Methods and devices for selectively ignoring captured audio data

• US 10,475,445 B1
• Filed: 07/16/2018
• Issued: 11/12/2019
• Est. Priority Date: 11/05/2015
• Status: Active Grant

• Current Assignee: Amazon Technologies, Inc. (Amazon.com, Inc.)
• Original Assignee: Amazon Technologies, Inc. (Amazon.com, Inc.)
• Inventors: Meyers, James David, Piersol, Kurt Wesley
• Primary Examiner(s): Yen, Eric
• Application Number:
  US16/036,345
• Time in Patent Office: 484 Days
• CPC Class Codes: G10L 15/04 Segmentation; Word boundary detection
• CPC Class Codes: G10L 15/08 Speech classification or search
• CPC Class Codes: G10L 15/20 Speech recognition techniques specially adapted for robustness in adverse environments, e.g. in noise, of stress induced speech G10L21/02 takes precedence
• CPC Class Codes: G10L 15/22 Procedures used during a speech recognition process, e.g. man-machine dialogue
• CPC Class Codes: G10L 2015/088 Word spotting
• CPC Class Codes: G10L 2021/02082 the noise being echo, reverberation of the speech
• CPC Class Codes: G10L 21/028 using properties of sound source

Abstract

Systems and methods for selectively ignoring an occurrence of a wakeword within audio input data is provided herein. In some embodiments, a wakeword may be detected to have been uttered by an individual within a modified time window, which may account for hardware delays and echoing offsets. The detected wakeword that occurs during this modified time window may, in some embodiments, correspond to a word included within audio that is outputted by a voice activated electronic device. This may cause the voice activated electronic device to activate itself, stopping the audio from being outputted. By identifying when these occurrences of the wakeword within outputted audio are going to happen, the voice activated electronic device may selectively determine when to ignore the wakeword, and furthermore, when not to ignore the wakeword.

Claims

1. A system comprising:

at least one processor; and

memory including instructions operable to be executed by the at least one processor to configure the system to;

determine audio data;

determine a data tag associated with a sound represented within the audio data;

determine that the sound corresponds to a wakeword;

determine, based at least in part on the data tag, an estimated time window when the sound will be output during output of the audio data;

generate instructions to disregard the sound within the estimated time window; and

cause an audio data processing component to be disabled during the estimated time window.

2. The system of claim 1, wherein instructions that cause an audio data processing component to be disabled during the estimated time window comprise instructions to:

disable a hardware component during the estimated time window.

3. The system of claim 2, wherein instructions that disable the hardware component comprise instructions to terminate power to the hardware component during the estimated time window.

4. The system of claim 1, wherein the memory further comprises instructions that further configure the system to:

generate an indication to delete a portion of the audio data corresponding to the estimated time window.

5. The system of claim 1, wherein instructions that cause an audio data processing component to be disabled during the estimated time window comprise instructions to:

direct a component to, during the estimated time window, disregard an indication that the wakeword was detected.

6. A computer-implemented method comprising:

determining audio data;

determining a data tag associated with a sound represented within the audio data;

determining that the sound corresponds to a wakeword;

determining, based at least in part on the data tag, an estimated time window when the sound will be output during output of the audio data; and

calculating, based on an offset and the estimated time window, a modified time window when the sound will be output during output of the audio data, the offset corresponding to a distance between a first device and second device.

7. The computer-implemented method of claim 6, further comprising:

causing the audio data to be sent to the first device for output; and

causing an audio data processing component of the second device to be disabled during the modified time window.

8. The computer-implemented method of claim 6, further comprising:

causing a hardware component of the second device to be disabled during the modified time window.

9. The computer-implemented method of claim 6, wherein calculating the modified time window includes calculating an amount of time between the audio data being processed by the first device and the audio data being output by the first device.

10. The computer-implemented method of claim 6, wherein calculating the modified time window includes determining an amount of time between an end time of the sound within the audio data that is output and at least one of a start time of a second sound or an end time of the audio data.

11. The computer-implemented method of claim 6, further comprising:

calculating a second modified time window by determining an acoustic echoing offset time based on a feedback time after output of the audio data.

12. The computer-implemented method of claim 11, wherein determining the acoustic echoing offset time further comprises:

determining a receipt time of audio input data;

calculating a time difference between an audio data output time and the receipt time;

determining the second modified time window by applying a hardware delay time and the acoustic echoing offset time to the modified time window;

determining that the audio input data includes the sound;

determining that the sound is detected within the second modified time window; and

disabling an audio data processing component when the sound is detected during the second modified time window.

13. The computer-implemented method of claim 6, further comprising:

wherein determining the audio data comprises receiving the audio data from the first device;

sending, to the second device, a first instruction to output the audio data; and

sending, to the second device, a second instruction to disable an audio data processing component when an occurrence of the sound is detected during the modified time window.

14. A computer-implemented method comprising:

receiving, from a device, audio data;

determining a data tag associated with a sound within the audio data;

determining, based at least in part on the data tag, an estimated time window when the sound will be output during output of the audio data;

generating a modified time window based on an offset and the estimated time window when the sound will be output during output of the audio data; and

disregarding the audio data when the sound is detected within the audio data output during the estimated time window.

15. The computer-implemented method of claim 14, further comprising:

disabling an audio data processing component during the modified time window.

16. The computer-implemented method of claim 14, further comprising:

disabling a hardware component during the modified time window.

17. The computer-implemented method of claim 16, further comprising:

terminating power to the hardware component during the estimated time window.

18. The computer-implemented method of claim 14, further comprising:

generating an indication to delete a portion of the audio data corresponding to the estimated time window.

19. The computer-implemented method of claim 14, further comprising:

receiving additional audio input data;

determining that the additional audio input data includes an occurrence of the sound;

determining that the occurrence of the sound was captured outside the estimated time window; and

recording the additional audio input data.