Guest Editorial: Special Section on Music Data Mining

Abstract

M USIC has been an important application area for data mining and machine learning techniques for many years. Music data mining is an interdisciplinary area that studies computational methods for understanding and delivering music data and is a topic of growing importance with large commercial relevance and substantial potential. It attracts researchers not only from computer science, electrical engineering, and musicology but also library science and psychology [1]. During the last few years there has been a dramatic shift in how music is produced, distributed and consumed. A combination of advances in digital storage, audio compression as well as significant increases in network bandwidth has made digital music distribution a reality. Portable music players, computers and smart phones frequently contain personal collections of thousands of music tracks. Digital stores in which users can purchase music contain millions of tracks that can be easily downloaded. The research area of music data mining has gradually evolved during this time period in order to address the challenge of effectively accessing and interacting with these increasing large collections of music and associated data such as styles, artists, lyrics and music reviews. The algorithms and systems developed frequently employ sophisticated and advanced data mining and machine learning techniques in their attempt to better capture the frequently elusive relevant music information. Recent advancements in music listening technologies, in particular, the Internet-based music communities, radio stations and music stores, have introduced several new interesting aspects to the area, such as multimodal analysis of music data, community-based labeling of music, and listening pattern analysis. The introduction has made the area an exciting research ground and there is a strong and emergent need to publicize this area in multimedia literature. In addition, music data is of significant scale with diverse information sources and aspects. Many of the relevant aspects such as user behaviors and web-based information retrieval have direct analogies in other multimedia content items including images, videos, and pictures. As a result, the techniques and tools developed in music data mining can be relevant and useful in general to other areas of multimedia research.

DOI: 10.1109/TMM.2014.2325693

Extracted Key Phrases

Cite this paper

@article{Li2014GuestES, title={Guest Editorial: Special Section on Music Data Mining}, author={Tao Li and Mitsunori Ogihara and George Tzanetakis}, journal={IEEE Trans. Multimedia}, year={2014}, volume={16}, pages={1185-1187} }