| 摘要 |
PROBLEM TO BE SOLVED: To solve such a problem that it is impossible to acquire feature quantities for obtaining high quality output voice in conventional voice synthesis.SOLUTION: A voice processing device comprises: a voice storage unit capable of storing voice; a feature quantity storage unit capable of storing one or more feature quantities; a spectrum acquisition unit for acquiring voice spectra or spectrum envelopes stored in the voice storage unit; a shortening processing unit for performing shortening processing to shorten a spectrum having a frequency equal to or more than a predetermined threshold on the spectra or spectrum envelops acquired by the spectrum acquisition unit; a feature quantity acquisition unit for acquiring one or more feature quantities from the spectra or spectrum envelopes on which the shortening processing is performed; and a feature quantity accumulation unit for accumulating one or more feature quantities acquired by the feature quantity acquisition unit in the feature quantity storage unit. Thus, it is possible to acquire feature quantities for obtaining high quality output voice. |
