Optimized phase-space reconstruction for accurate musical-instrument signal classification
- 280 Downloads
Traditional musical-instrument classification methods mainly use regions in the time or/and frequency characteristics, cepstrum characteristics, and MPEG-7 characteristics, and they often lead to erroneous classification. Therefore, there is need to develop a more suitable method that is more applicable to the nonlinear characteristics of musical-instrument signals and can avoid the abovementioned problems. In this paper, a musical-instrument classification method that couples the optimized phase-space reconstruction (OPSR) with a flexible neural tree (FNT) is proposed. As per nonlinear dynamic theory, a principal component analysis and correlation coefficient are used to optimize the phase-space reconstruction (PSR) method. Multidimensional PSR results for different musical-instrument signals are extracted as the main components, and the dimensionality is reduced by the OPSR method. A probability density function (PDF) is introduced in the feature extraction step to differentiate musical instruments according to the phase-space-reconstructible characteristics. A FNT is adopted as a classifier to tackle the variability in musical-instrument signals and to improve the adaptive ability of various target classification problems. Experimental testing has been conducted to show that the proposed OPSR–PDF–FNT algorithm gives superior performance over other comparable algorithms and can classify 12 musical instruments with an accuracy of 98.2 %.
KeywordsMusical-instrument classification Phase-space reconstruction Principal component analysis Flexible neural tree
Funding for this work was supported by the National Natural Science Foundation of China (NO. 61301250, NO. 61401298), Program for the Outstanding Innovative Teams of Higher Learning Institutions of Shanxi (NO. 3), Project of Shanxi Scholarship Council of China (NO. 2014-060), Doctoral Program of Taiyuan University of Science and Technology (NO. 20152003), and Project for “131” Talented Person Project of Higher Learning Institutions of Shanxi (NO. ).
- 2.Bao W, Chen Y, Wang D (2014) Prediction of protein structure classes with flexible neural tree. Bio-Med Mater Eng 24(6):3797–3806Google Scholar
- 4.Benetos E, Kotti M, Kotropoulos C (2007) Large scale musical instrument identification. Paper presented at the 4th Sound and Music Computing Conference 11: 13Google Scholar
- 5.Bhalke DG, Rao CBR, Bormane DS (2014) Musical instrument classification using higher order spectra. Signal Processing and Integrated Networks (SPIN), 2014 International Conference on. IEEE 40–45Google Scholar
- 7.Chen Y, Abraham A (2009) Tree-structure based hybrid computational intelligence: Theoretical foundations and applications. Springer Science & Business Media 2:39–96Google Scholar
- 10.Eronen A (2001) Comparison of features for musical instrument recognition. Applications of Signal Processing to Audio and Acoustics, 2001 I.E. Workshop on the. IEEE 19–22Google Scholar
- 18.Jolliffe I (2002) Principal component analysis. John Wiley & Sons, LtdGoogle Scholar
- 19.Kazi FI, Bhalke DG (2014) Musical instrument classification using higher order spectra and hierarchical taxonomies. Int J Comput Appl 107(17):17–22Google Scholar
- 21.McKay C (2010) Automatic music classification with jMIR. Doctoral dissertation, McGill UniversityGoogle Scholar
- 22.Misron MM, Rosli N, Manaf NA, Halim HA (2014) Music emotion classification (mec): Exploiting vocal and instrumental sound features. Recent Advances on Soft Computing and Data Mining. Springer International Publishing, pp 539–549Google Scholar
- 23.Patil K, Elhilali M (2015) Biomimetic spectro-temporal features for music instrument recognition in isolated notes and solo phrases. EURASIP JASMP 1:1–13Google Scholar
- 24.Rui R, Bao C (2012) The musical instrument classification algorithm based on nonlinear dynamics. Acta Electron Sin 7:032Google Scholar