An overview of audio information retrieval
Multimedia Systems - Special issue on audio and multimedia
Machine Learning
Signal Processing Methods for Music Transcription
Signal Processing Methods for Music Transcription
Maximum Likelihood Study for Sound Pattern Separation and Recognition
MUE '07 Proceedings of the 2007 International Conference on Multimedia and Ubiquitous Engineering
Cooperative music retrieval based on automatic indexing of music by instruments and their types
Cooperative music retrieval based on automatic indexing of music by instruments and their types
Musical Instruments in Random Forest
ISMIS '09 Proceedings of the 18th International Symposium on Foundations of Intelligent Systems
Journal of Intelligent Information Systems
Random musical bands playing in random forests
RSCTC'10 Proceedings of the 7th international conference on Rough sets and current trends in computing
Boruta - A System for Feature Selection
Fundamenta Informaticae
Recognition of instrument timbres in real polytimbral audio recordings
ECML PKDD'10 Proceedings of the 2010 European conference on Machine learning and knowledge discovery in databases: Part II
All that jazz in the random forest
ISMIS'11 Proceedings of the 19th international conference on Foundations of intelligent systems
Harmonic source separation using prestored spectra
ICA'06 Proceedings of the 6th international conference on Independent Component Analysis and Blind Signal Separation
Hi-index | 0.00 |
In this paper, we deal with the difficult problem of automatic identification of multiple instruments playing sounds of the same pitch, i.e. in unison. Random forests have been selected to be used as a classifier. Training data represent isolated sounds of selected instruments which originate from three commonly used repositories, namely McGill University Master Samples, The University of IOWA Musical Instrument Samples, and RWC. Testing data represent audio records especially prepared by one of the authors for research purposes, and next carefully labeled. The experiments on identification of instruments in a frame-by-frame manner and the obtained results are presented and discussed.