Multi-mode voice triggering for audio devices

Patent metadata

Field	Value
Publication number	US-11922948-B2
Application number	US-202318137958-A
Country	US
Kind code	B2
Filing date	Apr 21, 2023
Priority date	Mar 11, 2021
Publication date	Mar 5, 2024
Grant date	Mar 5, 2024

Abstract

Implementations of the subject technology provide systems and methods for multi-mode voice triggering for audio devices. An audio device may store multiple voice recognition models, each trained to detect a single corresponding trigger phrase. So that the audio device can detect a specific one of the multiple trigger phrases without consuming the processing and/or power resources to run a voice recognition model that can differentiate between different trigger phrases, the audio device pre-loads a selected one of the voice recognition models for an expected trigger phrase into a processor of the audio device. The audio device may select the one of the voice recognition models for the expected trigger phrase based on a type of a companion device that is communicatively coupled to the audio device.

First claim

What is claimed is:

1. An electronic device, comprising:
a memory; and
at least one processor configured to:
provide, to an audio output device, an indicator of a particular virtual assistant at the electronic device;
receive a trigger signal from the audio output device prior to receiving audio input data from the audio output device, wherein the trigger signal corresponds to the particular virtual assistant; and
activate, responsive to the trigger signal, the particular virtual assistant for receiving the audio input data from the audio output device.

2. The electronic device of claim 1 , wherein the particular virtual assistant corresponds to a manufacturer of the electronic device that is different from a manufacturer of the audio output device.

3. The electronic device of claim 1 , wherein the at least one processor is further configured to provide audio content to the audio output device for output by the audio output device.

4. The electronic device of claim 1 , wherein the particular virtual assistant is one of multiple virtual assistants at the electronic device.

5. The electronic device of claim 1 , wherein the at least one processor is configured to provide the indicator of the particular virtual assistant at the electronic device to the audio output device while establishing a connection with the audio output device.

6. The electronic device of claim 5 , wherein the at least one processor is configured to provide the indicator of the particular virtual assistant at the electronic device to the audio output device while establishing the connection with the audio output device by including the indicator in connection information associated with establishing the connection.

7. The electronic device of claim 1 , wherein at least one processor is further configured to perform, with the activated particular virtual assistant, an active listening operation in cooperation with the audio output device based on the audio input data from the audio output device.

8. The electronic device of claim 7 , wherein the at least one processor is configured to perform the active listening operation, at least in part, by:
receiving voice data that is based on voice input captured by a microphone of the audio output device, from the audio output device; and
providing the voice data to one or more voice recognition models at the electronic device that are trained for identifying words and phrases for voice control of the particular virtual assistant.

9. The electronic device of claim 1 , wherein the trigger signal has been generated by the audio output device responsive to an output from a voice recognition model at the audio output device, the voice recognition model having been selected by the audio output device based on the indicator provided by the electronic device.

10. A method, comprising:
providing, to an audio output device from an electronic device, an indicator of a particular virtual assistant at the electronic device;
receiving a trigger signal from the audio output device at the electronic device prior to receiving audio input data from the audio output device, wherein the trigger signal corresponds to the particular virtual assistant; and
activating, by the electronic device responsive to the trigger signal, the particular virtual assistant for receiving the audio input data from the audio output device.

11. The method of claim 10 , wherein the particular virtual assistant corresponds to a manufacturer of the electronic device that is different from a manufacturer of the audio output device.

12. The method of claim 10 , further comprising providing audio content to the audio output device for output by the audio output device.

13. The method of claim 10 , wherein the particular virtual assistant is one of multiple virtual assistants at the electronic device.

14. The method of claim 10 , wherein providing the indicator of the particular virtual assistant at the electronic device to the audio output device comprises providing the indicator to the audio output device while establishing a connection with the audio output device.

15. The method of claim 14 , wherein providing the indicator of the particular virtual assistant at the electronic device to the audio output device while establishing the connection with the audio output device comprises including the indicator in connection information associated with establishing the connection.

16. The method of claim 10 , further comprising performing, with the activated particular virtual assistant, an active listening operation in cooperation with the audio output device based on the audio input data from the audio output device.

17. The method of claim 16 , wherein the active listening operation comprises:
receiving voice data that is based on voice input captured by a microphone of the audio output device, from the audio output device; and
providing the voice data to one or more voice recognition models at the electronic device that are trained for identifying words and phrases for voice control of the particular virtual assistant.

18. The method of claim 10 , wherein the trigger signal has been generated by the audio output device responsive to an output from a voice recognition model at the audio output device, the voice recognition model having been selected by the audio output device based on the indicator provided by the electronic device.

19. A processor configured to:
provide, to an audio output device that does not include the processor, an indicator of a particular virtual assistant accessible by the processor;
receive a trigger signal from the audio output device prior to receiving audio input data from the audio output device, wherein the trigger signal corresponds to the particular virtual assistant; and
activate, responsive to the trigger signal, the particular virtual assistant for receiving the audio input data from the audio output device.

20. The processor of claim 19 , wherein the particular virtual assistant is one of multiple virtual assistants accessible by the processor.

Assignees

• Apple Inc

Inventors

• Mehta Dersheet C
• Garg Dinesh
• Koli Sham Anton
• Kopp Kerry J
• Bernhard Hans

Classifications

• G10L15/32 Primary

  Multiple recognisers used in sequence or in parallel; Score combination systems therefor, e.g. voting systems · CPC title

• G10L15/083

  Recognition networks (G10L15/142, G10L15/16 take precedence) · CPC title

• G10L15/22

  Procedures used during a speech recognition process, e.g. man-machine dialogue · CPC title

• G10L15/30

  Distributed recognition, e.g. in client-server systems, for mobile phones or network applications · CPC title

• G10L2015/088

  Word spotting · CPC title