New patents are issued by the USPTO on Tuesdays. Today's Spotlight Patents concern aspects of digital watermarking and digital fingerprinting. Assigned to Google, the first patent addresses techniques for marking audio/video (A/V) signals for use in tracing content to a source. Assigned to Facebook, the second patent addresses techniques for detecting distorted audio signals based on audio fingerprinting.
9,392,344, "Audio/video identification watermarking," assigned to Google.
The invention is directed to marking audio/video (A/V) signals for use in tracing content to a source. An ID controller captures an A/V synchronization fingerprint from a master A/V signal, stores the fingerprint in a data store, and provides signals to an ID encoder to have encoded an identifier into a copy of the master A/V signal. The identifier is encoded to be persistent through actions such as capture, compression, and/or transcoding. In one embodiment, the identifier is encoded as a bit sequence, where each bit is encoded using an encoding technique that is hereinafter called a Mississippi encoding technique. The encoded identifier within the copied A/V signal may later be determined by extracting the fingerprint and comparing it to the stored fingerprint to determine the identifier. The identifier may then be used to trace a source of the copied A/V signal.
9,390,727, "Detecting distorted audio signals based on audio fingerprinting," assigned to Facebook.
An audio identification system generates a probe audio fingerprint of an audio signal and determines amount of pitch shifting in the audio signal based on analysis of correlation between the probe audio fingerprint and a reference audio fingerprint. The audio identification system applies a time-to-frequency domain transform to frames of the audio signal and filters the transformed frames. The audio identification system applies a two-dimensional discrete cosine transform (DCT) to the filtered frames and generates the probe audio fingerprint from a selected number of DCT coefficients. The audio identification system calculates a DCT sign-only correlation between the probe audio fingerprint and the reference audio fingerprint, and the DCT sign-only correlation closely approximates the similarity between the audio characteristics of the probe audio fingerprint and those of the reference audio fingerprint. Based on the correlation analysis, the audio identification system determines the amount of pitch shifting in the audio signal.