Speech synthesizer

A speech synthesizer comprising:

• an input unit to receive an input of a sentence;
• a generation unit to generate synthetic speech data from the sentence inputted to the input unit;
• a linguistic processing unit to generate a phonogram string, being segmented into a plurality of segmental parts, from the sentence received by the input unit;
• an accumulation unit to accumulate the phonogram string generated by the linguistic processing unit in a recording medium;
• a collation unit implemented in a processor to compare, when a new phonogram string is generated by the linguistic processing unit, corresponding segmental parts of the new phonogram string with a collation target phonogram string included in a predetermined range tracing back from the new phonogram string, to assign a predetermined value to one or more segmental parts of which the new phonogram string and the collation target phonogram string does not matches, and to calculate, with respect to each of the plurality of segmental parts, a variation degree of the new phonogram string from the collation target phonogram string based on predetermined values assigned to the one or more segmental parts;
• a calculation unit to calculate a variation coefficient for each of the plurality of segmental parts in the new phonogram string based on the variation degree of each of the plurality of segmental parts in the new phonogram string calculated by the collation unit, a normal sentence length of the new phonogram, a preset normal phoneme length of each of the plurality of segmental parts in the new phonogram string, and a preset coefficient minimum value;
• and
• a correction unit to correct the synthetic speech data with the variation coefficient.