Improving Access to Digital Music through Content-based Analysis
This project is a collaboration between MARL and NYU Library Services, concerned with the research and development of content-based approaches to the automatic organization of, access to and interaction with digital music archives.
The research concentrates on: how can we encode musical attributes such as harmony and rhythm using mid-level representations, how can these representations be used to characterize the similarities that exist between songs and phrases, and how can we use these methodologies to provide users with innovative modes of access to music.
This project has the potential to increase the scalability and reduce the cost of music analysis and markup, while increasing access and dissemination of music in the long-tail of existing collections. These potential results can improve current practices in digital libraries, which will see an increase in their ability to preserve and disseminate culture, and empower music education and research.
- Juan Pablo Bello, principal investigator
- Kent Underwood, co-investigator
- Ron Weiss, post-doctoral researcher
- Tae Min Cho, research assistant
- Gloria Rohmann, co-investigator
- Taemin Cho, Ron J. Weiss and Juan P. Bello. Exploring Common Variations in State of the Art Chord Recognition Systems. Proceedings of the Sound and Music Computing Conference (SMC), Barcelona, Spain, July, 2010.
- T. Bertin-Mahieux, R. J. Weiss, and D. P. W. Ellis. Clustering Beat-Chroma Patterns in a Large Music Database. In Proc. International Conference on Music Information Retrieval (ISMIR), Utrecht, Netherlands, August 2010.
- R. J. Weiss and J. P. Bello. Identifying Repeated Patterns in Music Using Sparse Convolutive Non-Negative Matrix Factorization. In Proc. International Conference on Music Information Retrieval (ISMIR), Utrecht, Netherlands, August 2010.
- Cho, T. and Bello, J.P. "Real-Time Implementation of HMM-Based Chord Estimation in Musical Audio". Proceedings of the International Computer Music Conference (ICMC-09), Montreal, Canada, August, 2009.
- Bello, J.P. "Grouping Recorded Music by Structural Similarity". Proceedings of the International Conference on Music Information Retrieval (ISMIR-09) Kobe, Japan, October, 2009.
- Project Narrative
- 2009 6-months Report (07/01/2009)
- 2009 Annual Report (02/01/2010)
- 2010 6-months Report (07/01/2010)
IN THE PRESS
- Tartar, A. "Madonna Meets Mozart". Cutting-Edge Research. NYU Alumni Magazine, Spring 2010, Issue # 14.
- NYU Today (Fall 2008): http://www.nyu.edu/nyutoday/article/1646
- Progressions, NYU Libraries Newsletter (Fall 2008, last page): http://library.nyu.edu/progressions/progF08.pdf
This project is made possible by National Leadership Grant LG-06-08-0073-08 from the U.S. Institute of Museum and Library Services.