Abstract | ||
---|---|---|
Previous work has explored the concept of music similarity measures and a variety of methods have been proposed for calculating such measures. This paper describes a system for music similarity which attempts to model and compare some of the more musically salient features of a set of audio signals. A model for timbre and a model for rhythm are implemented directly from previous work, and a model for song structure is developed. The different models are weighted and combined to provide an overall music similarity measure. The system is tested on a small set of popular music files spanning eleven different genres. The system is tuned to estimate genre boundaries using multidimensional scaling - a technique that allows for quick visualization of similarity data. An "automatic DJ" application, that generates playlists based on the music similarity models, serves as a subjective evaluation for the system. |
Year | Venue | Keywords |
---|---|---|
2006 | ISMIR 2013 | music similarity,playlist generation,song structure.,multidimensional scaling,automatic dj |
Field | DocType | Citations |
Audio signal,Multidimensional scaling,Similarity measure,Visualization,Computer science,Speech recognition,Popular music,Rhythm,Timbre,Salient | Conference | 3 |
PageRank | References | Authors |
0.41 | 9 | 1 |
Name | Order | Citations | PageRank |
---|---|---|---|
Kurt Jacobson | 1 | 47 | 4.66 |