A hidden Markov model approach to speech synthesis

This paper describes a novel technique for producing smooth speech parametric representation evolution by means of an application of traditional hidden Markov modeling techniques. It is based on the consideration that HMM training is able to locate the main acoustic events which occur during the speech process; thus the obtained decomposition can be used to reproduce the linguistic units utilized for training. This is accomplished by interpolating the state-related features values with some weighting functions, as it is done for temporal decomposition technique [1] [15]. Results will be given for isolated word synthesis