主权项 |
1. A method comprising:
obtaining particular audio information using a client computing device in a first power mode in which obtained audio information is not transcribed into text; detecting, in the particular audio information, audio name information indicative of a name of the client computing device without transcribing the particular audio information into text; switching, based on detecting, to a second power mode that differs from the first power mode and in which obtained audio information is transcribed into text; obtaining, in the second power mode, additional audio information; transmitting the additional audio information to a server computing device; following transmittal of the additional audio command information and prior to receipt from the server computing device of a response to the additional audio information:
generating, by the client computing device in the second power mode, an audio acknowledgement of processing of the additional audio information, wherein generation of the audio acknowledgement is independent of information received from the server computing device; andproviding, for output by the client computing device, the audio acknowledgement for a user of the client computing device; receiving, from the server computing device, the response to the additional audio information, with the response differing from the audio acknowledgement; and providing, for output, the response to the user of the client computing device. |