Content recognition and synchronization using local caching

1. A method of synchronizing a device with a program having an audio signal component, the method comprising:

with a processor in the device:

detecting a digital watermark signal in an audio signal;

based on the digital watermark signal, identifying a fingerprint database corresponding to the program;

obtaining through a network connection and caching locally in a memory of the device a local fingerprint database for the program;

extracting audio features from incoming segments of the audio signal, and forming fingerprints for the incoming segments from audio features extracted from corresponding segments;

matching the fingerprints for the incoming segments with audio fingerprints for the program in the local fingerprint database in the memory of the device, and responsive to detecting matches between fingerprints for incoming segments and matching audio fingerprints in the local fingerprint database, obtaining from the local fingerprint database program times corresponding to the matching audio fingerprints; and

tracking the program times relative to a time reference in the device to keep track of where a user is within the program as the device is exposed to audio of the program.

2. The method of claim 1 wherein the tracking comprises tracking the program times relative to elapsed time from a first program time corresponding to a first matching audio fingerprint.

3. The method of claim 2 including:

with a processor, synchronizing auxiliary services on the device with events in the program as determined from the elapsed time within the device.

4. The method of claim 1 wherein the matching is used to detect a discontinuity in a user's exposure to a program.

5. The method of claim 1 wherein the matching is used to detect time shifting, and with a processor, downloading supplemental material that is configured for time shifted mode, and synchronizing the supplemental material with program events based on the tracking.

6. The method of claim 4 wherein the discontinuity comprises a switch to a different program.

7. The method of claim 1 comprising:

invoking watermark detection in response to detecting loss of synchronization; and

re-establishing synchronization with a time reference obtained from the watermark detection.

8. The method of claim 1 comprising:

wherein the time reference is obtained from a sequence of digital watermarks decoded from the audio signal.

9. A device comprising:

a microphone;

a memory;

a radio for connecting to a network service through a cellular or wi-fi network;

one or more processors, programmed to:

detect a digital watermark signal in an audio signal of a program sensed by the microphone;

identify a fingerprint database corresponding to the program based on the digital watermark signal;

obtain through a network connection and cache locally in the memory a local fingerprint database for the program;

extract audio features from incoming segments of the audio signal, and form fingerprints for the incoming segments from audio features extracted from corresponding segments;

match the fingerprints for the incoming segments with audio fingerprints for the program in the local fingerprint database in the memory, and responsive to detecting matches between fingerprints for incoming segments and matching audio fingerprints in the local fingerprint database, obtain from the local fingerprint database program times corresponding to the matching audio fingerprints; and

track the program times relative to a time reference in the device to keep track of where a user is within the program as the device is exposed to audio of the program.

10. The device of claim 9 including a processor configured to track the program times relative to elapsed time from a first program time corresponding to a first matching audio fingerprint.

11. The device of claim 10 including a processor configured to synchronize auxiliary services on the device with events in the program as determined from the elapsed time within the device.

12. The device of claim 10 including a processor configured to detect a discontinuity in a user's exposure to a program based on data associated with the matching audio fingerprints in the local fingerprint database.

13. The device of claim 12 wherein the discontinuity comprises a switch to a different program.

14. The device of claim 9 including a processor configured to detect time shifting from data associated with the matching audio fingerprints, configured to download supplemental material that is configured for time shifted mode, and configured to synchronize the supplemental material with program events based on the tracking.

15. A non-transitory, computer readable medium on which is stored instructions, which when executed by a processor, perform a method of synchronizing a device with a program having an audio signal, the method comprising:

detecting a digital watermark signal in the audio signal;

based on the digital watermark signal, identifying a fingerprint database corresponding to the program;

obtaining through a network connection and caching locally in a memory of the device a local fingerprint database for the program;

extracting audio features from incoming segments of the audio signal, and forming fingerprints for the incoming segments from audio features extracted from corresponding segments;

matching the fingerprints for the incoming segments with audio fingerprints for the program in the local fingerprint database in the memory of the device, and responsive to detecting matches between fingerprints for incoming segments and matching audio fingerprints in the local fingerprint database, obtaining from the local fingerprint database program times corresponding to the matching audio fingerprints; and

tracking the program times relative to a time reference in the device to keep track of where a user is within the program as the device is exposed to audio of the program.

16. The medium of claim 15 wherein the tracking comprises tracking the program times relative to elapsed time from a first program time corresponding to a first matching audio fingerprint.

17. The medium of claim 16 including instructions, which when executed by a processor, perform an act of:

synchronizing auxiliary services on the device with events in the program as determined from the elapsed time within the device.

18. The medium of claim 16 wherein the matching is used to detect time shifting, and the medium including instructions, which when executed by a processor, perform acts of:

downloading supplemental material that is configured for time shifted mode, and synchronizing the supplemental material with program events based on the tracking.

19. The medium of claim 16 including instructions, which when executed by a processor, perform acts of:

invoking watermark detection in response to detecting loss of synchronization; and

re-establishing synchronization with a time reference obtained from the watermark detection.

20. The medium of claim 16 wherein the time reference is obtained from a sequence of digital watermarks decoded from the audio signal.