Machine-control of a device based on machine-detected transitions
View Patent ↗Apparatus, methods, and systems that operate to perform machine-control of a device based on machine-detected transitions are disclosed.
1. A method comprising:
accessing, by executing an instruction using one or more processors, a memory to retrieve audio data that represents audio received in an audio signal;
determining, by executing an instruction using the one or more processors, an audio characteristic in the audio, the audio characteristic being represented by an audio characteristic value;
detecting, by executing an instruction using the one or more processors, a transition between a music category and a talk category by comparing the audio characteristic value to a threshold value among a set of threshold values, the set of threshold values corresponding to different categories in a set of categories including the music category and the talk category;
modifying, by executing an instruction using the one or more processors, at least one threshold value among the set of threshold values based on the detecting of the transition between the music category and the talk category; and
controlling, by executing an instruction using the one or more processors, a device based on the detected transition between the music category and the talk category.
2. The method of claim 1 , wherein the detecting of the transition between the music category and the talk category includes detecting an increase in the audio characteristic in the audio based on the comparing of the audio characteristic value to the threshold value.
3. The method of claim 1 , wherein the detecting of the transition between the music category and the talk category includes detecting a decrease in the audio characteristic in the audio based on the comparing of the audio characteristic value to the threshold value.
4. The method of claim 1 , wherein the detecting of the transition between the music category and the talk category includes identifying the transition based on an increase in the audio characteristic value.
5. The method of claim 1 , wherein the detecting of the transition between the music category and the talk category includes identifying the transition based on a decrease in the audio characteristic value.
6. The method of claim 1 , wherein the controlling of the device based on the detected transition includes selecting a behavior of the device in response to the detected transition between the music category and the talk category.
7. The method of claim 1 , wherein the controlling of the device based on the detected transition includes selecting a fingerprinting algorithm in response to the detected transition between the music category and the talk category.
8. The method of claim 1 , wherein the controlling of the device based on the detected transition includes reducing a rate of audio classification requests in response to the detected transition between the music category and the talk category.
9. A non-transitory machine-readable storage medium comprising instructions that, when executed, cause one or more processors to at least:
access a memory to retrieve audio data that represents audio received in an audio signal;
determine, via audio processing, an audio characteristic in the audio, the audio characteristic being represented by an audio characteristic value;
identify a transition between a music category and a talk category by comparing the audio characteristic value to a threshold value among a set of threshold values, the set of threshold values each corresponding to a different category in a set of categories including the music category and the talk category;
modify at least one threshold value among the set of threshold values based on the detecting of the transition between the music category and the talk category; and
control a device based on the detected transition between the music category and the talk category.
10. The non-transitory machine-readable storage medium of claim 9 , wherein the instructions cause the machine to control the device based on the detected transition by reducing power consumption of the device by reducing a rate of audio classification requests in response to the detected transition between the music category and the talk category.
11. A system comprising:
one or more processors; and
a memory storing instructions that, when executed by the one or more processors, cause the one or more processors to:
access a memory to retrieve audio data that represents audio received in an audio signal;
determine, via audio processing, an audio characteristic in the audio, the audio characteristic being represented by an audio characteristic value;
determine a transition between a music category and a talk category by comparing the audio characteristic value to a threshold value among a set of threshold values, the set of threshold values corresponding to different categories in a set of categories including the music category and the talk category;
modify at least one threshold value among the set of threshold values based on the detecting of the transition between the music category and the talk category; and
control a device based on the detected transition between the music category and the talk category.
12. The system of claim 11 , wherein the memory stores instructions to cause the one or more processors to control the device based on the detected transition by initiating a media recognition service in response to the detected transition between the music category and the talk category.
13. The method of claim 1 , wherein the audio characteristics corresponds to at least one of rhythm, pitch, concentration of pitch features, tempo, or noise.
14. The non-transitory machine-readable storage medium of claim 9 , wherein the audio characteristics corresponds to at least one of rhythm, pitch, concentration of pitch features, tempo, or noise.
15. The non-transitory machine-readable storage medium of claim 9 , wherein the instructions cause the machine to detect the transition between the music category and the talk category by detecting an increase in the audio characteristic in the audio based on the comparing of the audio characteristic value to the threshold value.
16. The non-transitory machine-readable storage medium of claim 9 , wherein the instructions cause the machine to detect the transition between the music category and the talk category by detecting a decrease in the audio characteristic in the audio based on the comparing of the audio characteristic value to the threshold value.
17. The non-transitory machine-readable storage medium of claim 9 , wherein the instructions cause the machine to detect the transition between the music category and the talk category by identifying the transition based on an increase in the audio characteristic value.
18. The non-transitory machine-readable storage medium of claim 9 , wherein the instructions cause the machine to detect the transition between the music category and the talk category by identifying the transition based on a decrease in the audio characteristic value.
19. The system of claim 11 , wherein the audio characteristics corresponds to at least one of rhythm, pitch, concentration of pitch features, tempo, or noise.
20. The system of claim 11 , wherein the memory stores instructions to cause the one or more processors to detect the transition between the music category and the talk category by detecting an increase in the audio characteristic in the audio based on the comparing of the audio characteristic value to the threshold value.