Multiple-source speech dialog input

A method comprising:

• engaging in a speech dialog with a user to determine an intent of the user, wherein engaging in the speech dialog comprises engaging in a first dialog turn and, a second dialog turn, and a third dialog turn with the user;
• wherein engaging in the first dialog turn comprises:
• receiving a first audio signal produced by a first device, the first audio signal representing first user speech;
• and
• determining, based at least in part on providing the first audio signal to a speech service, a first meaning of the first user speech;
• wherein engaging in the second dialog turn comprises:
• receiving a second audio signal that is produced using a microphone of a second device, the second audio signal representing second user speech;
• and
• determining, based at least in part on providing the second audio signal to the speech service, a second meaning of the second user speech based;
• and
• wherein engaging in the third dialog turn comprises:
• receiving, based at least in part on an actuation of a talk control of the first device within a predefined time period after engaging in the second dialog turn, a third audio signal from the first device, the third audio signal representing third user speech;
• and
• determining a third meaning of the third user speech.

A method comprising:

• engaging in a speech dialog to determine an intent of a user, wherein engaging in the speech dialog comprises engaging in a first dialog turn and a second dialog turn;
• wherein engaging in the first dialog turn comprises:
• determining an actuation of a talk control associated with a first device;
• receiving a first audio signal produced by the first device, wherein the first audio signal represents first user speech;
• and
• determining a first meaning of the first user speech;
• wherein engaging in the second dialog turn comprises:
• receiving, after engaging in the first dialog turn, a second audio signal representing second user speech, the second audio signal produced using a microphone of a second device;
• and
• determining a second meaning based at least in part on:
• receiving a third audio signal produced by the first device based at least in part on an actuation of the talk control of the first device within a predefined time period after the first dialog turn, the third audio signal representing third user speech;
• or
• receiving the second audio signal based at least in part on the predefined time period elapsing without actuation of the talk control.

A method comprising:

• engaging in a speech dialog with a user to determine an intent of the user, wherein engaging in the speech dialog comprises engaging in a first dialog turn, a second dialog turn, and a third dialog turn with the user
• wherein engaging in the first dialog turn comprises:
• receiving a first audio signal produced by a first device, the first audio signal representing first user speech;
• and
• determining, based at least in part on providing the first audio signal to a speech service, a first meaning of the first user speech;
• wherein engaging in the second dialog turn comprises:
• receiving a second audio signal produced using a microphone of a second device, the second audio signal representing second user speech;
• determining, based at least in part on providing the second audio signal to the speech service, a second meaning of the second user speech;
• and
• wherein engaging in the third dialog turn comprises:
• receiving, based at least in part on a predefined time period elapsing after engaging in the second dialog turn without actuation of a talk control of the first device, a third audio signal from the second device, the third audio signal representing third user speech;
• and
• determining a third meaning of the third user speech.