# US 2025/0157461 A1 · Wakeword detection using a secondary microphone

> Agents: this data is available as JSON from the patentgrep API and MCP server — see https://patentgrep.com/llms.txt

- Number: US 2025/0157461 A1
- Document ID: US20250157461A1
- Status: Published application
- Kind: A1
- Application number: 18/985,185
- Filed: 2024-12-18
- Published: 2025-05-15
- Earliest claimed: 2019-02-11
- Assignees: Amazon Technologies, Inc.
- Applicants: Amazon Technologies, Inc.
- Inventors: Andrew Mitchell; Gabor Nagy
- Web page: https://patentgrep.com/patent/US20250157461A1

## CPC

- G10L 15/08: Speech classification or search
- G10L 15/32: Multiple recognisers used in sequence or in parallel; Score combination systems therefor, e.g. voting systems
- G10L 15/22: Procedures used during a speech recognition process, e.g. man-machine dialogue
- G10L 15/30: Distributed recognition, e.g. in client-server systems, for mobile phones or network applications
- G10L 2015/088: {Word spotting}
- G10L 2015/223: {Execution procedure of a spoken command}
- G10L: SPEECH ANALYSIS TECHNIQUES OR SPEECH SYNTHESIS; SPEECH RECOGNITION; SPEECH OR VOICE PROCESSING TECHNIQUES; SPEECH OR AUDIO CODING OR DECODING

## Abstract

Techniques for capturing spoken user inputs while a device is prevented from capturing such spoken user inputs are described. When a first device becomes incapable of capturing spoken user inputs intended for a system, a second device, for capturing such spoken user inputs, may be identified. The second device may be identified based on the second device being connected to a same vehicle computing system as the first device. The second device may be enabled to capture spoken user inputs, intended for the system, until the first device is again able to capture such spoken user inputs.

## Claims

### Claim at position 1

-20. (canceled)

### Claim 21

A computer-implemented method, comprising:
capturing, by a first device, first audio representing a first spoken input by a first user;
determining, by the first device, first audio data representing the first audio;
causing speech processing to be performed using the first audio data;
determining a second device associated with the first device is to capture further audio corresponding to further spoken inputs by the first user;
capturing, by a second device, second audio representing a second spoken input by the first user;
determining, by the second device, second audio data representing the second audio; and
causing speech processing to be performed using the second audio data.

### Claim 22 (depends on 21)

The computer-implemented method of claim 21, further comprising:
determining network data corresponding to a network connection of the second device,
wherein determining the second device is to capture further audio is based at least in part on the network data.

### Claim 23 (depends on 21)

The computer-implemented method of claim 21, further comprising:
determining position data corresponding to the second device,
wherein determining the second device is to capture further audio is based at least in part on the position data.

### Claim 24 (depends on 21)

The computer-implemented method of claim 21, further comprising:
before determining the second device is to capture further audio, determining the first device corresponds to a voice call,
wherein determining the second device is to capture further audio is based at least in part on the first device corresponding to a voice call.

### Claim 25 (depends on 21)

The computer-implemented method of claim 21, wherein:
the first device is associated with a first profile;
the second device is associated with the first profile; and
determining the second device is to capture further audio is based at least in part on the first device and the second device being associated with the first profile.

### Claim 26 (depends on 21)

The computer-implemented method of claim 21, further comprising:
receiving, by the second device, a model corresponding to the first user and configured to be used to process audio data; and
processing, by the second device, the second audio data using the model.

### Claim 27 (depends on 21)

The computer-implemented method of claim 21, wherein causing speech processing to be performed using the second audio data comprises causing speech processing to be performed using the second audio data, as the second audio data originated with the first device.

### Claim 28 (depends on 21)

The computer-implemented method of claim 21, further comprising, prior to capturing, by the second device, the second audio:
receiving, by the second device, an instruction to process audio corresponding to a detected spoken input.

### Claim 29 (depends on 21)

The computer-implemented method of claim 21, further comprising, prior to capturing, by the second device, the second audio:
outputting a notification indicating that the second device is configured for speech capture.

### Claim 30 (depends on 21)

The computer-implemented method of claim 21, further comprising after causing speech processing to be performed using the second audio data:
determining the first device is to capture further audio corresponding to further spoken inputs by the first user;
capturing, by the first device, third audio representing a third spoken input by a first user;
determining, by the first device, third audio data representing the third audio; and
causing speech processing to be performed using the third audio data.

### Claim 31

A system comprising:
at least one processor; and
at least one memory comprising instructions that, when executed by the at least one processor, cause the system to:
capture, by a first device, first audio representing a first spoken input by a first user;
determine, by the first device, first audio data representing the first audio;
cause speech processing to be performed using the first audio data;
determine a second device associated with the first device is to capture further audio corresponding to further spoken inputs by the first user;
capture, by a second device, second audio representing a second spoken input by the first user;
determine, by the second device, second audio data representing the second audio; and
cause speech processing to be performed using the second audio data.

### Claim 32 (depends on 31)

The system of claim 31, wherein the at least one memory further comprises instructions that, when executed by the at least one processor, further cause the system to:
determine network data corresponding to a network connection of the second device,
wherein determination that the second device is to capture further audio is based at least in part on the network data.

### Claim 33 (depends on 31)

The system of claim 31, wherein the at least one memory further comprises instructions that, when executed by the at least one processor, further cause the system to:
determine position data corresponding to the second device,
wherein determination that the second device is to capture further audio is based at least in part on the position data.

### Claim 34 (depends on 31)

The system of claim 31, wherein the at least one memory further comprises instructions that, when executed by the at least one processor, further cause the system to:
before determination that the second device is to capture further audio, determine the first device corresponds to a voice call,
wherein determination that the second device is to capture further audio is based at least in part on the first device corresponding to a voice call.

### Claim 35 (depends on 31)

The system of claim 31, wherein:
the first device is associated with a first profile;
the second device is associated with the first profile; and
determination that the second device is to capture further audio is based at least in part on the first device and the second device being associated with the first profile.

### Claim 36 (depends on 31)

The system of claim 31, wherein the at least one memory further comprises instructions that, when executed by the at least one processor, further cause the system to:
receive, by the second device, a model corresponding to the first user and configured to be used to process audio data; and
process, by the second device, the second audio data using the model.

### Claim 37 (depends on 31)

The system of claim 31, wherein the instructions that cause the system to cause speech processing to be performed using the second audio data comprise instructions that, when executed by the at least one processor, cause the system to cause speech processing to be performed using the second audio data, as the second audio data originated with the first device.

### Claim 38 (depends on 31)

The system of claim 31, wherein the at least one memory further comprises instructions that, when executed by the at least one processor, further cause the system to, prior to capture, by the second device, of the second audio:
receive, by the second device, an instruction to process audio corresponding to a detected spoken input.

### Claim 39 (depends on 31)

The system of claim 31, wherein the at least one memory further comprises instructions that, when executed by the at least one processor, further cause the system to, prior to capture, by the second device, of the second audio:
output a notification indicating that the second device is configured for speech capture.

### Claim 40 (depends on 31)

The system of claim 31, wherein the at least one memory further comprises instructions that, when executed by the at least one processor, further cause the system to, after causing speech processing to be performed using the second audio data:
determine the first device is to capture further audio corresponding to further spoken inputs by the first user;
capture, by the first device, third audio representing a third spoken input by a first user;
determine, by the first device, third audio data representing the third audio; and
cause speech processing to be performed using the third audio data.
