Interactive streaming content apparatus, systems and methods
View Patent ↗Apparatus, methods, and systems that operate to provide interactive streaming content identification and processing are disclosed.
1. A method comprising:
continuously receiving an incoming audio signal including audio content;
processing the audio signal to determine audio characteristics that include a rhythm of the audio content;
classifying the audio content into a classification among multiple classifications that include a music classification and a talk classification based on the audio characteristics that include the rhythm of the audio content and based on multiple sets of threshold values that each correspond to a different one of the multiple classifications;
identifying a transition between the music classification and the talk classification by detecting that a change in the rhythm of the audio content transgresses at least one of the multiple sets of threshold values;
in response to the transition between the music classification and the talk classification being identified by the detecting that the change in the rhythm of the audio content transgresses at least one of the multiple sets of threshold values, adjusting at least one of the multiple sets of threshold values; and
selecting a behavior of a device in response to the identified transition between the music classification and the talk classification.
2. The method of claim 1 , wherein the processing comprises:
equalizing the audio signal, based on the environmental context, to substantially eliminate selected bands of frequency.
3. The method of claim 1 , wherein the processing comprises:
windowing the audio signal to limit a time period for the processing.
4. The method of claim 1 , wherein the processing comprises:
thresholding the audio signal to reject amplitude components that exceed a defined level.
5. The method of claim 1 , wherein the audio characteristics comprise:
at least one of amplitude, frequency, pitch, tempo, or energy.
6. The method of claim 1 , wherein the threshold values comprise:
the multiple sets of threshold values include at least one of a minimum threshold, a maximum threshold, and a historical average threshold to measure against the audio characteristics that include the rhythm of the audio content.
7. The method of claim 1 , further comprising:
in response to the transition, updating time position information associated with the incoming audio signal.
8. The method of claim 1 , further comprising:
in response to the transition, triggering the selected behavior of the device.
9. The method of claim 1 , wherein:
the identifying of the transition between the music classification and the talk classification includes detecting an increase in the rhythm of the audio content.
10. The method of claim 1 , wherein:
the identifying of the transition between the music classification and the talk classification includes detecting a decrease in the rhythm of the audio content.
11. The method of claim 1 , wherein:
the identifying of the transition between the music classification and the talk classification identifies a transition from the music classification to the talk classification based on a decrease in the rhythm of the audio content.
12. The method of claim 1 , wherein:
the identifying of the transition between the music classification and the talk classification identifies a transition from the talk classification to the music classification based on an increase in the rhythm of the audio content.
13. The method of claim 1 , wherein:
the identifying of the transition between the music classification and the talk classification identifies a transition from the music classification to the talk classification based on an increase in concentration of pitch in the audio content.
14. The method of claim 1 , wherein:
the identifying of the transition between the music classification and the talk classification identifies a transition from the talk classification to the music classification based on a decrease in concentration of pitch in the audio content.
15. A method comprising:
determining an implicit context in which a mobile device is receiving an incoming audio signal including audio content;
processing the audio signal to determine audio characteristics that include a rhythm of the audio content;
determining a classification of the audio content among multiple classifications that include a music classification and a talk classification based on the audio characteristics that include the rhythm of the audio content and based on multiple sets of threshold values that each correspond to a different one of the multiple classifications;
identifying a transition between the music classification and the talk classification by detecting that a change in the rhythm of the audio content transgresses at least one of the multiple sets of threshold values;
selecting a behavior of the mobile device in response to the transition between the music classification and the talk classification being identified by the detecting that the change in the rhythm of the audio content transgresses at least one of the multiple sets of threshold values; and
changing the classification of the audio content by adjusting at least one of the multiple sets of threshold values in accordance with the implicit context.
16. The method of claim 15 , further comprising:
determining previous content recognition, wherein the changing of the classification of the audio content comprises changing the classification in accordance with the implicit context and the previous content recognition.
17. The method of claim 15 , further comprising:
determining a device operating mode, power supply type, and network connection type for the mobile device, wherein the changing of the classification of the audio content comprises changing the classification in accordance with the implicit context and the device operating mode, power supply type, and network connection type.
18. An apparatus for determining the environmental context associated with a mobile device, comprising:
a classifier comprising one or more processors and configured to:
receive an incoming audio signal that includes audio content;
process the audio signal to provide audio characteristics that include a rhythm of the audio content; and
to classify the audio content into a classification among multiple classifications that include a music classification and a talk classification based on the audio characteristics that include the rhythm of the audio content and based on multiple sets of threshold values that each correspond to a different one of the multiple classifications;
a transition detector comprising one or more processors of the machine and configured to recognize a transition between the music classification and the talk classification by detecting that a change in the rhythm of the audio content transgresses at least one of the multiple sets of threshold values; and
a context manager comprising one or more processors of the machine and configured to trigger a selected behavior of the mobile device in dependence on the transition between the music classification and the talk classification being recognized by the detecting that the change in the rhythm of the audio content transgresses at least one of the multiple sets of threshold values.
19. The apparatus of claim 18 , wherein the classifier is configured to equalize the signal, based on the environmental context, to substantially eliminate selected bands of frequency, or threshold the signal to reject amplitude components that exceed a defined level.
20. The apparatus of claim 18 , configured to be assisted by meta-data returned from a network service.