Name
Abstract | ||
|---|---|---|
We describe the MusicMiner system for organizing large collections of music with databionic mining techniques. Low level audio features are extracted from the raw au- dio data on short time windows during which the sound is assumed to be stationary. Static and temporal statis- tics were consistently and systematically used for aggre- gation of low level features to form high level features. A supervised feature selection targeted to model percep- tual distance between different sounding music lead to a small set of non-redundant sound features. Clustering and visualization based on these feature vectors can discover emergent structures in collections of music. Visualization based on Emergent Self-Organizing Maps in particular en- ables the unsupervised discovery of timbrally consistent clusters that may or may not correspond to musical genres and artists. We demonstrate the visualizations capabilities of the U-Map, displaying local sound differences based on the new audio features. An intuitive browsing of large music collections is offered based on the paradigm of to- pographic maps. The user can navigate the sound space and interact with the maps to play music or show the con- text of a song. |
Year | Venue | Keywords |
|---|---|---|
2005 | ISMIR 2013 | visualization,music similarity,perception,audio features,clustering,feature selection,feature vector |
Field | DocType | Citations |
Feature vector,Feature selection,Topographic map,Visualization,Musical,Computer science,Speech recognition,Raw audio format,Cluster analysis,Perception | Conference | 35 |
PageRank | References | Authors |
1.54 | 15 | 4 |
Name | Order | Citations | PageRank |
|---|---|---|---|
| Fabian Mörchen | 1 | 372 | 17.94 |
| Alfred Ultsch | 2 | 403 | 51.77 |
| Mario Nöcker | 3 | 42 | 2.53 |
| Christian Stamm | 4 | 38 | 2.12 |