| 摘要 |
PROBLEM TO BE SOLVED: To provide a method in which phonemes of a target language are assigned to each of the basic phoneme units of a set of basic phoneme units. SOLUTION: A basic phoneme unit is expressed by each of the basic phoneme models generated through the utilization of voice data in which a source language is made usable. In a first step of the method, at least two voice data control assigning methods (1 and 2) are used to assign the target language to each of the phoneme units. In a second step, detection is made to determine whether individual phoneme is agreeably assigned to a same basic phoneme unit employing a majority of various methods or not. In this case, a basic phoneme unit assigned by many is assigned to respective phoneme. In other case, one basic phoneme unit is selected from all basic phoneme units assigned by at least one method while the degree of similarity is used in accordance with the assigned phoneme and symbolic pronunciation display of the basic phoneme unit. |
