摘要 |
PROBLEM TO BE SOLVED: To obtain a voice synthesizing device which outputs a synthesized voice corresponding to features of a desired human voice by inputting the desired human voice. SOLUTION: This device is equipped with a voice input part 11 which inputs a desired voice, a spectrum analysis part 14 which analyzes voice feature data of voice data inputted on the basis of basic voice data, a synthesized phoneme data generation part 18 which shapes the waveform of basic phoneme data corresponding to the analyzed voice feature data to generate synthesized phoneme data, a voice synthesis part 21 which synthesizes a voice by extracting synthesized phoneme data corresponding to text data 22 from the generated synthesized phoneme data, and a voice output part 23 which outputs the voice- synthesized voice data. |