Abstract | ||
---|---|---|
Voice separation is a critical component of music information retrieval, music analysis and automated transcription systems. We present a contig mapping approach to voice separation based on perceptual principles. The algorithm runs in O(n2) time, uses only pitch height and event boundaries, and requires no user-defined parameters. The method segments a piece into contigs according to voice count, then reconnects fragments in adjacent contigs using a shortest distance strategy. The order of connection is by distance from maximal voice contigs, where the voice ordering is known. This contig-mapping algorithm has been implemented in VoSA, a Java-based voice separation analyzer software. The algorithm performed well when applied to J. S. Bach's Two- and Three-Part Inventions and the forty-eight Fugues from the Well-Tempered Clavier. We report an overall average fragment consistency of 99.75%, correct fragment connection rate of 94.50% and average voice consistency of 88.98%, metrics which we propose to measure voice separation performance. |
Year | DOI | Venue |
---|---|---|
2004 | 10.1007/978-3-540-31807-1_1 | CMMR |
Keywords | Field | DocType |
contig mapping approach,music analysis,correct fragment connection rate,adjacent contigs,voice count,maximal voice contigs,polyphonic music,separating voice,contig-mapping algorithm,voice separation performance,average voice consistency,java-based voice separation analyzer,voice separation | Music information retrieval,Music theory,Music perception,Computer science,Contig,Speech recognition,Software,Contig Mapping,Polyphony,Java | Conference |
Volume | ISSN | ISBN |
3310 | 0302-9743 | 3-540-24458-1 |
Citations | PageRank | References |
15 | 1.43 | 3 |
Authors | ||
2 |
Name | Order | Citations | PageRank |
---|---|---|---|
Elaine Chew | 1 | 36 | 5.17 |
Xiaodan Wu | 2 | 15 | 1.43 |