Abstract
We present a new method to segment popular music based on rhythm. By computing a shortest path based on the self-similarity matrix calculated from a model of rhythm, segmenting boundaries are found along the di- agonal of the matrix. The cost of a new segment is opti- mized by matching manual and automatic segment boundaries. We compile a small song database of 21 randomly selected popular Chinese songs which come from Chinese Mainland, Taiwan and Hong Kong. The segmenting results on the small corpus show that 78% manual segmentation points are detected and 74% auto- matic segmentation points are correct. Automatic seg- mentation achieved 100% correct detection for 5 songs. The results are very encouraging.
| Original language | English |
|---|---|
| Title of host publication | Proceeding of the ISMIR |
| Number of pages | 7 |
| Publisher | Queen Mary and Goldsmith College, University of London |
| Publication date | 2005 |
| Pages | 374-380 |
| ISBN (Print) | 0955117909 |
| Publication status | Published - 2005 |
| Event | International Conference on Music Information Retrieval - London, United Kingdom Duration: 11 Sept 2005 → 15 Sept 2005 Conference number: 6 |
Conference
| Conference | International Conference on Music Information Retrieval |
|---|---|
| Number | 6 |
| Country/Territory | United Kingdom |
| City | London |
| Period | 11/09/2005 → 15/09/2005 |