Learning pseudo-physical models for sound synthesis and transformation

Synthesis by physical models is a sound synthesis technique which has recently become popular due to sound duality and expressiveness of control. We propose a rather general structure based on an interaction scheme where the nonlinear component is modeled by radial basis function (RBF) networks. This leads to a system which has the ability to learn the shape of the nonlinearity in order to reproduce a target sound. From the waveform data it is possible to deduce a training set for off-line learning techniques, and the parameters of the RBF network are computed by iterated selection of the radial units. In this work we first consider memoryless nonlinear exciters. After then, dynamic exciters are simulated by adopting a nonlinear ARMA model. Once the system has converged to a well behaved instrument model, it is possible to control sound features, such as pitch, by modifying the physically-informed parameters in an intuitive way.

[1]  Axel Röbel.  Neural Networks for Modeling Time Series of Musical Instruments , 1995, ICMC.

[2]  Xavier Rodet,et al.  Models of musical instruments from Chua's circuit with time delay , 1993 .

[3]  K. S. Narendra,et al.  Neural networks for control theory and practice , 1996, Proc. IEEE.

[4]  Shang-Liang Chen,et al.  Orthogonal least squares learning algorithm for radial basis function networks , 1991, IEEE Trans. Neural Networks.

[5]  F. Girosi,et al.  Networks for approximation and learning , 1990, Proc. IEEE.

[6]  Julius O. Smith,et al.  Physical Modeling Using Digital Waveguides , 1992 .

[7]  Carlo Drioli,et al.  A generalized musical-tone generator with application to sound compression and synthesis , 1997, 1997 IEEE International Conference on Acoustics, Speech, and Signal Processing.

[8]  Andreas Spanias,et al.  Speech coding: a tutorial review , 1994, Proc. IEEE.

[9]  G. P. King,et al.  Extracting qualitative dynamics from experimental data , 1986 .

[10]  Kevin Karplus,et al.  Digital Synthesis of Plucked-String and Drum Timbers , 1983 .

[11]  Allen Gersho,et al.  Vector quantization and signal compression , 1991, The Kluwer international series in engineering and computer science.

[12]  Perry R. Cook,et al.  Non Linear Periodic Prediction for On-Line Identification of Oscillator Characteristics in Woodwind Instruments , 1991, International Conference on Mathematics and Computing.

[13]  Jean Laroche,et al.  ANALYSIS/SYNTHESIS OF QUASI-HARMONIC SOUNDS BY USE OF THE KARPLUS-STRONG ALGORITHM , 1992 .

[14]  Vesa Välimäki,et al.  Parameter Estimation of Non-Linear Physical Models by Simulated Evolution - Application to the Flute Model , 1993, ICMC.