摘要 |
PROBLEM TO BE SOLVED: To facilitate construction of a database used for corpus-based speech synthesis.SOLUTION: A data generation system generates data to be used for corpus-based speech synthesis processing utilizing speech data of one or a plurality of objects to be processed. The data generation system includes: a means of holding data of a sequence of phonemes corresponding to the speech data of the objects to be processed; a storage means of storing one or a plurality of model data generated by modeling feature quantities of speech data of one or a plurality of speakers and information on boundary positions associated with the phonemes corresponding to the speech data; a means of generating boundary position information showing boundary positions associated with the respective phonemes with respect to the speech data of the objects to be processed utilizing the speech data of the objects to be processed, the held data of the sequence of phonemes, and one of the model data stored in the storage means; and a means of generating data to be used for speech processing using the speech data of the object to be processed and the generated boundary position information. |