Generating objectively evaluated sufficiently natural synthetic speech from text by using selective paraphrases

A method for generating synthetic speech, comprising acts of:

• storing a plurality of phoneme segment data pieces indicating a plurality of sounds of phonemes different from each other;
• generating voice data representing synthetic speech of text by receiving an inputted text, reading out the phoneme segment data pieces corresponding to respective phonemes indicating the pronunciation of the inputted text, and connecting the read-out phoneme segment data pieces to each other;
• computing a score indicating naturalness of the synthetic speech of the text, on the basis of the voice data;
• storing a plurality of notations each comprising a word or phrase, the plurality of notations comprising a plurality of first notations and a plurality of second notations, each second notation being a paraphrase of a respective first notation;
• searching the text for a notation matching any of the first notations, and replacing a matching notation with the second notation corresponding to the first notation;
• determining whether the score indicates that the synthetic speech is sufficiently natural;
• and
• if the score indicates that the synthetic speech is sufficiently natural, outputting the generated voice data;
• and
• if the score indicates that the synthetic speech is not sufficiently natural, generating revised text by replacing at least one other notation in the inputted text matching a first notation with a corresponding second notation, and generating voice data for the revised text.

At least one storage device having instructions encoded thereon which, when executed, perform a method of generating synthetic speech, the method comprising acts of:

• storing a plurality of phoneme segment data pieces indicating a plurality of sounds of phonemes which are different from each other;
• and
• generating voice data representing synthetic speech of text by receiving an inputted text, reading out phoneme segment data pieces that correspond to respective phonemes indicating the pronunciation of the inputted text, and connecting the read-out phoneme segment data pieces to each other;
• computing a score indicating naturalness of the synthetic speech of the text, on the basis of the voice data;
• storing a plurality of notations each comprising a word or phrase, the plurality of notations comprising a plurality of first notations and a plurality of second notations, each of the second notations being a paraphrase of a respective first notation;
• and
• searching the text for a notation matching any of the first notations and replacing a matching notation with the second notation corresponding to the first notation;
• and
• determining whether the score indicates that the synthetic speech is sufficiently natural;
• and
• if the score indicates that the synthetic speech is sufficiently natural, outputting the generated voice data;
• and
• if the score indicates that the synthetic speech is not sufficiently natural, generating revised text by replacing at least one other notation in the inputted text matching a first notation with a respective second notation, and generating voice data for the revised text.