×

Content recognition employing fingerprinting at different resolutions

  • US 9,280,977 B2
  • Filed: 12/09/2014
  • Issued: 03/08/2016
  • Est. Priority Date: 05/21/2009
  • Status: Active Grant
First Claim
Patent Images

1. A method of content recognition comprising:

  • receiving an audio signal captured from a microphone;

    sampling the audio signal at a first resolution to provide a first sampled audio signal;

    with a processor, computing at least a first audio fingerprint from the first sampled audio signal;

    transferring the first audio fingerprint to a remote server, and in response, receiving metadata identifying a TV show, advertisement, movie or song from which the audio signal has been captured;

    sampling the audio signal at a second resolution to provide a second sampled audio signal;

    with a processor, computing at least a second audio fingerprint from the second sampled audio signal;

    transferring the second audio fingerprint to a remote server, and in response to transferring the second audio fingerprint, receiving metadata to distinguish between distinct versions of the TV show, advertisement, movie or song from which the audio signal has been captured;

    wherein the first and second fingerprints are derived from first and second different resolutions of the audio signal, corresponding to fingerprint databases corresponding to the first and second resolutions.

View all claims
  • 0 Assignments
Timeline View
Assignment View
    ×
    ×