CPC G10L 15/22 (2013.01) [G10L 15/08 (2013.01); G10L 2015/088 (2013.01); G10L 2015/223 (2013.01)] | 20 Claims |
5. A computer-implemented method comprising:
determining first audio data corresponding to a first portion of an utterance;
determining, using a first component of a user device, that the first audio data includes a first representation of a first wakeword corresponding to a first speech-processing system;
sending, to the first speech-processing system, first data corresponding to the first audio data;
determining second audio data corresponding to a second portion of the utterance;
determining, using a second component of the user device, that the second audio data includes a second representation of a second wakeword corresponding to a second speech-processing system;
determining that the user device is in communication with the first speech-processing system;
sending, to the first speech-processing system, second data corresponding to the second audio data; and
based at least in part on the user device being in communication with the first speech-processing system, refraining from sending the second data to the second speech-processing system.
|