Musical instrument classification using higher order spectra

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

doi:10.1109/spin.2014.6776918

Cited by 10 publications

(9 citation statements)

References 7 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…where, 3 = − 1 − 2 Similarly, it can be shown in the trispectrum using four frequency notations (Eq. (15)) [31,32]. 2 3 4 1 2 3 4 , , ,…”

Section: Trispectrummentioning

confidence: 99%

Spectral and Statistical Analysis for Damage Detection in Ceramic Materials

Akgun¹

2020

View full text Add to dashboard Cite

In this study, the internal or superficial cracks that may occur during the production of ceramic plates were determined using the impact noise method. In the industry, ceramic materials are frequently used in areas such as kitchenware and construction. Many different methods are used in the quality control processes of ceramic materials. In this study, the sound produced by the impact applied to the ceramic material was analyzed. As a result of the analysis, the material was found to be undamaged or damaged. This method is called the Impulse Noise method. In this study, damaged and undamaged ceramic plates with different cracks were selected and impact plates were applied to the plates by impact pendulum. The ceramic plates used in the application have the same characteristics and dimensions produced by the same company of the same type. The noise generated as a result of the impact applied to a determined point on the tested materials was examined by Wigner-Ville method which is one of the time-frequency analysis methods. In addition, bispectrum and trispectrum analyzes, which are high-order spectral analysis (HOSA) methods, were used. Statistically, signal analysis with running minimum and maximum, mean value and peak to RMS examinations were also added. The applied methods give good results in differentiating between undamaged and damaged ceramic plates.

show abstract

“…where, 3 = − 1 − 2 Similarly, it can be shown in the trispectrum using four frequency notations (Eq. (15)) [31,32]. 2 3 4 1 2 3 4 , , ,…”

Section: Trispectrummentioning

confidence: 99%

Spectral and Statistical Analysis for Damage Detection in Ceramic Materials

Akgun¹

2020

View full text Add to dashboard Cite

show abstract

“…Various features such as Timbral, Temporal, Spectral, Wavelet and MFCC have been proposed in the past years for music genre classification. Also, it has been observed that Timbral and MFCC features have made a significant contribution to genre classification (Bhalke et al, 2014;Fu et al, 2011;Ghosal et al, 2012). In addition, Fractional Fourier Transform makes use of chirp decomposition which is especially suitable for music signals in which time, frequency and phase information play a vital role (Ashok Narayanan, Prabhu, 2003; Bhalke et al, 2016).…”

Section: Literature Surveymentioning

confidence: 99%

Automatic Genre Classification Using Fractional Fourier Transform Based Mel Frequency Cepstral Coefficient and Timbral Features

Bhalke¹,

Rajesh²,

Bormane³

2017

Archives of Acoustics

View full text Add to dashboard Cite

This paper presents the Automatic Genre Classification of Indian Tamil Music and Western Music using Timbral and Fractional Fourier Transform (FrFT) based Mel Frequency Cepstral Coefficient (MFCC) features. The classifier model for the proposed system has been built using K-NN (K-Nearest Neighbours) and Support Vector Machine (SVM). In this work, the performance of various features extracted from music excerpts has been analysed, to identify the appropriate feature descriptors for the two major genres of Indian Tamil music, namely Classical music (Carnatic based devotional hymn compositions) & Folk music and for western genres of Rock and Classical music from the GTZAN dataset. The results for Tamil music have shown that the feature combination of Spectral Roll off, Spectral Flux, Spectral Skewness and Spectral Kurtosis, combined with Fractional MFCC features, outperforms all other feature combinations, to yield a higher classification accuracy of 96.05%, as compared to the accuracy of 84.21% with conventional MFCC. It has also been observed that the FrFT based MFCC effieciently classifies the two western genres of Rock and Classical music from the GTZAN dataset with a higher classification accuracy of 96.25% as compared to the classification accuracy of 80% with MFCC.

show abstract

“…Music pieces are mapped on the plane and classified. Bhalke et al (2014), had proposed fractional Fourier transform (FrFT) based MFCC features for discriminating musical instruments and have found that the interclass variation was greatly maximised and intra-class variation was minimised by the use of the chirp like kernel basis function of the FrFT.…”

Section: Literature Surveymentioning

confidence: 99%

“…FrFt uses linear chirps as a basis function, and thus, it offers a great deal of flexibility in the processing of audio signals (Bhalke et al 2014). The time-frequency representation of a signal is on a plane with two orthogonal axes, where the time axis is represented horizontally as x(t) and the frequency axis is represented vertically.…”

Section: Frft Based Mfcc Features (Frmfcc)mentioning

confidence: 99%

Automatic genre classification of Indian Tamil and western music using fractional MFCC

Rajesh

Bhalke

2016

Int J Speech Technol

Self Cite

View full text Add to dashboard Cite

This paper presents the automatic genre classification of Indian Tamil music and western music using timbral features and fractional Fourier transform (FrFT) based Mel frequency cepstral coefficient (MFCC) features. The classifier model for the proposed system has been built using K-nearest neighbours and support vector machine (SVM) classifiers. In this work, the performance of various features extracted from music excerpts have been analyzed, to identify the appropriate feature descriptors for the two major genres of Indian Tamil music, namely classical music (Carnatic based devotional hymn compositions) and folk music. The results have shown that the feature combination of spectral roll off, spectral flux, spectral skewness and spectral kurtosis, combined with fractional MFCC features, outperforms all other feature combinations, to yield a higher classification accuracy of 96.05 %, as compared to the accuracy of 84.21 % with conventional MFCC. It has also been observed, that the FrFT based MFCC, with timbral features and SVM, efficiently classifies the two western genres of rock and classical music, from the GTZAN dataset, with fewer features and a higher classification accuracy of 96.25 %, as compared to the classification accuracy of 80 % with conventional MFCC.

show abstract

Musical instrument classification using higher order spectra

Cited by 10 publications

References 7 publications

Spectral and Statistical Analysis for Damage Detection in Ceramic Materials

Spectral and Statistical Analysis for Damage Detection in Ceramic Materials

Automatic Genre Classification Using Fractional Fourier Transform Based Mel Frequency Cepstral Coefficient and Timbral Features

Automatic genre classification of Indian Tamil and western music using fractional MFCC

Contact Info

Product

Resources

About