HIDDEN MARKOV MODEL AND APPLICATION OF VOICE CONVERSION

Abstract

Speech synthesis, an electronics system talks like human has grown in popularity over the last few years. This paper gives a general overview of techniques used in speech synthesis. One instance of these techniques, called hidden Markov model (HMM) based speech synthesis, has recently been demonstrated to be very effective in synthesizing acceptable speech. This paper also contrasts these techniques with the more conventional technique, calledlinear predictive coding (LPC) that has dominated speech synthesis over the last decade. The problem in implementation, advantages and drawbacks of these synthesis techniques are highlighted. Finally, advanced techniques for future developments are described. This paper gives brief idea about application of voice conversion using a codebook method.