A class of physical modeling recurrent networks for analysis/synthesis of plucked string instruments

IEEE Transactions on Neural Networks - Tập 13 Số 5 - Trang 1137-1148 - 2002
A.W.Y. Su1, Sheng-Fu Liang2
1Department of CSIE, National Cheng Kung University, Tainan, Taiwan
2Department of Electrical and Control Engineering, National Chiao Tung University, Hsinchu, Taiwan

Tóm tắt

A new approach is proposed that closely synthesizes tones of plucked string instruments by using a class of physical modeling recurrent networks. The strategies employed consist of a fast training algorithm and a multistage training procedure that are able to obtain the synthesis parameters for a specific instrument automatically. The training vector can be recorded tones of most target plucked instruments with ordinary microphones. The proposed approach delivers encouraging results when it is applied to different types of plucked string instruments such as steel-string guitar, nylon-string guitar, harp, Chin, Yueh-chin, and Pipa. The synthesized tones sound very close to the originals produced by their acoustic counterparts. In addition, the paper presents an embedded technique that can produce special effects such as vibrato and portamento that are vital to the playing of plucked-string instruments. The computation required in the resynthesis processing is also reasonable.

Từ khóa

#Network synthesis #Instruments #Signal synthesis #Speech synthesis #Digital filters #Lattices #Synthesizers #Position measurement #Time measurement #Microphones

Tài liệu tham khảo

10.1109/78.765137 duyne, 1996, the 3-d tetrahedral digital waveguide with musical applications, Proc 1996 ICMC, 9 välimäki valimaki, 1996, physical modeling of plucked string instruments with application to real-time sound synthesis, J Audio Eng Soc, 44, 331 10.2307/3681155 10.1109/MMSP.1997.602615 10.1109/72.822519 10.1162/neco.1989.1.2.161 kraußkraub, 1995, application of multidimensional wave digital filters to boundary value problems, IEEE Signal Processing Letters, 2, 183 10.1109/72.701179 kinsler, 1982, Fundamentals of Acoustics oppenhim, 1989, Discrete-Time Signal Processing cremer, 1984, The Physics of the Violin 10.2307/3680470 deller, 1993, Discrete-Time Processing of Speech Signals smith, 1993, efficient synthesis of stringed musical instruments, Proc 1993 Int Comput Music Conf, 64 smith, 0, Music application of digital waveguide 10.1007/978-1-4612-2980-3 10.1109/PROC.1986.13458 morse, 1936, Vibration and Sound 10.1162/neco.1990.2.4.490 riedmiller, 1993, a direct adaptive method for faster backpropagation learning: the rprop algorithm, Proc ICNN93, 586 haykin, 1994, Neural Networks bodman, 1987, Chinese Musical Iconography A History of Musical Instrument Depicted in Chinese Art szu, 1987, nonconvex optimization by fast simulated annealing, Proceedings of the IEEE, 75, 1538, 10.1109/PROC.1987.13916 10.1121/1.390533