Music Similarity and Recommendation

Auditude.Com Computer Science, 2002-03

Liaison(s): Nicholas Seet ’99
Advisor(s): Melissa O’Neill
Students(s): Paul Ruvolo (PM), Brad Poon, Elizabeth Schoof, Nicholas Taylor

The Auditude Clinic team has investigated content-based similarity relationships between musical performances. Similarity is a complex concept involving many judgments. Our team has focused our attention on a combination of rhythm, timbre, and apparent loudness. We have developed software that extracts these features from a recording and uses them to categorize new music, to make recommendations, and to generate playlists that arrange music in a sequence with smooth transitions between songs.