IP Library Granted Patent US 12700405
Granted Patent B2
US 12700405 · App. 18/327,487 · Granted Aug 4, 2026

Speech-processing system

Inventors: Kunal Dewan Pahwa (Seattle, WA); Patrick Sheehy (Seattle, WA)
Assignee: Amazon Technologies, Inc.
G10L15/22G06F3/167G06N3/047G10L13/08G10L15/083G10L2015/088G10L2015/223
View Patent ↗
Loading inventors, assignments & file history…
Monitor This Case
Get email alerts when status or documents change.
Order Certified Copies
Most orders are placed with the USPTO same day — all within 24 business hours.
Order via The Patent Place →
Pre-filled with this patent's details
Quick Facts
Patent No.
US 12700405
App. No.
18/327,487
Granted
Aug 4, 2026
Kind
B2
Abstract

A system may include first and second speech-processing systems with corresponding first and second wakewords. An utterance may contain two or more wakewords. The system determines which speech-processing system to use to perform further audio processing and to determine a response to the utterance.

Claims (40)

1 . A computer-implemented method comprising:

receiving audio data corresponding to an utterance detected by a first device, wherein the audio data is sent from the first device to a first speech-processing system associated with a first wakeword;

determining the utterance corresponds to a second speech-processing system associated with a second wakeword different from the first wakeword; and

based at least in part on the utterance corresponding to the second speech-processing system, causing the first speech-processing system to cease speech processing with regard to the audio data.

2 . The computer-implemented method of claim 1 , wherein causing the first speech-processing system to cease speech processing with regard to the audio data comprises:

receiving, by the first speech-processing system, a command to cease the speech processing.

3 . The computer-implemented method of claim 1 , wherein determining the utterance corresponds to the second speech-processing system comprises:

processing, by the first device, a portion of the audio data to determine the utterance corresponds to the second speech-processing system.

4 . The computer-implemented method of claim 1 , wherein determining the utterance corresponds to the second speech-processing system comprises:

processing, by the first device, a portion of the audio data to determine the utterance comprises the second wakeword associated with the second speech-processing system.

5 . The computer-implemented method of claim 1 , further comprising:

after determining the utterance corresponds to the second speech-processing system, sending, to the second speech-processing system, the audio data.

6 . The computer-implemented method of claim 5 , wherein the audio data is sent from the first device to the second speech-processing system.

7 . The computer-implemented method of claim 1 , further comprising:

causing the first speech-processing system to delete the audio data.

8 . The computer-implemented method of claim 1 , further comprising:

causing the first speech-processing system to delete metadata corresponding to the audio data.

9 . The computer-implemented method of claim 1 , wherein the first speech-processing system determines the utterance corresponds to the second speech-processing system.

10 . The computer-implemented method of claim 1 , wherein the audio data is sent from the first device to the first speech-processing system based at least in part on determining the utterance included the first wakeword associated with the first speech-processing system.

11 . 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:

receive audio data corresponding to an utterance detected by a first device, wherein the audio data is sent from the first device to a first speech-processing system associated with a first wakeword;

determine the utterance corresponds to a second speech-processing system associated with a second wakeword different from the first wakeword; and

based at least in part on the utterance corresponding to the second speech-processing system, cause the first speech-processing system to cease speech processing with regard to the audio data.

12 . The system of claim 11 , wherein the instructions that cause the system to cause the first speech-processing system to cease speech processing with regard to the audio data comprise instructions that, when executed by the at least one processor, cause the system to:

receiving, by the first speech-processing system, a command to cease the speech processing.

13 . The system of claim 11 , wherein the instructions that cause the system to determine the utterance corresponds to the second speech-processing system comprise instructions that, when executed by the at least one processor, cause the system to:

process, by the first device, a portion of the audio data to determine the utterance corresponds to the second speech-processing system.

14 . The system of claim 11 , wherein the instructions that cause the system to determine the utterance corresponds to the second speech-processing system comprise instructions that, when executed by the at least one processor, cause the system to:

process, by the first device, a portion of the audio data to determine the utterance comprises the second wakeword associated with the second speech-processing system.

15 . The system of claim 11 , wherein the at least one memory further comprises instructions that, when executed by the at least one processor, further cause the system to:

after determination that the utterance corresponds to the second speech-processing system, send, to the second speech-processing system, the audio data.

16 . The system of claim 15 , wherein the audio data is sent from the first device to the second speech-processing system.

17 . The system of claim 11 , wherein the at least one memory further comprises instructions that, when executed by the at least one processor, further cause the system to:

cause the first speech-processing system to delete the audio data.

18 . The system of claim 11 , wherein the at least one memory further comprises instructions that, when executed by the at least one processor, further cause the system to:

cause the first speech-processing system to delete metadata corresponding to the audio data.

19 . The system of claim 11 , wherein the instructions that cause the system to determine the utterance corresponds to the second speech-processing system are executed by the first speech-processing system.

20 . The system of claim 11 , wherein the audio data is sent from the first device to the first speech-processing system based at least in part on determining the utterance included the first wakeword associated with the first speech-processing system.