Internet services expose nowadays vast amounts of multimedia data for exchange and browsing, the most notable example being YouTube. These digital databases cannot be easily searched through, because automatic understanding and indexing of multimedia content is still too difficult for computers - take, for example, the diversity of musical trends and genres, uncommon instruments or the variety of performers and their compositions present in typical multimedia databases.
In ISMIS 2011 Contest, researchers and students interested in sound recognition and related areas (signal processing, data mining, machine learning) are invited to design algorithms for two important and challenging problems of Music Information Retrieval:
- Recognition of genre of music (jazz, rock, pop, ...) from a short sample, and
- Recognition of instruments playing together in a given music track.
Competition web page: tunedit.org/challenge/music-retrieval