TY - CHAP

T1 - Optimized neural networks for modeling of loudspeaker directivity diagrams

AU - Wilk, Eva

AU - Wilk, Jan

N1 - Titel d. Bandes: Speech processing 2, industry technology track, design & implementation of signal processing systems, neural networks for signal processing. ISSN: 1520-6149

PY - 2001/5

Y1 - 2001/5

N2 - For the electro-acoustical simulation of sound reinforcement systems, calculation and simulation of the sound field distribution requires measurement and storage of the frequency dependent directivity characteristics (level and phase) of the used loudspeaker models. In modern simulation programs, the spatial resolution can be less than five degrees in third - or even twelfth - octave frequency bands. Therefore, modeling of the directivity diagram of loudspeakers can reduce storage place and simulation time and may even increase the accuracy of the simulation. Modeling - in the sense of mapping the resulting enormous amount of measured data - can be realized very efficiently and with small approximation error using second order neural networks. To reduce the model development time, we in addition created a new adaptation rule for feedforward neural networks with improved convergence behavior. This is achieved only by using the training data and the output error to analytically determine values for the learning parameters momentum and learning rate in each learning step. We will show the advantages of using neural networks with optimized learning parameters by the example of modeling measured directional response patterns of two real loudspeakers. For measurement we used maximum length sequences (MLSSA).

AB - For the electro-acoustical simulation of sound reinforcement systems, calculation and simulation of the sound field distribution requires measurement and storage of the frequency dependent directivity characteristics (level and phase) of the used loudspeaker models. In modern simulation programs, the spatial resolution can be less than five degrees in third - or even twelfth - octave frequency bands. Therefore, modeling of the directivity diagram of loudspeakers can reduce storage place and simulation time and may even increase the accuracy of the simulation. Modeling - in the sense of mapping the resulting enormous amount of measured data - can be realized very efficiently and with small approximation error using second order neural networks. To reduce the model development time, we in addition created a new adaptation rule for feedforward neural networks with improved convergence behavior. This is achieved only by using the training data and the output error to analytically determine values for the learning parameters momentum and learning rate in each learning step. We will show the advantages of using neural networks with optimized learning parameters by the example of modeling measured directional response patterns of two real loudspeakers. For measurement we used maximum length sequences (MLSSA).

KW - Informatics

UR - http://www.scopus.com/inward/record.url?scp=0034855182&partnerID=8YFLogxK

U2 - 10.1109/icassp.2001.941160

DO - 10.1109/icassp.2001.941160

M3 - Article in conference proceedings

SN - 0-7803-7041-4

SN - 0-7803-7042-2

VL - 2

T3 - ICASSP, IEEE International Conference on Acoustics, Speech and Signal Processing - Proceedings

SP - 1285

EP - 1288

BT - 2001 IEEE International Conference on Acoustics, Speech, and Signal Processing

PB - IEEE - Institute of Electrical and Electronics Engineers Inc.

T2 - IEEE International Conference on Acoustics, Speech, and Signal Processing 2001

Y2 - 7 May 2001 through 11 May 2001

ER -