Partial Identification Analysis for MP3 Music

Abstract

With the advent of BitTorrent protocol, internet users can easily share their movie and music files. Although the BitTorrent provides a highly efficient mechanism, the illegal use of BitTorrent on unauthorized distributing of copyright- protected digital content is increasing rapidly. To prevent illegal distribution of copyrighted files from spreading over the internet, the file pieces split by torrent file must be detected as soon as possible. In this paper, we propose a method of audio recognition on a few pieces of audio files downloaded by BitTorrent client program. The audio identification algorithm is made up of beat tracking and chroma features. To identify audio in the piece, the beat-by-chroma representations obtained from the piece and original audio are cross-correlated and look for sharp peaks. The experimental results show probabilities of successfully identifying the pieces with different piece sizes and different number of pieces.