Musical instrument classification using higher order spectra

Author

Bhalke, D.G. ; Rao, C. B. Rama ; Bormane, Dattatraya S.

Author_Institution

Dept. of ECE, Nat. Inst. of Technol., Warangal, India

fYear

2014

fDate

20-21 Feb. 2014

Firstpage

40

Lastpage

45

Abstract

This paper presents classification and recognition of monophonic isolated musical instrument sounds using higher order spectra such as Bispectrum and Trispectrum. Experimental results on a widely used dataset shows that higher order spectra based features improve the recognition accuracy, when combined with conventional features such as Mel Frequency Cepstral Coefficient (MFCC), Cepstral, Spectral and Temporal features. Nineteen western musical instruments covering four families with full pitch range have been used for experimentation.

Keywords

music; pattern classification; MFCC; Mel frequency cepstral coefficient; bispectrum; cepstral features; full pitch range; higher order spectra; monophonic isolated musical instrument sounds classification; monophonic isolated musical instrument sounds recognition; recognition accuracy; spectral features; temporal features; trispectrum; western musical instruments; Accuracy; Feature extraction; Instruments; Mel frequency cepstral coefficient; Music; Neural networks; Signal processing; Bispectrum; MFCC; Spectral; Temporal; Trispectrum;

fLanguage

English

Publisher

ieee

Conference_Titel

Signal Processing and Integrated Networks (SPIN), 2014 International Conference on

Conference_Location

Noida

Print_ISBN

978-1-4799-2865-1

Type

conf

DOI

10.1109/SPIN.2014.6776918

Filename

6776918