摘要 |
<p>PURPOSE: To provide a voice synthesization output method/device which can easily perform the start/stop control of the voice synthesization output. CONSTITUTION: This method/device includes an input part 1 which inputs the commands, data, etc., that are received from users, a display control part 2 which controls the display in response to the input of the part 1, a display part 3 which shows the display screen that is processed at the part 2, and a face image data base 4. The base 4 holds the data on the eyes, noises, mouths, contours and hairs of faces and their changed shape data. Thus each of these shape data can be taken out in response to each request. An input text holding part 5 holds an input text, i.e., an object of voice synthesization. A voice synthesization part 6 converts the text held at the part 6 into the synthetic voices in response to the voice synthesization start/stop command that is designated at the part 1. Then a speaker 7 outputs the synthetic voices obtained at the part 6.</p> |