Generating Audio Fingerprints based on Audio Signal Complexity
AssigneeFacebook, Inc.
InventorSergiy Bilobrov
Life of this patent
Estimating the term…
Abstract
An audio identification system accounts for an audio signal's complexity when generating a test audio fingerprint for identification of the audio signal. In particular, the audio identification system determines a complexity of an audio signal to be fingerprinted. For example, the audio signal's complexity may be determined by performance of an autocorrelation on the audio signal. Based on the determined complexity, the audio identification system determines a length of a sample of the audio signal used to generate a test audio fingerprint. A sample having the length is then obtained and used to generate a test audio fingerprint for the audio signal. The test audio fingerprint may be compared to a set of reference audio fingerprints to identify the audio signal.
Claims20
A computer-implemented method comprising:
- receiving an audio signal including a plurality frames, each frame representing a portion of the audio signal;
- selecting an initial window of one or more frames from the plurality of frames;
- generating an initial window fingerprint based on the initial window;
- selecting an additional window of one or more frames from the plurality of frames;
- generating an additional window fingerprint based on the additional window;
- determining whether the initial window fingerprint matches the additional window fingerprint;
- determining a length for a sample of the audio signal based on determining whether the initial window fingerprint matches the additional window fingerprint;
- obtaining a sample of the audio signal having the determined length;
- generating a test audio fingerprint of the audio signal from the obtained sample;
- and
- comparing the test audio fingerprint to a set of reference audio fingerprints.
A computer-implemented method comprising:
- determining a complexity of an audio signal based at least in part on one or more audio characteristics of the audio signal;
- determining a sample length for generating a test audio fingerprint for the audio signal based on the determined complexity of the audio signal;
- obtaining a sample of the audio signal having the determined sample length;
- and
- generating the test audio fingerprint based on the obtained sample of the audio signal.
A computer-implemented method comprising:
- selecting an initial window of one or more frames of an audio signal, each frame corresponding to a portion of the audio signal;
- generating an initial window fingerprint based on the initial window;
- receiving additional frames of the audio signal;
- selecting an additional window of one or more frames of the audio signal, the additional window including one or more of the received additional frames;
- generating an additional window fingerprint based on the additional window of one or more frames;
- comparing the initial window fingerprint to the additional window fingerprint;
- determining a sample length based on the comparing;
- obtaining a sample of the audio signal having the determined sample length;
- generating a test audio fingerprint of the audio signal based on the obtained sample of the audio signal;
- comparing the test audio fingerprint to one or more reference audio fingerprints;
- responsive to the test audio fingerprint matching a reference audio fingerprint, associating the audio signal with identifying information associated with the reference audio fingerprint.
Dependencies are inferred from the claim text.