Title | ||
---|---|---|
Instrument identification in solo and ensemble music using Independent Subspace Analysis |
Abstract | ||
---|---|---|
We investigate the use of Independent Subspace Analy- sis (ISA) for instrument identification in musical record- ings. We represent short-term log-power spectra of pos- sibly polyphonic music as weighted non-linear combina- tions of typical note spectra plus background noise. These typical note spectra are learnt either on databases contain- ing isolated notes or on solo recordings from different in- struments. We show that this model has some theoreti- cal advantages over methods based on Gaussian Mixture Models (GMM) or on linear ISA. Preliminary experiments with five instruments and test excerpts taken from com- mercial CDs give promising results. The performance on clean solo excerpts is comparable with existing methods and shows limited degradation under reverberant condi- tions. Applied to a difficult duo excerpt, the model is also able to identify the right pair of instruments and to provide an approximate transcription of the notes played by each instrument. |
Year | Venue | Keywords |
---|---|---|
2004 | ISMIR 2013 | gaussian mixture model |
Field | DocType | Citations |
Background noise,Subspace topology,Computer science,Speech recognition,Artificial intelligence,Mixture model,Machine learning | Conference | 20 |
PageRank | References | Authors |
1.41 | 4 | 2 |
Name | Order | Citations | PageRank |
---|---|---|---|
Emmanuel Vincent | 1 | 2963 | 186.26 |
Xavier Rodet | 2 | 627 | 107.87 |