Recognition of Instrument Timbres in Real Polytimbral Audio Recordings

Automatic recognition of multiple musical instruments in polyphonic and polytimbral music is a difficult task, but often attempted to perform by MIR researchers recently. In papers published so far, the proposed systems were validated mainly on audio data obtained through mixing of isolated sounds of musical instruments. This paper tests recognition of instruments in real recordings, using a recognition system which has multilabel and hierarchical structure. Random forest classifiers were applied to build the system. Evaluation of our model was performed on audio recordings of classical music. The obtained results are shown and discussed in the paper.

[1]  Alicja Wieczorkowska,et al.  Identification of a dominating instrument in polytimbral same-pitch mixes using SVM classifiers with non-linear kernel , 2009, Journal of Intelligent Information Systems.

[2]  Zbigniew W. Ras,et al.  Cooperative music retrieval based on automatic indexing of music by instruments and their types , 2007 .

[3]  Xavier Serra,et al.  Towards Instrument Segmentation for Music Content Description: a Critical Review of Instrument Classification Techniques , 2000, ISMIR.

[4]  Shusaku Tsumoto,et al.  Foundations of Intelligent Systems, 15th International Symposium, ISMIS 2005, Saratoga Springs, NY, USA, May 25-28, 2005, Proceedings , 2005, ISMIS.

[5]  Ingo Mierswa.  Collaborative Use of Features in a Distributed System for the Organization of Music Collections , 2008 .

[6]  Masataka Goto,et al.  RWC Music Database: Popular, Classical and Jazz Music Databases , 2002, ISMIR.

[7]  Leo Breiman,et al.  Random Forests , 2001, Machine Learning.

[8]  Perfecto Herrera,et al.  Music Genre Categorization in Humans and Machines , 2006 .

[9]  Vesa T. Peltonen,et al.  Computational auditory scene recognition , 2002, 2002 IEEE International Conference on Acoustics, Speech, and Signal Processing.

[10]  Masataka Goto,et al.  Instrogram: Probabilistic Representation of Instrument Existence for Polyphonic Music , 2007 .

[11]  Riccardo Miotto,et al.  Statistical Music Modeling Aimed at Identification and Alignment , 2010, Advances in Music Information Retrieval.

[12]  Alicja Wieczorkowska,et al.  Analysis of Recognition of a Musical Instrument in Sound Mixes Using Support Vector Machines , 2011, Fundam. Informaticae.

[13]  Alicja Wieczorkowska,et al.  Music Information Retrieval , 2009, Encyclopedia of Data Warehousing and Mining.

[14]  William P. Birmingham,et al.  MUSART: Music Retrieval Via Aural Queries , 2001, ISMIR.

[15]  Harald Viste,et al.  Separation of harmonic instruments with overlapping partials in multi-channel mixtures , 2003, 2003 IEEE Workshop on Applications of Signal Processing to Audio and Acoustics (IEEE Cat. No.03TH8684).

[16]  Anssi Klapuri,et al.  Signal Processing Methods for the Automatic Transcription of Music , 2004 .

[17]  Zbigniew W. Ras,et al.  Advances in Music Information Retrieval , 2012, Advances in Music Information Retrieval.

[18]  Alicja Wieczorkowska,et al.  Random Musical Bands Playing in Random Forests , 2010, RSCTC.

[19]  Andreas Hotho,et al.  Automatic Multi-label Subject Indexing in a Multilingual Environment , 2003, ECDL.

[20]  D. Niewiadomy,et al.  Implementation of MFCC vector generation in classification context , 2008 .

[21]  David Mason,et al.  Encyclopedia of Data Warehousing and Mining, 2nd ed. , 2009 .

[22]  Masataka Goto,et al.  Instrument Equalizer for Query-by-Example Retrieval: Improving Sound Source Separation Based on Integrated Harmonic and Inharmonic Models , 2008, ISMIR.

[23]  Alicja Wieczorkowska,et al.  Musical Instruments in Random Forest , 2009, ISMIS.

[24]  Anssi Klapuri,et al.  Musical Instrument Recognition in Polyphonic Audio Using Source-Filter Model for Sound Separation , 2009, ISMIR.

[25]  J. Stephen Downie,et al.  Music information retrieval , 2005, Annu. Rev. Inf. Sci. Technol..

[26]  Zbigniew W. Ras,et al.  Maximum Likelihood Study for Sound Pattern Separation and Recognition , 2007, 2007 International Conference on Multimedia and Ubiquitous Engineering (MUE'07).

[27]  Bryan Pardo,et al.  Learning Musical Instruments from Mixtures of Audio with Weak Labels , 2008, ISMIR.

[28]  George Tzanetakis,et al.  MARSYAS: a framework for audio analysis , 1999, Organised Sound.

[29]  Chih-Jen Lin,et al.  A Practical Guide to Support Vector Classication , 2008 .

[30]  Piotr Synak,et al.  Quality Assessment of k-NN Multi-label Classification for Music Data , 2006, ISMIS.

[31]  Piotr Dalka,et al.  Estimation of Musical Sound Separation Algorithm Effectiveness Employing Neural Networks , 2005, Journal of Intelligent Information Systems.

[32]  Shingo Uchihashi,et al.  The beat spectrum: a new approach to rhythm analysis , 2001, IEEE International Conference on Multimedia and Expo, 2001. ICME 2001..

[33]  Zbigniew W. Ras,et al.  Polyphonic Music Information Retrieval Based on Multi-label Cascade Classification System , 2009, Advances in Information and Intelligent Systems.