| 摘要 |
A speech synthesis device comprises a pitch pattern generating section (104) for combining a standard pattern which approximately represents the facies of a pitch pattern and an original utterance pattern which represents the pitch pattern of a recorded speech to generate a pitch patter on the basis of pitch pattern target data including sound information composed of at least a syllable, a phoneme, a word, or the like, a unit waveform selecting section (106) for selecting unit waveform data on the basis of the generated pitch pattern and selecting the original utterance unit waveform data corresponding to an original utterance pattern in the section in which the original utterance pattern is used in selecting the unit waveform data, and a speech waveform generating section (107) for editing the selected unit waveform data to generate a synthesized speech so that the rhythm represented by the generated pitch pattern is reproduced. |
