Optimized neural networks for modeling of loudspeaker directivity diagrams

Publikation: Beiträge in SammelwerkenAufsätze in KonferenzbändenForschung

Authors

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).

OriginalspracheEnglisch
Titel2001 IEEE International Conference on Acoustics, Speech, and Signal Processing : Proceedings
Anzahl der Seiten4
Band2
VerlagIEEE - Institute of Electrical and Electronics Engineers Inc.
Erscheinungsdatum05.2001
Seiten1285-1288
ISBN (Print)0-7803-7041-4 , 0-7803-7042-2
DOIs
PublikationsstatusErschienen - 05.2001
VeranstaltungIEEE International Conference on Acoustics, Speech, and Signal Processing 2001 - Salt Lake City, USA / Vereinigte Staaten
Dauer: 07.05.200111.05.2001

Bibliographische Notiz

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

DOI

Zuletzt angesehen

Publikationen

  1. A Voxel-based technique to estimate the volume of trees from terrestrial laser scanner data
  2. Treating dialogue quality evaluation as an anomaly detection problem
  3. Offline question answering over linked data using limited resources
  4. Evaluating structural and compositional canopy characteristics to predict the light-demand signature of the forest understorey in mixed, semi-natural temperate forests
  5. Primary Side Circuit Design of a Multi-coil Inductive System for Powering Wireless Sensors
  6. Support vector machines with example dependent costs
  7. A Playful Approach to Interactive Media in the Foreign Language Classroom
  8. Complex problem solving and intelligence
  9. Metaheuristics approach for solving personalized crew rostering problem in public bus transit
  10. Experiments on the Fehrer-Raab effect and the ‘Weather Station Model’ of visual backward masking
  11. Taking the pulse of Earth's tropical forests using networks of highly distributed plots
  12. Automatic three-dimensional geometry and mesh generation of periodic representative volume elements for matrix-inclusion composites
  13. Introduction: The representative turn in EU studies
  14. GERBIL - General entity annotator benchmarking framework
  15. Rapid grain refinement and compositional homogenization in a cast binary Cu50Ni alloy achieved by friction stir processing
  16. Mathematical relation between extended connectivity and eigenvector coefficients.
  17. Integrating the underlying structure of stochasticity into community ecology
  18. Towards productive functions?
  19. Inside-sediment partitioning of PAH, PCB and organochlorine compounds and inferences on sampling and normalization methods
  20. The Structure of Student Interest in Computers and Information Technology
  21. Monitoring of microbially mediated corrosion and scaling processes using redox potential measurements
  22. Managing complexity in automative production
  23. Scholarly Question Answering Using Large Language Models in the NFDI4DataScience Gateway
  24. A Computational Research System for the History of Science
  25. What Makes for a Good Theory? How to Evaluate a Theory Using the Strength Model of Self-Control as an Example