CPC G10L 15/22 (2013.01) [G10L 15/24 (2013.01); H04R 1/406 (2013.01); H04R 3/005 (2013.01); G10L 2015/223 (2013.01); G10L 2015/228 (2013.01)] | 20 Claims |
1. A method implemented by one or more processors, the method comprising:
receiving audio data that is captured via one or more microphones of a computing device, wherein the audio data captures a spoken utterance, of a user, that is directed to an automated assistant of the computing device;
determining, based on processing the audio data:
that the spoken utterance requests performance, by the automated assistant, of an action, and
that the user is non-authenticated;
causing performance of the action in response to determining that the spoken utterance requests performance of the action;
in response to determining that the user is non-authenticated:
storing, only transiently until one or more purge conditions are satisfied, circumstantial data and an association of the circumstantial data to the action, the circumstantial data characterizing one or more circumstantial conditions associated with the user providing the spoken utterance;
receiving, at the computing device and prior to the one or more purge conditions being satisfied, further user interface input;
comparing the circumstantial data, stored in association with the action, to further circumstantial data characterizing one or more circumstantial conditions associated with the further user interface input; and
in response to the comparing indicating a threshold degree of similarity:
causing performance of a further action that is based on both the further user interface input and the action.
|