CPC G06F 3/167 (2013.01) [G06F 3/0481 (2013.01); G06F 3/0484 (2013.01); G06F 3/04886 (2013.01); G06F 40/117 (2020.01); G06F 40/143 (2020.01); G06F 40/174 (2020.01); G06F 40/30 (2020.01); G10L 15/22 (2013.01); G10L 15/26 (2013.01)] | 20 Claims |
1. A method implemented by one or more processors, the method comprising:
receiving a selection of a keyboard element that is provided to a graphical user interface of a keyboard application that is being rendered at a computing device,
wherein the keyboard application is separate from an automated assistant that is accessible at the computing device, and
wherein the keyboard application is provided by a third-party entity that is separate from a first-party entity that provided the computing device and/or the automated assistant;
receiving, subsequent to receiving the selection of the keyboard element, a spoken utterance from a user,
wherein the user is accessing a particular application that includes an entry field when the user provides the spoken utterance;
causing, based on the spoken utterance, a candidate text string to be determined,
wherein the candidate text string characterizes at least a portion of the spoken utterance provided by the user, and
wherein the candidate text string is determined by the automated assistant that is provided by the first-party entity;
determining whether to incorporate the candidate text string into the entry field or to incorporate non-textual visual content, that is determined based on the candidate text string, into the entry field; and
in response to determining to incorporate the non-textual visual content into the entry field:
causing the keyboard application, that is provided by the third-party entity, to incorporate the non-textual visual content into the entry field of the particular application.
|