A method for recognizing a media entity in a media sample

Abstract

The present invention provides a method which is used for identifying medium entity from the medium sample, and the method comprises the following procedures: generating the consistency between the sign of the medium sample and the corresponding sign of the medium entity to be identified, wherein the sign of the medium sample and the corresponding sign of the medium entity have equivalent fingerprint; and identifying the medium sample and the media file if a plurality of consistencies has the linear relationship defined by the following formula, landmark<*>n=m<*>landmark n +offset, wherein, landmark n is the sample sign, landmark<*>n is the file mark corresponding to the landmark n, and m represents the slope.

Description

[0001] This application is a divisional application of an invention patent application with an application date of July 26, 2001, an application number of 01813565.X, and an invention title of "System and Method for Identifying Sound and Music Signals under Strong Noise and Distortion" . technical field [0002] The present invention generally relates to content-based information retrieval. More specifically, the present invention particularly relates to the identification of audio signals comprising sounds or music that are highly distorted, or contain intense noise. The invention also particularly relates to a method for recognizing media entities from media samples. Background technique [0003] There is an increasing need to automatically recognize music or other audio signals produced from a variety of sources. For example, owners of copyrighted works or advertisers are interested in obtaining data about the broadcast frequency of their material. Music tracking servi...

AI Technical Summary

Problems solved by technology

All these disadvantages make the use of state-of-the-art methods infeasible in many practical applications

Images