Multiple step identification of recordings

Abstract

Multiple information is extracted from an unknown recording and information associated therewith. Associated information includes the filename, if the recording is a computer file in, e.g., MP3 format, or table of contents (TOC) data, if the recording is on a removable medium, such as a compact disc. At least one and preferably several algorithmically determined fingerprints are extracted from the recording using one or more fingerprint extraction methods. The information extracted is compared with corresponding information in a database maintained for reference recordings. Identification starts with the most accurate and efficient method available, e.g., using a hash ID, a unique ID or text. Fingerprint matching is used to confirm other matches and validation is performed by comparing the duration of the unknown and a possibly matching reference recording.

Description

CROSS-REFERENCE TO RELATED APPLICATION(S)[0001]This application is a Divisional of U.S. application Ser. No. 10 / 208,189, filed on Jul. 31, 2002, which claims priority to U.S. Provisional Application No. 60 / 308,594, filed Jul. 31, 2001, and which applications are incorporated by reference herein in their entirety.BACKGROUND OF THE INVENTION[0002]1. Field of the Invention[0003]The present invention is directed to recognition of recordings from their content, and, more particularly to combining fingerprint recognition with other information about a recording to increase reliability of recognition and to accomplish reliable recognition efficiently by using the least expensive forms of recognition first and layering on more complex forms as needed.[0004]2. Description of the Related Art[0005]There are many uses for recognition of audio (and video) recordings. Many of the uses relate to compensation or control by the rights holders for reproduction and performance of the works recorded. T...

AI Technical Summary

Benefits of technology

[0010]An aspect of the present invention is maximizing identification of recordings while minimizing resource usage.

[0012]A further aspect of the invention is minimization of processing of unidentified data.

[0015]Yet another aspect of the present invention is use of recording identification methods from different sources to increase reliability.

[0020]Preferably, the database is maintained by a provider of identification services which supplies unique identifiers that can be recognized only by servers under the control of the provider of identification services. The unique identifiers are associated with recordings once they have been identified. Subsequently, copies of the recordings are recognized using the unique identifiers to greatly speed up the process. The unique identifiers optionally are cached in high-speed RAM or specially indexed database tables.

Problems solved by technology

Although the need for accurate recognition has been significant for several years, no system has been successful in meeting this need.

By relying on just one fingerprinting technique, single source solutions are less accurate when encountering a ‘blind spot’.

However, the ID3V2 tags can easily be manipulated to store a TUID for one file in the ID3V2 tag for another file and therefore, the TUID alone is not a reliable identifier of the audio content in a file.

Although this text matching utilizes user-generated spelling variants associated with each record to improve recognition, there has been no way to verify that the text matches the audio content of the recording once the recording has been separated from a compact disc and stored in a file in any format.

Images