Systems and methods for interactive broadcast content
View Patent ↗Devices and methods for scoring viewer's interactions with content broadcast on a presentation device by processing at least one audio signal received by a microphone proximate the viewer and the presentation device, to generate at least one audio signature, which is compared to at least two different reference audio signatures.
1. A device comprising:
at least two microphones collectively capable of simultaneously receiving audio from a user and receiving audio broadcast by a presentation device proximate said user, the at least two microphones comprising a first microphone and a second microphone, where audio received by said first microphone is used to cancel at least a portion of audio received by said second microphone;
a first signature generator that generates a first audio signature representing said audio from said presentation device, and a second signature generator that generates a second audio signature representing said audio from said user, said first audio signature generated based on said audio from said user;
a matching module that uses said first audio signature to match said first audio signature to a first reference audio signature;
a synchronizer that synchronizes said second audio signature to said first reference audio signature; and
a display capable of displaying a score, where said score is based on comparing said second audio signature to at least one second reference audio signature.
2. The device of claim 1 where said matching module selects said first reference audio signature from among a plurality of reference audio signatures using a matching algorithm having a first set of at least one parameter.
3. The device of claim 2 where said score is based on a second matching module that selects said second reference audio signature from among a plurality of reference audio signatures using a matching algorithm having a second set of at least one parameter, said second set being more relaxed than said first set.
4. The device of claim 1 where said score is based on synchronization information determined by said synchronizer.
5. The device of claim 1 having a preprocessor operably between said first microphone and said first signature generator, where said preprocessor enhances vocals.
6. The device of claim 1 having a preprocessor operably between said second microphone and said second signature generator, where said preprocessor enhances signals having a low SNR ratio.
7. The device of claim 1 , further including a transmitter that sends said first audio signature to a remote server, and a receiver that receives said score from said remote server.
8. The device of claim 7 where said matching module selects said first reference audio signature from among a plurality of reference audio signatures downloaded from said remote server.
9. The device of claim 1 where said score is used to selectively modify a presentation comprising said audio broadcast.
10. The device of claim 1 where at least one of the said at least two microphones is periodically activated to determine whether said user is providing audio to generate the said first audio signature.
11. A method comprising:
receiving with a processing device first and second audio signals occurring simultaneously, said first audio signal originating from a presentation device proximate said user and said second audio signal originating from a user;
from said first and second audio signals, generating a first data structure representative of audio from said presentation device and generating a second data structure representative of audio from said user;
matching said first data structure to a first reference data structure;
synchronizing said second data structure to said first reference data structure;
comparing said second data structure to at least one second reference data structure;
scoring said audio from said user based on said comparison; and
performing an action based upon said scoring.
12. The method of claim 11 where said first and second data structures are generated by determining which portions of said simultaneously received first and second audio signals represent audio from said first and second audio sources, respectively.
13. The method of claim 11 where at least one of said first and second data structures is a set of audio samples.
14. The method of claim 11 where at least one of said first and second data structures is an audio signature.
15. The method of claim 11 where at least one of said first and second reference data structures is a set of audio samples.
16. The method of claim 11 where at least one of said first and second reference data structures is an audio signature.
17. The method of claim 11 where said first and second audio signals are recorded by first and second microphones, respectively.
18. The method of claim 17 including the step of periodically deactivating said first microphone based on the amount of energy in said second audio signal from said second microphone.
19. A method comprising:
receiving a signal comprising audio from a presentation device proximate a viewer, intermixed with audio from said viewer;
processing said signal to identify a first component of said signal, said first component comprising at least one interval in said signal not including said audio from said viewer;
using said first component of said signal to match said signal to a first reference audio signature;
using the matched said first reference audio signature to identify a second reference audio signature and synchronizing at least a portion of said signal to said second reference audio signature;
generating a score for said audio from said viewer based on comparing said at least a portion of said signal to the synchronized said second reference audio signature; and
displaying said score to said viewer.
20. The method of claim 19 including the step of identifying a second component of said signal, said second component comprising at least one interval in said signal including said audio from said viewer, and where said score is based on comparing said second component to said second reference audio signature.
21. The method of claim 19 where said signal is received by a first microphone configured to receive audio primarily from a direction away from said viewer, and said first component is identified using a second signal received by a second microphone configured to receive audio primarily from a direction toward said viewer.
22. The method of claim 19 where said first component is matched to said first reference audio signature by nullifying portions of said signal not included in said at least one interval.