US 10,546,583 B2Granted

Context-based device arbitration

AssigneeAmazon Technologies, Inc.

InventorsJoseph White, Ravi Kiran Rachakonda, Vinodth Kumar Mohanam, Lalithkumar Rajendran, Deepak Uttam Shah, Maziyar Khorasani, Venkata Snehith Cherukuri

Life of this patent

Estimating the term…

patentgrep

Loading patent…

Abstract

This disclosure describes, in part, context-based device arbitration techniques to select a voice-enabled device from multiple voice-enabled devices to provide a response to a command included in a speech utterance of a user. In some examples, the context-driven arbitration techniques may include determining a ranked list of voice-enabled devices that are ranked based on audio signal metric values for audio signals generated by each voice-enabled device, and iteratively moving through the list to determine, based on device states of the voice-enabled devices, whether one of the voice-enabled devices can perform an action responsive to the command. If the voice-enabled devices that detected the speech utterance are unable to perform the action responsive to the command, all other voice-enabled devices associated with an account may be analyzed to determine whether one of the other voice-enabled devices can perform the action responsive to the command in the speech utterance.

Claims20

Dependent claims

A system comprising:

one or more processors;
computer-readable media storing computer-executable instructions that, when executed by the one or more processors, cause the one or more processors to perform operations comprising:
receiving, from a first voice-enabled device, first audio data representing a speech utterance;
receiving, from the first voice-enabled device, a first audio signal metric value indicating a first signal-to-noise ratio associated with the first audio data;
receiving, from a second voice-enabled device, second audio data representing the speech utterance;
receiving, from the second voice-enabled device, a second audio signal metric value indicating a second signal-to-noise ratio associated with the second audio data;
determining that the first signal-to-noise ratio is greater than the second signal-to-noise ratio;
identifying device state data associated with the first voice-enabled device;
generating, using automatic speech recognition (ASR) on at least one of the first audio data or the second audio data, text data corresponding to the speech utterance;
determining, using natural language understanding (NLU) on the text data, intent data associated with the speech utterance, the intent data representing a request for a client device to perform an action;
determining, based at least in part on the device state data, that the first voice-enabled device is capable of performing the action responsive to the speech utterance;
determining a command to cause the first voice-enabled device to perform the action;
and
sending, to the first voice-enabled device, data indicating the command.

11 more elements

A system comprising:

one or more processors;
computer-readable media storing computer-executable instructions that, when executed by the one or more processors, cause the one or more processors to perform operations comprising:
receiving a first device identifier of a first device;
receiving first audio data associated with the first device identifier, the first audio data representing a speech utterance;
receiving a second device identifier of a second device;
receiving second audio data associated with the second device identifier, the second audio data representing the speech utterance;
determining intent data associated with the speech utterance, the intent data representing a machine response for a device to perform responsive to the speech utterance;
identifying first device state data associated with the first device;
identifying second device state data associated with the second device;
based at least in part on the second device state data, determining the second device is to be used for the machine response;
determining command data to cause the second device to perform the machine response;
and
sending, to the second device, the command data to perform the machine response.

10 more elements

Dependencies are inferred from the claim text.

Facts

Application: 15/691,460Filed 30 Aug 2017
Published: US 2019/0066670 A128 Feb 2019
Granted: 28 Jan 2020
Term ends: Not estimatedThe source records don’t support an estimate.

Classification6 codes

G10L 15/22
Speech recognition: procedures used during a speech recognition process, e.g. man-machine dialogue
G10L 15/1815
Using natural language modelling: semantic context, e.g. disambiguation of the recognition hypotheses based on word meaning
G10L 15/28
Speech recognition: constructional details of speech recognition systems
G10L 25/84
Detection of presence or absence of voice signals: for discriminating voice from noise