Signal processing based on audio context

• US 9,721,568 B1
• Filed: 05/27/2016
• Issued: 08/01/2017
• Est. Priority Date: 05/01/2012
• Status: Active Grant

• Current Assignee: Amazon Technologies, Inc. (Amazon.com, Inc.)
• Original Assignee: Amazon Technologies, Inc. (Amazon.com, Inc.)
• Inventors: Watanabe, Yuzo, Polansky, Stephen M., Bell, Matthew P.
• Primary Examiner(s): Pullias, Jesse
• Application Number:
  US15/166,809
• Time in Patent Office: 431 Days
• Field of Search: 704200-257, 704270-504
• CPC Class Codes: G10L 15/22 Procedures used during a speech recognition process, e.g. man-machine dialogue
• CPC Class Codes: G10L 15/26 Speech to text systems G10L15/08 takes precedence
• CPC Class Codes: G10L 17/22 Interactive procedures; Man-machine interfaces
• CPC Class Codes: G10L 21/0208 Noise filtering
• CPC Class Codes: G10L 25/72 for transmitting results of analysis
• CPC Class Codes: H04R 1/08 Mouthpieces; Microphones; Attachments therefor
• CPC Class Codes: H04R 29/00 Monitoring arrangements; Testing arrangements for hearing aids H04R25/30; detection of loudspeaker connection H04R5/04; sound-field adaptation dependent on speaker detection H04S7/308
• CPC Class Codes: H04R 3/002 Damping circuit arrangements for transducers, e.g. motional feedback circuits

Abstract

Described herein are systems, methods, and apparatus for determining audio context between an audio source and an audio sink and selecting signal profiles based at least in part on that audio context. The signal profiles may include noise cancellation which is configured to facilitate operation within the audio context. Audio context may include user-to-user and user-to-device communications.

Claims

1. A system comprising:

at least one microphone configured to generate an audio signal at a first user device;

at least one memory storing computer-executable instructions;

at least one processor configured to access the at least one memory and execute the computer-executable instructions to;

receive the audio signal;

determine that the audio signal comprises a trigger word;

determine an audio context associated with a destination device;

determine at least one processing profile to process the audio signal based at least in part on the audio context and the trigger word, wherein the at least one processing profile is speech-to-text processing profile;

generate a processed audio signal; and

send the processed audio signal to the destination device.

2. The system of claim 1, wherein the at least one processor is configured to:

determine that the audio context relates to an automated speech recognition to be performed.

3. The system of claim 1, wherein the at least one processing profile is selected from a plurality of processing profiles.

4. The system of claim 1, wherein the at least one processing profile comprises optimizing sound for automated speech recognition.

5. The system of claim 1, wherein the audio signal is a first audio signal and the audio context is a first audio context, and wherein the at least one processor is configured to:

receive a second audio signal;

determine a second audio context for the second audio signal;

determine that the second audio context relates to a communication for human consumption via a second user device; and

determine a user device processing profile from a plurality of processing profiles to process second audio signal.

6. The system of claim 5, wherein the second user device comprises a telephony device configured to present audio to a human, and wherein the user device processing profile comprises noise cancellation sound processing.

7. The system of claim 1, wherein the first user device comprises a button, and wherein the at least one processor is further configured to:

receive an indication that the button at the first user device has been engaged; and

determine a speech-to-text processing profile.

8. The system of claim 1, wherein the at least one processor is further configured to:

determine a routing device for the processed audio signal; and

route the processed audio signal through the routing device, and wherein the routing device comprises an automated speech recognition device or a cellular connection device.

9. The system of claim 1, wherein the audio signal is a first audio signal, the destination device is a first destination device, and the processed audio signal is a first processed audio signal, and wherein the at least one processor is configured to:

determine a speech-to-text processing profile for an automated speech recognition device;

receive a second audio signal;

determine that a second destination device of the second audio signal is a telephony device;

determine a user device processing profile to process the second audio signal; and

send a second processed audio signal to the telephony device.

10. A method comprising:

receiving, by a first user device one or more computer processors coupled to at least one memory, an audio signal, wherein the first user device comprises a button;

determining an audio context associated with a destination device;

receiving an indication that the button at the first user device has been engaged;

determining at least one processing profile to process the audio signal based at least in part on the audio context and the indication, wherein the at least one processing profile is a speech-to-text processing profile;

generating a processed audio signal; and

sending the processed audio signal to the destination device.

11. The method of claim 10, wherein determining the at least one processing profile to process the audio signal based at least in part on the audio context comprises:

determining that the audio context relates to an automated speech recognition to be performed.

12. The method of claim 10, wherein the at least one processing profile is selected from a plurality of processing profiles.

13. The method of claim 10, wherein the at least one processing profile comprises optimizing sound for automated speech recognition.

14. The method of claim 10, wherein the audio signal is a first audio signal and the audio context is a first audio context, the method further comprising:

receiving a second audio signal;

determining a second audio context for the second audio signal;

determining that the second audio context relates to a communication for human consumption via a second user device; and

determining a user device processing profile from a plurality of processing profiles to process the second audio signal.

15. The method of claim 14, wherein the second user device comprises a telephony device configured to present audio to a human, and wherein the user device processing profile comprises noise cancellation sound processing.

16. The method of claim 10, further comprising:

determining that the audio signal comprises a trigger word;

wherein determining the processing profile to process the audio signal based at least in part on the audio context comprises determining a speech-to-text processing profile.

17. The method of claim 10, further comprising:

determining a routing device for the processed audio signal;

wherein sending the processed audio signal to the destination device comprises routing the processed audio signal through a cloud server when the destination device is an automated speech recognition device, and routing the processed audio signal through the routing device, and wherein the routing device comprises an automated speech recognition device or a cellular connection device.

18. The method of claim 10, wherein the audio signal is a first audio signal, the destination device is a first destination device, and the processed audio signal is a first processed audio signal, and wherein determining the at least one processing profile to process the audio signal based at least in part on the audio context comprises determining a speech-to-text processing profile for an automated speech recognition device, the method further comprising:

receiving a second audio signal;

determining that a second destination device of the second audio signal is a telephony device;

determining a user device processing profile to process the second audio signal; and

sending a second processed audio signal to the telephony device.