| 摘要 |
PURPOSE:To enable a user to easily understand the content of speech without specially paying attention by regularly synthesizing an accent or a toning down included in the natural voice of a sentence sounded by a human body. CONSTITUTION:Since the control of rhythm by a prominence generation rule is obtained based on the quantitative analysis of the natural voice, the synthetic speech like human body's speech is accomplished by giving the natural human accent and toning down to the speech synthesized from an inputted document. Therefore, the user can easily understand the content of the speech without specially paying attention and a burden imposed on the user is remarkably lightened. Especially, the effect of reducing fatigue at the time of long-time work such as proofreading and checking a newspaper is remarkable, and the improvement of working efficiency is expected. |
