ARBITRATION BETWEEN VOICE-ENABLED DEVICES

摘要

Architectures and techniques for selecting a voice-enabled device to handle audio input that is detected by multiple voice-enabled devices are described herein. In some instances, multiple voice-enabled devices may detect audio input from a user at substantially the same time, due to the voice-enabled devices being located within proximity to the user. The architectures and techniques may analyze a variety of audio signal metric values for the voice-enabled devices to designate a voice-enabled device to handle the audio input.

主权项

1. A method comprising:
determining, by a computing device, that a first voice-enabled device and a second voice-enabled device received audio input at substantially a same time; receiving, by the computing device and from the first voice-enabled device, a first audio signal metric value indicating a signal-to-noise ratio associated with a first beamformed audio signal, the first beamformed audio signal having been determined, at the first voice-enabled device, for the audio input received at the first voice-enabled device, the first beamformed audio signal being determined for a direction relative to the first voice-enabled device; receiving, by the computing device and from the second voice-enabled device, a second audio signal metric value indicating a signal-to-noise ratio associated with a second beamformed audio signal, the second beamformed audio signal having been determined, at the second voice-enabled device, for the audio input received at the second voice-enabled device, the second beamformed audio signal being determined for a direction relative to the second voice-enabled device; determining, by the computing device, that the signal-to-noise ratio associated with the first beamformed audio signal is greater than the signal-to-noise ratio associated with the second beamformed audio signal; processing, by the computing device, the first beamformed audio signal using one or more speech recognition techniques; performing, by the computing device, a task associated with the audio input; and sending, by the computing device, an instruction to the first voice-enabled device, the instruction requesting that the first voice-enabled device output an indication that the task has been completed.