US 11,145,299 B2Granted

Managing voice interface devices

AssigneeX Development LLC

InventorsMeltem Oktem, Max Benjamin Braun

Life of this patent

Estimating the term…

Loading patent…

Abstract

Methods, systems, and apparatus, including computer-readable storage devices, for managing voice interface devices. In some implementations, messages are received from a plurality of devices, each of the messages indicating a respective voice input detected by the device that sent the message. Audio signatures are obtained for the voice inputs detected by the plurality of devices. The audio signatures for the voice inputs and times that the voice inputs were detected are evaluated. Based on the evaluation, at least some of the plurality of devices are grouped to form a group of multiple devices that detected a same user utterance. A device from the group is selected to respond to the user utterance, and the multiple devices in the group are managed so that only the selected device outputs a synthesized speech response to the user utterance.

Claims19

Dependent claims

A method performed by one or more computers, the method comprising:

receiving, by the one or more computers, messages from a plurality of devices that have collectively detected two or more different voice inputs that overlap in time, each of the messages indicating a respective voice input of the two or more different voice inputs that was detected by the device that sent the message, the plurality of devices including a robot;
obtaining, by the one or more computers and based on the messages, an audio signature for each of the two or more different voice inputs that overlap in time and that were collectively detected by the plurality of devices;
receiving, by the one or more computers, context data from the robot that describes conditions in an environment of the robot, the context data being based on sensor data captured by one or more sensors of the robot;
evaluating, by the one or more computers, the audio signatures for the two or more different voice inputs that overlap in time, and times that the voice inputs were detected;
based on evaluating the audio signatures for the two or more different voice inputs that overlap in time and the times that the voice inputs were detected, grouping, by the one or more computers, at least some of the plurality of devices to form a group of multiple devices that are determined, based on the evaluation of the audio signatures, to have detected a same one of the two or more different voice inputs that overlap in time, and that are each configured to respond to the one of the two or more different voice inputs, the group including the robot;
selecting, by the one or more computers, the robot from among the multiple devices in the group based on (i) device types of the devices in the group, and (ii) the context data provided by the robot;
and
managing, by the one or more computers, the multiple devices in the group so that only the robot outputs a response to the one of the two or more different voice inputs that overlap in time.

5 more elements

A system comprising:

one or more computers;
and
one or more non-transitory computer-readable media storing instructions that, when executed by the one or more computers, cause the one or more computers to perform operations comprising:
receiving, by the one or more computers, messages from a plurality of devices that have collectively detected two or more different voice inputs that overlap in time, each of the messages indicating a respective voice input of the two or more different voice inputs that was detected by the device that sent the message;
obtaining, by the one or more computers and based on the messages, an audio signature for each of the two or more different voice inputs that overlap in time and that were collectively detected by the plurality of devices;
evaluating, by the one or more computers, the audio signatures for the two or more different voice inputs that overlap in time, and times that the voice inputs were detected;
based on evaluating the audio signatures for the two or more different voice inputs that overlap in time and the times that the voice inputs were detected, grouping, by the one or more computers, at least some of the plurality of devices to form a group of multiple devices that are determined, based on the evaluation of the audio signatures, to have detected a same one of the two or more different voice inputs that overlap in time and that are each configured to respond to one of the two or more different voice inputs;
selecting, by the one or more computers, a device from among the multiple devices in the group based on a direction of travel of a user with respect to the selected device;
and
managing, by the one or more computers, the multiple devices in the group so that only the selected device outputs a response to the one of the two or more different voice inputs that overlap in time.

7 more elements

One or more non-transitory computer-readable media storing instructions that, when executed by one or more computers, cause the one or more computers to perform operations comprising:

receiving, by the one or more computers, messages from a plurality of devices that have collectively detected two or more different voice inputs that overlap in time, each of the messages indicating a respective voice input of the two or more different voice inputs that was detected by the device that sent the message;
obtaining, by the one or more computers and based on the messages, an audio signature for each of the two or more different voice inputs that overlap in time and that were collectively detected by the plurality of devices;
evaluating, by the one or more computers, the audio signatures for the two or more different voice inputs that overlap in time, and times that the voice inputs were detected;
based on evaluating the audio signatures for the two or more different voice inputs that overlap in time and the times that the voice inputs were detected, grouping, by the one or more computers, at least some of the plurality of devices to form a group of multiple devices that are determined, based on the evaluation of the audio signatures, to have detected a same one of the two or more different voice inputs that overlap in time and that are each configured to respond to one of the two or more different voice inputs, wherein the multiple devices in the group are each determined to be located in a same location;
receiving, by the one or more computers, data indicating a request from a particular device in the group, sent by the particular device after the one of the two or more different voice inputs was detected, for the particular device to respond to the one of the two or more different voice inputs;
selecting, by the one or more computers, the particular device to respond to the one of the voice inputs based on the request;
and
managing, by the one or more computers, the multiple devices in the group so that only the particular device outputs a response to the one of the two or more different voice inputs that overlap in time, comprising (i) allowing the particular device to respond to the one of the two or more different voice inputs that overlap in time and (ii) sending, to each of the other devices in the group, a command suppressing response to the one of the two or more different voice inputs that overlap in time by the other devices.

5 more elements

Dependencies are inferred from the claim text.