RADIAL / ELLIPTICAL BASIS FUNCTION NEURAL NETWORKS FOR TIMBRE CLASSIFICATION

This paper outlines a RBF/EBF neural network approach for automatic musical instrument classification using salient feature extraction techniques with a combination of supervised and unsupervised learning schemes. 829 monophonic sound examples (86% Siedlaczek Library [2], 14% other sources) from the string, brass, and woodwind families with a variety of performance techniques, dynamics, and pitches were used for the development of feature extraction, network initialization algorithms, and training of the neural networks resulting in approximately 71% individual instrument and 88% instrument family classification. A novel approach for automatically fine-tuning the system using the Nearest Centroid Error Clustering (NCC) method which determines a robust number of centroids is also discussed.

[1]  Ichiro Fujinaga,et al.  Realtime Recognition of Orchestral Instruments , 2000, International Conference on Mathematics and Computing.

[2]  Akinobu Shimizu,et al.  Face detection using a modified radial basis function neural network , 2002, Object recognition supported by user interaction for service robots.

[3]  Michael R. Berthold,et al.  A time delay radial basis function network for phoneme recognition , 1994, Proceedings of 1994 IEEE International Conference on Neural Networks (ICNN'94).

[4]  Bozena Kostek.  Soft Computing in Acoustics: Applications of Neural Networks, Fuzzy Logic and Rough Sets to Musical Acoustics , 1999 .

[5]  Carlos E. Thomaz,et al.  Design of radial basis function network as classifier in face recognition using eigenfaces , 1998, Proceedings 5th Brazilian Symposium on Neural Networks (Cat. No.98EX209).

[6]  Jake K. Aggarwal,et al.  Partial face recognition using radial basis function networks , 1998, Proceedings Third IEEE International Conference on Automatic Face and Gesture Recognition.

[7]  Man-Wai Mak,et al.  Speaker identification using radial basis functions , 1993 .

[8]  Ichiro Fujinaga,et al.  Machine recognition of timbre using steady-state tone of acoustic musical instruments , 1998, ICMC.

[9]  J C Brown,et al.  Feature dependence in the automatic identification of musical woodwind instruments. , 2001, The Journal of the Acoustical Society of America.

[10]  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).

[11]  Youngmoo E. Kim,et al.  Musical instrument identification: A pattern‐recognition approach , 1998 .

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

[13]  Keith Dana Martin,et al.  Sound-source recognition: a theory and computational model , 1999 .

[14]  Mahesan Niranjan,et al.  Neural networks and radial basis functions in classifying static speech patterns , 1990 .

[15]  Martin Birgmeier,et al.  Nonlinear prediction of speech signals using radial basis function networks , 1996, 1996 8th European Signal Processing Conference (EUSIPCO 1996).

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