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 indicated for speech processing. The system may determine output audio data responsive to the input audio data. 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:
determining first audio data corresponding to an output by a first device;
determining, using a first detector of the first device, that the first audio data includes a first representation of a keyword;
after determining the first audio data includes the first representation, adjusting operation with regard to a second detector of the first device, the second detector configured to determine whether second audio data includes a second representation of the keyword; and
after adjusting the operation of the second detector, causing audio, corresponding to the first audio data, to be output by the first device.
2. The computer-implemented method of claim 1 , wherein adjusting operation with regard to the second detector comprises disabling the second detector.
3. The computer-implemented method of claim 2 , further comprising:
determining the first representation will be output as a portion of the audio during a first time period; and
enabling the second detector following the first time period.
4. The computer-implemented method of claim 1 , wherein adjusting operation with regard to the second detector comprises ignoring output data of the second detector.
5. The computer-implemented method of claim 1 , wherein the first device comprises a microphone and an audio output component, wherein the second detector is coupled to the microphone, and wherein the method further comprises:
causing the first audio data to be sent to the audio output component.
6. The computer-implemented method of claim 5 , further comprising:
disabling the second detector prior to causing the first audio data to be sent to the audio output component.
7. The computer-implemented method of claim 1 , wherein the first detector is configured to send an indicator to the second detector based at least in part on the first detector determining the first audio data includes the first representation, the indicator causing the second detector to ignore the second representation determined in second audio data corresponding to the audio.
8. The computer-implemented method of claim of claim 7 , wherein the indicator prevents the second detector from ceasing output of the audio in response to determining the second representation.
9. The computer-implemented method of claim 1 , further comprising:
receiving the first audio data from a second device.
10. The computer-implemented method of claim 1 , further comprising, prior to determining the first audio data:
receiving input audio data;
determining, using the first detector, that the input audio data represents the keyword; and
causing speech processing to be performed based at least in part on the input audio data.
11. A first device, comprising:
at least one processor; and
at least one memory including instructions that, when executed by the at least one processor, cause the first device to:
determine first audio data corresponding to an output by a first device;
determine, using a first detector of the first device, that the first audio data includes a first representation of a keyword;
after determination that the first audio data includes the first representation, adjust operation with regard to a second detector of the first device, the second detector configured to determine whether second audio data includes a second representation of the keyword; and
after adjustment of the operation of the second detector, cause audio, corresponding to the first audio data, to be output by the first device.
12. The first device of claim 11 , wherein the instructions that cause the first device to adjust operation with regard to the second detector comprise instructions that, when executed by the at least one processor, cause the first device to disable the second detector.
13. The first device of claim 12 , wherein the at least one memory further includes instructions that, when executed by the at least one processor, further cause the first device to:
determine the first representation will be output as a portion of the audio during a first time period; and
enable the second detector following the first time period.
14. The first device of claim 11 , wherein the instructions that cause the first device to adjust operation with regard to the second detector comprise instructions that, when executed by the at least one processor, cause the first device to ignore output data of the second detector.
15. The first device of claim 11 , wherein the first device comprises a microphone and an audio output component, wherein the second detector is coupled to the microphone, and wherein the at least one memory further includes instructions that, when executed by the at least one processor, further cause the first device to:
cause the first audio data to be sent to the audio output component.
16. The first device of claim 15 , wherein the at least one memory further includes instructions that, when executed by the at least one processor, further cause the first device to:
disable the second detector prior to causing the first audio data to be sent to the audio output component.
17. The first device of claim 11 , wherein the first detector is configured to send an indicator to the second detector based at least in part on the first detector determining the first audio data includes the first representation, the indicator causing the second detector to ignore the second representation determined in second audio data corresponding to the audio.
18. The first device of claim 17 , wherein the indicator prevents the second detector from ceasing output of the audio in response to determining the second representation.
19. The first device of claim 11 , wherein the at least one memory further includes instructions that, when executed by the at least one processor, further cause the first device to:
receive the first audio data from a second device.
20. The first device of claim 11 , wherein the at least one memory further includes instructions that, when executed by the at least one processor, further cause the first device to prior to determination of the first audio data:
receive input audio data;
determine, using the first detector, that the input audio data represents the keyword; and
cause speech processing to be performed based at least in part on the input audio data.