Paper Info
Title
Improving instrument recognition in polyphonic music through system integration
Abstract
A method is proposed for instrument recognition in polyphonic music which combines two independent detector systems. A polyphonic musical instrument recognition system using a missing feature approach and an automatic music transcription system based on shift invariant probabilistic latent component analysis that includes instrument assignment. We propose a method to integrate the two systems by fusing the instrument contributions estimated by the first system onto the transcription system in the form of Dirichlet priors. Both systems, as well as the integrated system are evaluated using a dataset of continuous polyphonic music recordings. Detailed results that highlight a clear improvement in the performance of the integrated system are reported for different training conditions.
Year
DOI
Venue
2014
10.1109/ICASSP.2014.6854599
Acoustics, Speech and Signal Processing
Keywords
Field
DocType
audio signal processing,musical instruments,principal component analysis,Dirichlet priors,automatic music transcription system,continuous polyphonic music recordings,independent detector systems,instrument assignment,instrument recognition,missing feature approach,shift invariant probabilistic latent component analysis,system integration,Musical instrument recognition,automatic music transcription,music signal analysis
Probabilistic latent component analysis,Pattern recognition,Computer science,Speech recognition,Artificial intelligence,Invariant (mathematics),Dirichlet distribution,Polyphony,Musical instrument recognition,Prior probability,Detector,System integration
Conference
ISSN
Citations 
PageRank 
1520-6149
3
0.40
References 
Authors
11
4
Name
Order
Citations
PageRank
Dimitrios Giannoulis130114.36
Emmanouil Benetos255752.48
Anssi Klapuri385870.02
M. D. Plumbley41915202.38