| 摘要 |
<P>PROBLEM TO BE SOLVED: To provide a voice data management system and the like for surely obtaining naturally synthesized voices. <P>SOLUTION: When supplied with data representing a fixed form message, a sound piece edition section 8 retrieves the sound piece data of the sound pieces matching in reading with the sound pieces within the fixed form message from a sound piece database 10 and has utterance speed conversion etc., executed. On the other hand, the sound piece edition section 8 performs the rhythm prediction of the fixed form message and specifies the sound piece data having the highest correlations with the respective sound pieces within the fixed form messages piece by piece from among the retrieved sound piece data based on the results of the rhythm prediction. The sound piece edition section forms the data indicating the synthesized voices by coupling the specified sound piece data etc., to each other. The sound piece edition section 8 totals the scores indicating the weakness of the correlations between the specified sound piece data and the results of the rhythm prediction by each sound piece and requests the outside for the supply of the fresh sound piece data when the results exceed the prescribed value. The supplied fresh sound piece data is additionally registered in a sound piece data base forming section l3. <P>COPYRIGHT: (C)2005,JPO&NCIPI |
