摘要 |
PROBLEM TO BE SOLVED: To generate a synthesis sound reflecting intention of a user with fineness.SOLUTION: A voice synthesis device comprises: a display control unit that displays, in time series on a display device, a phoneme symbol 63 and a starting point (pV and pC) of a sounding period for each of a plurality of phonemes corresponding to sounding content of each specified sound in which a tone pitch and a sounding period are specified, and moves, for each phoneme, the starting point of the sounding period of each phoneme on a temporal axis according to an instruction of a user. |