| 摘要 |
<P>PROBLEM TO BE SOLVED: To provide a speech synthesizer and a speech synthesis program that can reduce the time required for speech synthesis and improve accuracy of the speech synthesis. <P>SOLUTION: A speech synthesizer 1 synthesizes speech corresponding to the input content of a character input device 2 comprising a kana character key, a voiced sound symbol key, a semi-voiced sound symbol key, an a-line small letter key, a ya-line small letter key and a ta-line small letter key. The speech synthesizer 1 comprises; an unvoiced sound and syllabic nasal discrimination means 11 discriminating an unvoiced character from a syllabic nasal character; a voiced sound discrimination means 12 discriminating a voiced sound character; a semi-voiced sound discrimination means 13 discriminating a semi-voiced sound character; a contracted sound discrimination sound means 14 discriminating a contracted sound character; a syllable with a double consonant discrimination means 15 discriminating a syllable character with a double consonant; a speech waveform storage means 16 storing each speech waveform of an unvoiced sound, a syllabic nasal, a voiced sound, a semi-voiced sound, a contracted sound and a syllable with a double consonant; and a speech synthesis means 17 synthesizing speech by extracting a speech waveform corresponding to each of the syllable characters discriminated by each discrimination means from the speech waveform storage means 16. <P>COPYRIGHT: (C)2012,JPO&INPIT |
