A generalized musical-tone generator with application to sound compression and synthesis

Author

Drioli, Carlo ; Rocchesso, Davide

Author_Institution

Centro di Sonologia Computazionale, Padova Univ., Italy

Volume

1

fYear

1997

fDate

21-24 Apr 1997

Firstpage

431

Abstract

A musical-tone generator based on physical modeling of sound production mechanisms is presented. For the purpose of making this scheme general for a wide class of musical instruments, the nonlinear part of the tone-generator is modeled by a neural network. The system learns its parameters and the nonlinearity shape by means of nonlinear identification procedures based on waveform or spectral matching. Two possible applications of this model are discussed: sound compression can be obtained when considering the system as a nonlinear predictor, while sound synthesis can be obtained by adding control inputs to the network and by training the system to respond as desired

Keywords

acoustic signal processing; data compression; electronic music; frequency synthesizers; identification; learning (artificial intelligence); music; neural nets; signal synthesis; spectral analysis; control inputs; generalized musical-tone generator; musical instruments; neural network; nonlinear identification procedures; nonlinear part; nonlinear predictor; nonlinearity shape; sound compression; sound production mechanisms; sound synthesis; spectral matching; training; waveform matching; Control system synthesis; Delay lines; Filtering; Instruments; Low pass filters; Network synthesis; Physics computing; Production; Resonator filters; Shape;

fLanguage

English

Publisher

ieee

Conference_Titel

Acoustics, Speech, and Signal Processing, 1997. ICASSP-97., 1997 IEEE International Conference on

Conference_Location

Munich

ISSN

1520-6149

Print_ISBN

0-8186-7919-0

Type

conf

DOI

10.1109/ICASSP.1997.599667

Filename

599667