Methods and devices for selectively ignoring captured audio data
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.
1. A computer-implemented method comprising:
receiving audio data;
receiving, via a network from a first device external to a second device, metadata corresponding to detection of a wakeword represented in the audio data;
causing output of audio in response to the audio data; and
processing the metadata to disable audio processing to avoid a disruption of operation of the second device in response to the wakeword being detected in the audio by the second device.
2. The computer-implemented method of claim 1 , wherein the disruption of operation of the second device comprises a disruption of the output of the audio by the second device.
3. The computer-implemented method of claim 1 , wherein processing the metadata to avoid the disruption comprises:
using the metadata to generate a first command to alter operation of a component of the second device; and
sending the first command to the component.
4. The computer-implemented method of claim 3 , wherein:
the component comprises a hardware component of the second device; and
the first command causes the hardware component to be disabled.
5. The computer-implemented method of claim 3 , wherein:
the component comprises an audio input component of the second device; and
the first command causes the audio input component to be disabled.
6. The computer-implemented method of claim 3 , wherein:
the component comprises a speech processing component of the second device; and
the first command causes the speech processing component to be disabled.
7. The computer-implemented method of claim 3 , wherein:
the component comprises a wakeword detection component of the second device; and
the first command causes the wakeword detection component to be disabled.
8. The computer-implemented method of claim 3 , wherein:
the component comprises a wakeword detection component of the second device; and
the first command causes the wakeword detection component to disregard an indication of detection of the wakeword.
9. The computer-implemented method of claim 3 , further comprising:
determining, based at least in part on the metadata, an estimated time window when the wakeword will be represented in output audio; and
sending a second command to the component to restore operation of the component after the estimated time window.
10. A system, comprising:
at least one processor;
at least one memory comprising instructions that, when executed by the at least one processor, cause the system to:
receive audio data;
receive, via a network from a first device external to a second device, metadata corresponding to detection of a wakeword represented in the audio data;
cause output of audio in response to the audio data; and
process the metadata to disable audio processing to avoid a disruption of operation of the second device in response to the wakeword being detected in the audio by the second device.
11. The system of claim 10 , wherein the disruption of operation of the second device comprises a disruption of the output of the audio by the second device.
12. The system of claim 10 , wherein the instructions that cause the system to process the metadata to avoid the disruption comprise instructions that, when executed by the at least one processor, cause the system to:
use the metadata to generate a first command to alter operation of a component of the second device; and
send the first command to the component.
13. The system of claim 12 , wherein:
the component comprises a hardware component of the second device; and
the first command causes the hardware component to be disabled.
14. The system of claim 12 , wherein:
the component comprises an audio input component of the second device; and
the first command causes the audio input component to be disabled.
15. The system of claim 12 , wherein:
the component comprises a speech processing component of the second device; and
the first command causes the speech processing component to be disabled.
16. The system of claim 12 , wherein:
the component comprises a wakeword detection component of the second device; and
the first command causes the wakeword detection component to be disabled.
17. The system of claim 12 , wherein:
the component comprises a wakeword detection component of the second device; and
the first command causes the wakeword detection component to disregard an indication of detection of the wakeword.
18. The system of claim 12 , wherein the at least one memory further comprises instructions that, when executed by the at least one processor, further cause the system to:
determine, based at least in part on the metadata, an estimated time window when the wakeword will be represented in output audio; and
send a second command to the component to restore operation of the component after the estimated time window.
19. A computer-implemented method comprising:
receiving audio data;
receiving metadata indicating that a wakeword is represented in the audio data;
causing output of audio in response to the audio data;
processing the metadata to avoid a disruption of operation of a device in response to output of the audio corresponding to the wakeword;
using the metadata to generate a first command to alter operation of an audio input component of the device; and
sending the first command to the component.