원문정보
초록
영어
In this paper, we propose a methodology for identification of MP3 audio pieces downloaded by BitTorrent client program using cross-correlation of 12 chroma features extracted from audio signal. To prevent illegal distribution of copyrighted audio files from spreading over the internet, the file pieces split by torrent file must be detected as accurately as possible. In order to improve the probability of successfully identifying the audio pieces, we use Peak In Piece Position (PIPP) method which means the maximum peak appeared in a range corresponding to piece position and length is selected to reduce the probability of misidentification. The experimental results show probabilities of successfully identification of the pieces with different piece properties, comparisons between the proposed algorithms and conventional algorithm in terms of precisions and robustness of the proposed algorithms.
목차
1. Introduction
2. BitTorrent Audio Piece
2.1. BitTorrent Protocol
2.2. MP3 Audio Piece
3. Identification Algorithms
3.1. Conventional Identification Algorithm
3.2. Streamlined Algorithm
3.3. Improved Algorithm with 2D Cross Correlation Using 2D FFT
3.4. Optimized Algorithm using PIPP
4. Performance Evaluation
4.1. Experimental Data
4.2. Results and Discussion
5. Conclusion
Acknowledgments
References