Multi-layer keyword detection
A system and method for temporarily disabling keyword detection to avoid detection of machine-generated keywords. A local device may operate two keyword detectors. The first keyword detector operates on input audio data received by a microphone to capture keywords uttered by a user. In these instances, the keyword may be detected by the first detector and the audio data may be transmitted to a remote device for processing. The remote device may generate output audio data to be sent to the local device. The local device may process the output audio data to determine that it also includes the keyword. The device may then disable the first keyword detector while the output audio data is played back by an audio speaker of the local device. Thus the local device may avoid detection of a keyword originating from the output audio. The first keyword detector may be reactivated after a time interval during which the keyword might be detectable in the output audio.
1. A computer-implemented method, comprising:
receiving, by a device, audio data;
processing at least a portion of the audio data using a first wakeword detection component, wherein the device is configured to perform a first function in response to a positive wakeword detection by the first wakeword detection component;
processing at least a portion of the audio data using a second wakeword detection component, wherein the device is configured to perform a second function different from the first function in response to a positive wakeword detection by the second wakeword detection component; and
causing at least one of the first function or second function to be performed in response to a positive wakeword detection by at least one of the first wakeword detection component or the second wakeword detection component.
2. The computer-implemented method of claim 1 , wherein:
processing by the first wakeword detection component comprises processing to detect a first wakeword; and
processing by the second wakeword detection component comprises processing to detect a second wakeword.
3. The computer-implemented method of claim 1 , wherein the first function comprises sending at least a portion of the audio data to a remote device for speech processing.
4. The computer-implemented method of claim 1 , wherein the second function comprises altering an operation of the device with respect to the first wakeword detection component.
5. The computer-implemented method of claim 1 , wherein the second function comprises outputting time data corresponding to a detected wakeword.
6. The computer-implemented method of claim 1 , wherein receiving the audio data comprises receiving the audio data from a separate microphone array.
7. The computer-implemented method of claim 1 , wherein receiving the audio data comprises receiving at least a portion of the audio data from an audio processing component.
8. The computer-implemented method of claim 1 , wherein receiving the audio data comprises:
receiving a first portion of the audio data from at least one microphone of the device; and
receiving a second portion of audio data from a remote device.
9. The computer-implemented method of claim 8 , wherein:
the first wakeword detection component operates on the first portion of audio data; and
the second wakeword detection component operates on the first portion of audio data.
10. The computer-implemented method of claim 1 , wherein:
the processing using the second wakeword detection component occurs after the processing using the first wakeword detection component.
11. A device, comprising:
at least one microphone;
at least one processor; and
at least one memory comprising instructions that, when executed by the at least one processor, cause the device to:
receive audio data;
process at least a portion of the audio data using a first wakeword detection component, wherein the device is configured to perform a first function in response to a positive wakeword detection by the first wakeword detection component;
process at least a portion of the audio data using a second wakeword detection component, wherein the device is configured to perform a second function different from the first function in response to a positive wakeword detection by the second wakeword detection component; and
cause at least one of the first function or second function to be performed in response to a positive wakeword detection by at least one of the first wakeword detection component or the second wakeword detection component.
12. The device of claim 11 , the first wakeword detection component is configured to detect a first wakeword and the second wakeword detection component is configured to detect a second wakeword.
13. The device of claim 11 , wherein the first function comprises sending at least a portion of the audio data to a remote device for speech processing.
14. The device of claim 11 , wherein the second function comprises altering an operation of the device with respect to the first wakeword detection component.
15. The device of claim 11 , wherein the second function comprises outputting time data corresponding to a detected wakeword.
16. The device of claim 11 , wherein at least a portion of the audio data is received from a separate microphone array.
17. The device of claim 11 , wherein at least a portion of the audio data is received from an audio processing component.
18. The device of claim 11 , wherein the audio data comprises:
a first portion of audio data received from the at least one microphone; and
a second portion of audio data received from a remote device.
19. The device of claim 18 , wherein:
the first wakeword detection component operates on the first portion of audio data; and
the second wakeword detection component operates on the first portion of audio data.
20. The device of claim 11 , wherein:
the processing using the second wakeword detection component occurs after the processing using the first wakeword detection component.