10 January 2003 Media segmentation using self-similarity decomposition
Author Affiliations +
We present a framework for analyzing the structure of digital media streams. Though our methods work for video, text, and audio, we concentrate on detecting the structure of digital music files. In the first step, spectral data is used to construct a similarity matrix calculated from inter-frame spectral similarity.The digital audio can be robustly segmented by correlating a kernel along the diagonal of the similarity matrix. Once segmented, spectral statistics of each segment are computed. In the second step,segments are clustered based on the self-similarity of their statistics. This reveals the structure of the digital music in a set of segment boundaries and labels. Finally, the music is summarized by selecting clusters with repeated segments throughout the piece. The summaries can be customized for various applications based on the structure of the original music.
© (2003) COPYRIGHT Society of Photo-Optical Instrumentation Engineers (SPIE). Downloading of the abstract is permitted for personal use only.
Jonathan T. Foote, Jonathan T. Foote, Matthew L. Cooper, Matthew L. Cooper, } "Media segmentation using self-similarity decomposition", Proc. SPIE 5021, Storage and Retrieval for Media Databases 2003, (10 January 2003); doi: 10.1117/12.476302; https://doi.org/10.1117/12.476302


Using content models to build audio-video summaries
Proceedings of SPIE (December 16 1998)
Texture resynthesis using principle component analysis
Proceedings of SPIE (May 29 2002)
New approach for logo recognition
Proceedings of SPIE (March 30 2000)
PNRS: personalized news retrieval system
Proceedings of SPIE (August 23 1999)
Content-based classification and retrieval of audio
Proceedings of SPIE (October 01 1998)

Back to Top