论文信息 - The Use of Mel-frequency Cepstral Coefficients in Musical Instrument Identification

The Use of Mel-frequency Cepstral Coefficients in Musical Instrument Identification

This paper examines the use of Mel-frequency Cepstral Coefficients in the classification of musical instruments. 2004 piano, violin and flute samples are analysed to get their coefficients. These coefficients are reduced using principal component analysis and used to train a multi-layered perceptron. The network is trained on the first 3, 4 and 5 principal components calculated from the envelope of the changes in the coefficients. This trained network is then used to classify novel input samples. By training and testing the network on a different number of coefficients, the optimum number of coefficients to include for identifying a musical instrument is determined. We conclude that using 4 principal components from the first 15 coefficients gives the most accurate classification results.

[1] Antti J. Eronen,et al. Musical instrument recognition using ICA-based transform of features and discriminatively trained HMMs , 2003, Seventh International Symposium on Signal Processing and Its Applications, 2003. Proceedings..

[2] Anssi Klapuri,et al. Musical instrument recognition using cepstral coefficients and temporal features , 2000, 2000 IEEE International Conference on Acoustics, Speech, and Signal Processing. Proceedings (Cat. No.00CH37100).

[3] S. Hyakin,et al. Neural Networks: A Comprehensive Foundation , 1994 .

[4] Douglas D. O'Shaughnessy,et al. Speech communication : human and machine , 1987 .

[5] Beth Logan,et al. Mel Frequency Cepstral Coefficients for Music Modeling , 2000, ISMIR.

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

[7] Paolo Prandoni,et al. Sonological models for timbre characterization , 1997 .

[8] J C Brown. Computer identification of musical instruments using pattern recognition with cepstral coefficients as features. , 1999, The Journal of the Acoustical Society of America.

[9] Stephen Grossberg,et al. ARTMAP: supervised real-time learning and classification of nonstationary data by a self-organizing neural network , 1991, [1991 Proceedings] IEEE Conference on Neural Networks for Ocean Engineering.