US 10,854,186 B1Granted

Processing audio data received from local devices

AssigneeAmazon Technologies, Inc.

InventorsSanjay Devireddy, Kenneth Edward Cecka, Adam Stevens, Sebastian Pierce-Durance, Naveen Kumar Devaraj, Po-Chen Paul Yang, Federico Dan Rozenberg, Pete Baldridge, Pranov Rai, Todd Greenwalt, Yusuf Goren, Rajiv Jain

Life of this patent

Estimating the term…

patentgrep

Loading patent…

Abstract

A device-management system performs audio processing, such as acoustic echo cancellation or beamforming, in a computing-resource allocation corresponding to a functionally limited device. The device-management system may be a locally-connected network device that is in communication with one or more user devices; the device-management system may also or instead be a remote device that communicates with the user devices using the locally-connected network device. The device-management system may receive audio data from one or more microphones of one or more user devices. To perform acoustic echo cancellation, the device-management system may receive and process time data corresponding to a time of output of audio by the user device.

Claims20

Dependent claims

A computer-implemented method comprising:

receiving, from a system, first audio data;
sending, at a first time and using a network, the first audio data to a first device;
receiving, from the first device, second audio data, the second audio data including a representation of the first audio data;
receiving, from the first device, an indication that the second audio data corresponds to an utterance;
receiving, from the first device, an indication of a second time corresponding to a time of output, by the first device, of audio corresponding to the first audio data;
determining, using the indication of the second time, a time difference between the first time and the second time, wherein the time difference corresponds to a latency of the network;
configuring a filter using the time difference, the filter corresponding to a delay;
processing the first audio data using the filter to create delayed first audio data;
performing acoustic echo cancellation using the delayed first audio data and the second audio data to remove at least a portion of the first audio data from the second audio data to generate third audio data;
and
sending, to the system, the third audio data.

8 more elements

A system comprising:

at least one processor;
and
at least one memory including instructions that, when executed by the at least one processor, cause the system to:
send, to a first device, first audio data,
cause the first device to output first audio corresponding to the first audio data,
receive, from the first device, second audio data, the second audio data including a representation of at least a portion of the first audio,
receive from the first device, time data corresponding to a time of output of the first audio,
process the first audio data based at least in part on the time data to generate delayed first audio data, the delayed first audio data having a temporal delay with respect to the first audio data in accordance with the time data,
process the second audio data and the time data to remove at least a portion of the first audio data from the second audio data to generate third audio data,
determine that the third audio data includes a representation of a wakeword, and
send, to a service-provider system, the third audio data.

8 more elements

Dependencies are inferred from the claim text.