Activation Trigger Processing

• US 20190325870A1
• Filed: 10/03/2018
• Published: 10/24/2019
• Est. Priority Date: 04/23/2018
• Status: Active Grant

• Current Assignee: Spotify AB (Spotify Technology SA)
• Original Assignee: Spotify AB (Spotify Technology SA)
• Inventors: MITIC, Richard
• Granted Patent: US 10,909,984 B2
• Time in Patent Office: Days
• CPC Class Codes: G10L 15/08 Speech classification or search
• CPC Class Codes: G10L 15/22 Procedures used during a speech recognition process, e.g. man-machine dialogue
• CPC Class Codes: G10L 15/30 Distributed recognition, e.g. in client-server systems, for mobile phones or network applications
• CPC Class Codes: G10L 2015/088 Word spotting
• CPC Class Codes: G10L 2015/223 Execution procedure of a spoken command

Abstract

Utterance-based user interfaces can include activation trigger processing techniques for detecting activation triggers and causing execution of certain commands associated with particular command pattern activation triggers without waiting for output from a separate speech processing engine. The activation trigger processing techniques can also detect speech analysis patterns and selectively activate a speech processing engine.

Claims

1. A non-transitory computer-readable medium storing one or more sequences of instructions that, when executed by one or more processors, cause the one or more processors to perform a method including:

receiving audio input;

determining, by an activation trigger engine, whether the audio input includes a speech analysis pattern;

responsive to the audio input including a speech analysis pattern, activating a speech analysis engine for identification of a command;

determining, by the activation trigger engine, whether the audio input includes a command pattern; and

responsive to determining that the audio input includes the command pattern, executing a command associated with the command pattern.

2. The non-transitory computer-readable medium of claim 1, wherein the method further includes:

establishing a connection with a remote server having the speech analysis engine.

3. The non-transitory computer-readable medium of claim 1, wherein the command pattern includes the speech analysis pattern;

and wherein the method further includes;

determining that the audio input includes the command pattern and the speech analysis pattern.

4. The non-transitory computer-readable medium of claim 1, wherein the method further includes:

disregarding a response from the speech analysis engine received after executing the command.

5. The non-transitory computer-readable medium of claim 1, wherein the method further includes:

responsive to determining that the audio input matches the command pattern, deactivating the speech analysis engine.

6. The non-transitory computer-readable medium of claim 1,

wherein the speech analysis pattern includes a first set of N components, where N is an integer greater than one;

and

wherein the command pattern includes a second set of components, wherein the second set includes one or more command components associated with a command, and M components from the first set, where M is an integer greater than zero and less than N.

7. The non-transitory computer-readable medium of claim 1, wherein the method further includes:

selecting the command associated with the speech analysis pattern from a plurality of commands.

8. The non-transitory computer-readable medium of claim 1, wherein the method further includes:

providing at least a portion of the audio input to the speech analysis engine for identification of the command within the audio input.

9. A method comprising:

receiving audio input;

determining, by an activation trigger engine, whether the audio input includes a speech analysis pattern;

responsive to the audio input including a speech analysis pattern, activating a speech analysis engine for identification of a command;

determining, by the activation trigger engine, whether the audio input includes a command pattern; and

responsive to determining that the audio input includes the command pattern, executing a command associated with the command pattern.

10. The method of claim 9, further comprising:

establishing a connection with a remote server having the speech analysis engine.

11. The method of claim 9, wherein the command pattern includes the speech analysis pattern and the method further includes:

determining that the audio input includes the command pattern and the speech analysis pattern.

12. The method of claim 9, further comprising:

disregarding a response from the speech analysis engine received after executing the command.

13. The method of claim 9, further comprising:

responsive to determining that the audio input matches the command pattern, deactivating the speech analysis engine.

14. The method of claim 9,

wherein the speech analysis pattern includes a first set of N components, where N is an integer greater than one;

and

wherein the command pattern includes a second set of components, wherein the second set includes one or more command components associated with a command, and M components from the first set, where M is an integer greater than zero and less than N.

15. The method of claim 9, further comprising:

selecting the command associated with the speech analysis pattern from a plurality of commands.

16. The method of claim 9, further comprising:

providing at least a portion of the audio input to the speech analysis engine for identification of the command within the audio input.

17. A system comprising

a first device having a first set of one or more processors configured to operate as a speech analysis engine;

a second device remote from the first device and having a second set of one or more processors configured to;

receive audio input;

determine, by an activation trigger engine, whether the audio input includes a speech analysis pattern;

responsive to the audio input including a speech analysis pattern, activating the speech analysis engine for identification of a command, wherein activating the speech analysis engine includes providing at least a portion of the audio input to the speech analysis engine for identification of the command within the audio input;

determining, by the activation trigger engine, whether the audio input includes a command pattern; and

responsive to determining that the audio input includes the command pattern, executing a command associated with the command pattern.

18. The system of claim 17, further comprising:

receiving a response from the speech analysis engine after executing the command, wherein the response is responsive to activating the speech analysis engine for identification of the command;

disregarding the response from the speech analysis engine.

19. The system of claim 17, further comprising:

responsive to determining that the audio input matches the command pattern, deactivating the speech analysis engine.

20. The system of claim 17,

wherein the speech analysis pattern includes a first set of N components, where N is an integer greater than one;

and

wherein the command pattern includes a second set of components, wherein the second set includes one or more command components associated with a command, and M components from the first set, where M is an integer greater than zero and less than N.