Voice synthesizer of multi sounds

A voice synthesizer apparatus comprising:

• a data acquisition portion that successively obtains phonetic entity data specifying a phonetic entity of a given voice;
• an envelope acquisition portion that identifies a voice segment corresponding to the phonetic entity specified by the phonetic entity data out of a plurality of voice segments corresponding to different phonetic entities, and that obtains a spectral envelope of a frequency spectrum of the voice segment corresponding to the phonetic entity specified by the phonetic entity data;
• a spectrum acquisition portion that obtains either of a first frequency spectrum of a single voice or a second frequency spectrum of a plurality of voices having almost the same pitch as that of the first frequency spectrum and having a peak width of frequency peaks greater than a peak width of frequency peaks contained in the first frequency spectrum;
• an envelope adjustment portion that adjusts a spectral envelope of either the first frequency spectrum or the second frequency spectrum obtained by the spectrum acquisition portion so as to match with the spectral envelope obtained by the envelope acquisition portion;
• and
• a voice generation portion that generates an output voice signal from either of the first frequency spectrum or the second frequency spectrum after being adjusted by the envelope adjustment portion.

A voice synthesizer apparatus comprising:

• an envelope acquisition portion that obtains a spectral envelope of a reference frequency spectrum of a given voice;
• a spectrum acquisition portion that obtains a frequency spectrum of a plurality of voices which are generated in parallel to one another;
• an envelope adjustment portion that adjusts a spectral envelope of the frequency spectrum obtained by the spectrum acquisition portion so as to match with the spectral envelope of the reference frequency spectrum obtained by the envelope acquisition portion;
• and a voice generation portion that generates an output voice signal from the frequency spectrum having the spectral envelope adjusted by the envelope adjustment portion.

A machine-readable medium containing a program executable by a computer to perform a voice synthesizing process comprising:

• a data acquisition process of successively obtaining phonetic entity data specifying a phonetic entity of a given voice;
• an envelope acquisition process of identifying a voice segment corresponding to the phonetic entity specified by the phonetic entity data out of a plurality of voice segments corresponding to different phonetic entities, and obtaining a spectral envelope of a frequency spectrum of the voice segment corresponding to the specified phonetic entity;
• a spectrum acquisition process of obtaining a frequency spectrum of a plurality of voices which are generated in parallel to one another;
• an envelope adjustment process of adjusting a spectral envelope of the frequency spectrum obtained by the spectrum acquisition process so as to match with the spectral envelope obtained by the envelope acquisition process;
• and
• a voice generation process of generating an output voice signal from the frequency spectrum having the spectral envelope adjusted by the envelope adjustment process.

A machine-readable medium containing a program executable by a computer to perform a voice synthesizing process comprising:

• a data acquisition process of successively obtaining phonetic entity data specifying a phonetic entity of a given voice;
• an envelope acquisition process of identifying a voice segment corresponding to the phonetic entity specified by the phonetic entity data out of a plurality of voice segments corresponding to different phonetic entities, and obtaining a spectral envelope of a frequency spectrum of the voice segment corresponding to the phonetic entity specified by the phonetic entity data;
• a spectrum acquisition process of obtaining either of a first frequency spectrum of a single voice or a second frequency spectrum of a plurality of voices having almost the same pitch as that of the first frequency spectrum and having a peak width of frequency peaks greater than a peak width of frequency peaks contained in the first frequency spectrum;
• an envelope adjustment process of adjusting a spectral envelope of either of the first frequency spectrum or the second frequency spectrum obtained by the spectrum acquisition process so as to match with the spectral envelope obtained by the envelope acquisition process;
• and
• a voice generation process of generating an output voice signal from either of the first frequency spectrum or the second frequency spectrum after being adjusted by the envelope adjustment process.