This technology describes a robust algorithm for acoustic fingerprinting capable of characterizing a particular audio event within a media file and identifying similar events within a database.
Databases of audio and video media are ever-expanding as audio and audio-video recording devices and public sharing platforms continue to proliferate. There is a significant need to automate the organization of this type of data as well as to develop efficient methods for the identification, detection, and sorting of audio files.
This technology obtains audio fingerprints using the matching pursuit algorithm, which decomposes a signal into a signature of distinctive energy bursts localized in time and frequency to form landmarks. The landmarks’ signatures and locations in the audio files are subsequently placed in an easily searchable hash table. Similar events in a database may be quickly identified by querying the hash table. Using energy bursts as a characterization metric allows the technology to identify unique acoustic events even in the presence of noise or background. The technology has great utility within the contexts of quickly identifying both music and cinematic copyright infringements, managing personal or public media databases, or identification of an event as recorded from multiple devices with differing background noise.
The algorithm's performance was tested on over 700 YouTube videos of the 2009 presidential inauguration address.
Daniel P.W. Ellis, Ph.D.
Patent Issued (US 8,706,276)
IR M10-035
Licensing Contact: Greg Maskel