Reducing response latency of intelligent automated assistants

A non-transitory computer-readable storage medium comprising computer-executable instructions, which when executed by one or more processors, causes the one or more processors to:

• receive, from a user, a speech input containing a user request;
• transmit, to a server, a representation of the speech input;
• receive, from the server, a domain signal representing a relevant domain associated with the user request;
• determine whether the relevant domain is associated with a predefined action of a set of predefined actions supported by the electronic device;
• in response to determining that the relevant domain is associated with a predefined action on the electronic device, perform the predefined action;
• receive, from the server, data content relevant to satisfying the user request;
• and
• output a result based on the data content to at least partially satisfy the user request.

A system comprising:

• one or more processors;
• memory storing computer-readable instructions, which when executed by the one or more processors, causes the one or more processors to:
• receive, from a user, a speech input containing a user request;
• transmit, to a server, a representation of the speech input;
• receive, from the server, a domain signal representing a relevant domain associated with the user request;
• determine whether the relevant domain is associated with a predefined action of a set of predefined actions supported by the electronic device;
• in response to determining that the relevant domain is associated with a predefined action on the electronic device, perform the predefined action;
• receive, from the server, data content relevant to satisfying the user request;
• and
• output a result based on the data content to at least partially satisfy the user request.