CPC G10L 15/22 (2013.01) [G06F 3/0482 (2013.01); G10L 13/047 (2013.01); H04L 67/306 (2013.01); H04M 3/4936 (2013.01)] | 19 Claims |
1. A method implemented by one or more processors, the method comprising:
receiving, from a given user via a client device associated with the given user, user input to initiate an assisted call;
determining, based on the user input:
an entity to engage with, on behalf of the given user, during the assisted call, and
a task to be performed, on behalf of the given user, during the assisted call;
determining, for one or more candidate parameters stored in association with the task and/or the entity, and based at least in part on a dialog with the given user, one or more corresponding values to be used in automatically generating synthesized speech, during the assisted call, in performing the task;
initiating, using the client device associated with given user, performing of the assisted call;
determining, during the performing of the assisted call and based on processing audio data, of the assisted call, that captures an utterance of an additional user associated with the entity, that a particular value, associated with an additional parameter and which was not previously determined during the dialog with the given user, is requested by the additional user; and
in response to determining that the particular value associated with the additional parameter is requested:
causing the client device to render, outside of the assisted call, a notification that identifies the additional parameter, and that requests further user input for the particular value;
prior to receiving any further input that is responsive to the notification, continuing the assisted call, wherein continuing the assisted call comprises rendering one or more instances of synthesized speech, as part of the assistant call and for presentation to the additional user, that are based on one or more of the corresponding values for the candidate parameters that were previously determined during the dialog with the given user but have not yet been provided to the additional user during the assisted call;
determining, during continuing the assisted call, whether further user input, that is responsive to the notification and that identifies the particular value for the additional parameter, is received within a threshold duration of time; and
in response to determining the further user input is received within the threshold duration of time:
rendering further synthesized speech, as part of the assisted call, that is based on the particular value.
|