| |
  |
| Visually Searching For Music Based On Its Sound |
|
 |
|
posted by Editor
on Monday October 16, @05:42PM
|
|
|
|
|
This article in MIT Technology Review discusses the AudioRadar tool for navigating large music collections. AudioRadar usese a coherent visual metaphor to show similarity between songs. The system scans a music collection, measuring song qualities in terms of tempo, chordal shifts, volume, and harmony. Then it weights the songs by four key criteria: speed; melodic or rhythmic; turbulent or calm; and rough or clean. Based on these metrics, the application creates a map in which a chosen song appears at the center of the screen, with similar songs clustered in a circle around it (see screenshot). The design is discussed in this paper (PDF). The article also compares AudioRadar with several other systems that help search for music based on its sound, including Liveplasma, Pandora, Last.fm, Musipedia, Playola, and Search Inside the Music.
|
|
|
|
< iZ3D 3D User Interface Display System Brings Games To Life
| Will Social Profiles Be Killer App For The Semantic Web? >
| |
|
