CPC G10L 15/22 (2013.01) [G06F 3/167 (2013.01); G10L 15/30 (2013.01); G10L 2015/088 (2013.01); G10L 2015/227 (2013.01)] | 25 Claims |
1. A method comprising:
tracking, by a computing system, availability of a plurality of voice assistant services, each of the voice assistant services configured to utilize a different respective recognizer for voice input and command interpretation, the tracking including receiving messages indicating wake words corresponding to each of the plurality of voice assistant services;
receiving audio from a microphone;
determining, using the messages, a plurality of wake words corresponding to the plurality of voice assistant services, the plurality of wake words comprising a first wake word for a first voice assistant service provided by a first device and a second wake word for a second voice assistant service provided by a second device;
detecting the first wake word in the audio corresponding to the first voice assistant service of the plurality of voice assistant services; and
in response to detecting the first wake word, activating the first voice assistant service by sending a message to trigger launch of the first voice assistant service, thereby establishing an audio link between the microphone and the first voice assistant service for voice input by a user.
|