Cloud callout identification of unknown broadcast signatures based on previously recorded broadcast signatures
Broadcast signatures (fingerprints) from different sources are compared to distinguish between a known base media item and unknown versions of the known base media item, without prior storage of the unknown altered versions of the known base media item. Field recorders collect and store in buffers signatures found within portions of sequential broadcast content. Mobile devices (users) collect unknown signatures while recording broadcast content. Using a cloud callout routine, the mobile device requests a comparison between the collected unknown signatures and the field recorded signatures. Potential matches can be loose matches, strict matches or comparisons between failed loose comparisons.
1. A method for identification of a broadcast:
capturing, by one or more recording devices, a plurality of continuous signature representations included as a portion of one or more broadcasts from one or more broadcast sources;
storing, temporarily in separate buffers, each of the plurality of continuous signature representations;
receiving, by a mobile device, a broadcast from the one or more broadcast sources;
analyzing the broadcast to determine at least one unknown signature representation;
delivering, to a cloud computing component, the at least one unknown signature representation; and
comparing the at least one unknown signature representation with each of the plurality of continuous signature representations; and
identifying any potential matches between the at least one unknown signature representation and the plurality of continuous signature representations.
2. The method of claim 1 , wherein the potential matches include any of: loose or strict comparisons, or comparisons between failed loose comparisons.
3. The method of claim 1 , wherein the identification of any potential matches includes identifying any of: a channel, a station, or a source.
4. The method of claim 1 , wherein the identification of any potential matches includes any of: an altered version of a media item or an advertisement.
5. The method of claim 1 , wherein the one or more broadcasts originate from any of: a broadcast radio station, a television station, a streaming video channel, or a streaming audio channel.
6. The method of claim 1 , wherein the one or more broadcasts include broadcasts originating from any of: Internet, communication networks, analog radio frequency broadcasts, digital radio frequency broadcasts, terrestrial broadcasts, satellite radio and television stations.
7. The method of claim 1 , wherein the mobile device includes any of: a tablet, a personal digital assistant, or a mobile phone.
8. The method of claim 1 , wherein the at least one unknown signature is a fingerprint.
9. The method of claim 1 , wherein the capturing, by the one or more recording devices is implemented by any of: a monitoring service or a service provider.
10. The method of claim 1 , wherein the recording devices are field recorders.
11. The method of claim 1 , wherein the plurality of continuous signature representations captured by the one or more recording devices is delivered to a repository.
12. The method of claim 11 , wherein the repository includes any of: a central, a regional server system, a data storage site, a service provider computer system, or a storage local to each of the recording devices.
13. The method of claim 12 , wherein the data stored in the repository includes records corresponding to discreet content items including any of: songs, videos, images, unanticipated, unscripted, or content that may be unknowable until the broadcast is generated.
14. The method of claim 1 , wherein the separate buffers, include any of: a FIFO (first-in-first-out) or LIFO (last-in-first-out) buffer.
15. The method of claim 1 , wherein the plurality of continuous signature representations include any of: audio signatures of advertisements, disc jockey chatter, listener telephone calls, viewer telephone calls, real-time audio content, custom mixed audio content, or prerecorded songs and live content.
16. The method of claim 1 , wherein the analyzing includes a spectral analysis performed on content of the one or more broadcasts intended to be reproduced in human perceptible form.
17. A system for identification of a broadcast, the system includes:
a processing device connected to a communications network, wherein the processing device is configured to:
receive from one or more recording devices, a plurality of continuous signature representations included as a portion of one or more broadcasts;
store, temporarily in separate buffers, each of the plurality of continuous signature representations;
receive a cloud callout from a mobile device to match at least one unknown signature representation;
compare the at least one unknown signature representation with each of the plurality of continuous signature representations; and
identify any potential matches between the at least one unknown signature representation and the plurality of continuous signature representations to identify.
18. The system of claim 17 , wherein the processing device includes any of: a regionally located server, a nationally located server, or a server local to a sub community.
19. The system of claim 17 , wherein identifying any potential matches includes analyzing the broadcast by performing a spectral analysis on all broadcast content intended to be reproduced in human perceptible form.
20. The system of claim 17 , wherein the cloud callout is used to perform any of: loose comparisons, stringent comparisons, comparisons between failed loose comparisons.