| 摘要 |
PURPOSE:To obtain the voice input/output device being optimum for use having hands full by constituting the voice input/output device of a transmitting/ receiving means, a voice recognizing means, a computer and a voice response means. CONSTITUTION:A transmitting/receiving means (for instance, a fixed station) 7 receives a sound signal from a microphone 1, and sends a composite sound signal to an earphone 2. A voice recognizing device 21 executes a voice recognition with regard to a sound signal of a higher level than a threshold level, and a host computer 9 sends out voice information based on a result of the voice recognition, and also, varies the threshold level in accordance with a prescribed sequence. A voice response device 10 synthesizes a voice, based on the voice information, and sends a synthesized sound signal to the transmitting/receiving means 7. According to this constitution, by uttering loudly at the time of starting a voice input, an operation which is turned ON manually by a voice input switch of a handset can be executed as proxy. Accordingly, even in a place where a noise is high, when only the first voice is uttered loudly, a series of sequences are performed, thereafter, hands become free completely. |
