Name
Title | ||
|---|---|---|
Unsupervised Single-Channel Music Source Separation by Average Harmonic Structure Modeling |
Abstract | ||
|---|---|---|
Source separation of musical signals is an appealing but difficult problem, especially in the single-channel case. In this paper, an unsupervised single-channel music source separation algorithm based on average harmonic structure modeling is proposed. Under the assumption of playing in narrow pitch ranges, different harmonic instrumental sources in a piece of music often have different but stable harmonic structures; thus, sources can be characterized uniquely by harmonic structure models. Given the number of instrumental sources, the proposed algorithm learns these models directly from the mixed signal by clustering the harmonic structures extracted from different frames. The corresponding sources are then extracted from the mixed signal using the models. Experiments on several mixed signals, including synthesized instrumental sources, real instrumental sources, and singing voices, show that this algorithm outperforms the general nonnegative matrix factorization (NMF)-based source separation algorithm, and yields good subjective listening quality. As a side effect, this algorithm estimates the pitches of the harmonic instrumental sources. The number of concurrent sounds in each frame is also computed, which is a difficult task for general multipitch estimation (MPE) algorithms. |
Year | DOI | Venue |
|---|---|---|
2008 | 10.1109/TASL.2008.919073 | IEEE Transactions on Audio, Speech & Language Processing |
Keywords | Field | DocType |
harmonic instrumental source,different harmonic instrumental source,harmonic structure model,unsupervised single-channel music source separation algorithm,unsupervised single-channel music source,musical signal,multipitch estimation,matrix algebra,source separation,stable harmonic structure,nonnegative matrix factorization,proposed algorithm,harmonic analysis,harmonic structure,clustering,real instrumental source,single-channel source separation,average harmonic structure modeling,instrumental source,multipitch estimation algorithm,mixed signal,multiple signal classification,side effect,concurrent computing,independent component analysis,space technology,clustering algorithms | Audio signal,Pattern recognition,Computer science,Matrix decomposition,Harmonic,Speech recognition,Harmonic analysis,Artificial intelligence,Independent component analysis,Non-negative matrix factorization,Cluster analysis,Source separation | Journal |
Volume | Issue | ISSN |
16 | 4 | 1558-7916 |
Citations | PageRank | References |
24 | 1.06 | 27 |
Authors | ||
4 | ||
Name | Order | Citations | PageRank |
|---|---|---|---|
| Zhiyao Duan | 1 | 305 | 26.86 |
| Yungang Zhang | 2 | 87 | 10.05 |
| Changshui Zhang | 3 | 5506 | 323.40 |
| Zhenwei Shi | 4 | 559 | 63.11 |