METHOD AND DEVICE FOR SPEECH SYNTHESIS

摘要

PURPOSE:To optionally vary the time required for speech synthesis and the quantity of a synthesized speech. CONSTITUTION:A Chinese character and Japanese syllabary mixed character code sequence as an object of speech synthesis and degree information showing a degree N are inputted through an input part 1, a language processing part 3 generates a phoneme series and phoneme information corresponding to the input character code sequence by using a word dictionary 2, and a synthesis parameter generation part 5 extracts the cepstrum parameter of the phoneme corresponding to the phoneme series from a speech piece file 4 by the degree indicated by the degree information from the input part 1 to generate a phoneme parameter and also generate a phoneme parameter corresponding to its rhythm information. The phoneme parameter and rhythm parameter are inputted to a speech synthesis part 6 and composition filtering of the degree indicated by the degree information from the input part 1 is performed on the basis of the phoneme parameter and rhythm parameter to generate a synthesized speech.