| CPC G06F 16/951 (2019.01) [G06F 16/3334 (2019.01); G10L 13/08 (2013.01); G10L 15/08 (2013.01); G10L 15/22 (2013.01); G10L 15/26 (2013.01); G10L 15/30 (2013.01); H04L 12/1827 (2013.01); H04L 51/02 (2013.01); H04L 51/18 (2013.01); H04M 3/56 (2013.01); G10L 2015/088 (2013.01); G10L 2015/223 (2013.01); H04L 51/04 (2013.01)] | 20 Claims |

|
1. A computer-implemented method executed on data processing hardware causes the data processing hardware to perform operations comprising:
while operating in a passive monitoring mode:
receiving a voice input spoken by a user, the voice input comprising a particular keyphrase followed by a plurality of words and a keyword subsequent to the plurality of words, the keyword indicating that the user has finished speaking a query characterized by the plurality of words; and
without recognizing the content of the voice input spoken by the user, determining that the voice input includes the particular keyphrase;
in response to determining that the voice input includes the particular keyphrase, transitioning from the passive monitoring mode to an active mode and invoking a speech-to-text converter to:
convert the plurality of words in the voice input into a string of text until the keyword is spoken; and
submit the string of text as the query to a network-connected service; and
receiving, from the network-connected service, results related to the query.
|