摘要 |
PROBLEM TO BE SOLVED: To provide a voice synthesizer, a voice synthesizing method, and a program capable of alleviating user's correction burden for improving the quality of synthetic voice.SOLUTION: An input unit receives an input language notation of a natural language for which voice synthesis is to be performed. A storage unit stores correction information indicating a correction content of prosody information while associating the correction information with part-of-speech information and accent phrase information. A correction unit corrects the prosody information generated by the language processing unit on the basis of the correction information if the correction information is stored in the storage unit. A voice synthesis unit performs the voice synthesis corresponding to the language notation on the basis of an intermediate notation including the prosody information reflecting correction by the correction unit. |