Delayed responses by computational assistant

A method implemented by one or more processors, the method comprising:

• receiving a representation of an utterance spoken at a computing device;
• identifying, based on the utterance, a task to be performed by a computational assistant;
• determining, based on the task, to place a call with an entity, on behalf of a user of the computing device, to perform the task;
• outputting, for playback by one or more speakers operably connected to the computing device, synthesized voice data that informs the user that complete performance of the task will not be immediate;
• initiating performance of the call with the entity, on behalf of the user, to perform the task;
• and
• during performance of the call:
• receiving a representation of an additional utterance spoken at the computing device;
• determining, based on the additional utterance, to modify performance of the task;
• and
• causing the computational assistant to complete modified performance of the task.

A system comprising:

• at least one processor;
• and
• memory storing instructions that, when executed, cause the at least one processor to:
• receive a representation of an utterance spoken at a computing device;
• identify, based on the utterance, a task to be performed by a computational assistant;
• determine, based on the task, to place a call with an entity, on behalf of a user of the computing device, to perform the task;
• output, for playback by one or more speakers operably connected to the computing device, synthesized voice data that informs the user that complete performance of the task will not be immediate;
• initiate performance of the call with the entity, on behalf of the user, to perform the task;
• and
• during performance of the call:
• receive a representation of an additional utterance spoken at the computing device;
• determine, based on the additional utterance, to modify performance of the task;
• and
• cause the computational assistant to complete modified performance of the task.