Syndication Including Melody Recognition and Opt Out

摘要

A syndication system facilitates rights management services between media content owners and media hosting services that elect to participate in the syndication system and mutually elect to participate with each other. The syndication system utilizes a content recognition system to identify hosted media content and ownership rights associated with the hosted content. By applying melody recognition, the content recognition system can identify compositions embodied in hosted media content even when these compositions do not precisely match any known sound recording. Thus, the content recognition system is beneficially able to detect, for example, recorded cover performances and recorded live performances embodied in hosted media content. Once identified, ownership information is determined and the syndication system can facilitate rights management policies associated with the content such as monetizing or blocking the protected content.

主权项

1. A computer-implemented method for facilitating a rights management service between a composition owner and a media hosting service, the method comprising:
receiving from the media hosting service, a representation of an input media file, the input media file including an audio clip; processing the audio clip to extract dominant musical tones present in the audio clip; generating, by a processing device, an input melody fingerprint for the audio clip, the input melody fingerprint representing a sequence of pitch intervals between the dominant musical tones present in the processed audio clip; determining a matching reference melody fingerprint from a melody fingerprint reference database that matches the input melody fingerprint, the matching reference melody fingerprint representing a melody of a composition that is embodied in the audio clip; determining a strength of the match between the matching reference melody fingerprint and the input melody fingerprint; generating an input audio fingerprint for the audio clip representing features that uniquely represent a sound recording embodied by the audio clip; comparing the input audio fingerprint to a plurality of reference audio fingerprints in an audio fingerprint reference database; and identifying a matching reference audio fingerprint that matches the input audio fingerprint responsive to the comparing and the determined strength of the match between the matching reference melody fingerprint and the input melody fingerprint; identifying the composition owner as having ownership of the composition based on a reference sound recording associated with the determined matching reference melody fingerprint and with the identified matching reference audio fingerprint; and facilitating an ownership management policy between the media hosting service and the composition owner, the ownership management policy associated with use of the input media file by the media hosting service.