VOICE SYNTHESIZING METHOD, DICTIONARY CONSTRUCTING METHOD FOR VOICE SYNTHESIS, VOICE SYNTHESIZER AND COMPUTER READABLE MEDIUM RECORDED WITH VOICE SYNTHESIS PROGRAM

摘要

PROBLEM TO BE SOLVED: To enable voice messages which are suitable for purposes having high entertainment property (entertainingness) like video games and which are made to correspond to the personality of a speaker, the emotion and the situation at the time of a speaking or various contents of the speaking to be produced. SOLUTION: Plural units (tasks) of a voice synthesis processing in which at least, one of the emotion, the situation of a speaker or at the time of a speaking or contents of the speaking is different are set (s1). Word dictionaries, rhythm dictionaries and waveform dictionaries corresponding to respective tasks are constructed (s2). When character strings which are to be synthesized are inputted together with the specification of a task from a game system or the like, the character strings are subjected to the voice synthesis processing by using the word dictionary, the rhythm dictionary and the waveform dictionary of the specified task (s3).