Optimized neural networks for modeling of loudspeaker directivity diagrams

Publikation: Beiträge in SammelwerkenAufsätze in KonferenzbändenForschung

Standard

Optimized neural networks for modeling of loudspeaker directivity diagrams. / Wilk, Eva; Wilk, Jan.
2001 IEEE International Conference on Acoustics, Speech, and Signal Processing : Proceedings. Band 2 IEEE - Institute of Electrical and Electronics Engineers Inc., 2001. S. 1285-1288 (ICASSP, IEEE International Conference on Acoustics, Speech and Signal Processing - Proceedings).

Publikation: Beiträge in SammelwerkenAufsätze in KonferenzbändenForschung

Harvard

Wilk, E & Wilk, J 2001, Optimized neural networks for modeling of loudspeaker directivity diagrams. in 2001 IEEE International Conference on Acoustics, Speech, and Signal Processing : Proceedings. Bd. 2, ICASSP, IEEE International Conference on Acoustics, Speech and Signal Processing - Proceedings, IEEE - Institute of Electrical and Electronics Engineers Inc., S. 1285-1288, IEEE International Conference on Acoustics, Speech, and Signal Processing 2001, Salt Lake City, USA / Vereinigte Staaten, 07.05.01. https://doi.org/10.1109/icassp.2001.941160

APA

Wilk, E., & Wilk, J. (2001). Optimized neural networks for modeling of loudspeaker directivity diagrams. In 2001 IEEE International Conference on Acoustics, Speech, and Signal Processing : Proceedings (Band 2, S. 1285-1288). (ICASSP, IEEE International Conference on Acoustics, Speech and Signal Processing - Proceedings). IEEE - Institute of Electrical and Electronics Engineers Inc.. https://doi.org/10.1109/icassp.2001.941160

Vancouver

Wilk E, Wilk J. Optimized neural networks for modeling of loudspeaker directivity diagrams. in 2001 IEEE International Conference on Acoustics, Speech, and Signal Processing : Proceedings. Band 2. IEEE - Institute of Electrical and Electronics Engineers Inc. 2001. S. 1285-1288. (ICASSP, IEEE International Conference on Acoustics, Speech and Signal Processing - Proceedings). doi: 10.1109/icassp.2001.941160

Bibtex

@inbook{8c7fa4cd044743f7b332f589971043c6,
title = "Optimized neural networks for modeling of loudspeaker directivity diagrams",
abstract = "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).",
keywords = "Informatics",
author = "Eva Wilk and Jan Wilk",
note = "Titel d. Bandes: Speech processing 2, industry technology track, design & implementation of signal processing systems, neural networks for signal processing. ISSN: 1520-6149 ; IEEE International Conference on Acoustics, Speech, and Signal Processing 2001 ; Conference date: 07-05-2001 Through 11-05-2001",
year = "2001",
month = may,
doi = "10.1109/icassp.2001.941160",
language = "English",
isbn = "0-7803-7041-4 ",
volume = "2",
series = "ICASSP, IEEE International Conference on Acoustics, Speech and Signal Processing - Proceedings",
publisher = "IEEE - Institute of Electrical and Electronics Engineers Inc.",
pages = "1285--1288",
booktitle = "2001 IEEE International Conference on Acoustics, Speech, and Signal Processing",
address = "United States",

}

RIS

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 -

DOI

Zuletzt angesehen

Aktivitäten

  1. Acceleration and Reflection
  2. The global classroom: Introduction, presentation and workshops
  3. Leveraging Error to Improve Audit Quality: Towards a Socio-Cognitive Model
  4. The influence of polycentricity on collaborative environmental management – the case of EU Water Framework Directive implementation in Germany
  5. Artistic Utopian Spaces and the Promise of Urban Development
  6. The Irish English discourse marker sure at the semantics/pragmatics interface
  7. Workshop mit David Bates: "Compossible Worlds"
  8. Using the Method of Limits to Assess Comfortable Time Headways in Adaptive Cruise Control
  9. Time and Organizational Development
  10. PhD Workshop 2022 - Empirical Microeconomics
  11. The Role of Public Participation in Managing Uncertainty in the Implementation of the Water Framework Directive (with C. Pahl-Wostl, and K. Sigel)
  12. Placemaking today: integrating place-oriented thinking into cultural policy frameworks
  13. CTRL + F_eminist futures: Hacking algorithmic architectures of cities to come
  14. Validity of a mathematics test for the selection of university applicants for teacher training
  15. Archive, Non-Archive, Counter-Archive
  16. How teachers use digital data: a systematic review
  17. Improving Human-Machine Interaction – A Multimodal Non-Invasive Approach to Detect Emotions in Car Drivers
  18. 2nd International Conference on Advances in Data-driven Computing and Intelligent Systems (ADCIS 2023)
  19. Using Gamification Elements as a tool for species protection awareness (Single Paper)
  20. Understanding Societal Development and Moral Progress: The Contribution of the World Values Surveys
  21. Development and validation of a video-based instrument for the assessment of feedback competence.

Publikationen

  1. The Open Anchoring Quest Dataset: Anchored Estimates from 96 Studies on Anchoring Effects
  2. BUSINESS MODELS IN BANKING: A CLUSTER ANALYSIS USING ARCHIVAL DATA
  3. Special Issue The Discourse of Redundancy Introduction
  4. Perfectly nested or significantly nested - an important difference for conservation management
  5. Combined MRI-PET dissects dynamic changes in plant structures and functions
  6. Advisory systems in pluralistic knowledge societies:
  7. A Voxel-based technique to estimate the volume of trees from terrestrial laser scanner data
  8. A longitudinal multilevel CFA-MTMM model for interchangeable and structurally different methods
  9. Exploiting ConvNet diversity for flooding identification
  10. How Much Home Office is Ideal? A Multi-Perspective Algorithm
  11. Phosphorus uptake from struvite is modulated by the nitrogen form applied
  12. How can problems be turned into something good? The role of entrepreneurial learning and error mastery orientation
  13. Scaling-based Least Squares Methods with Implemented Kalman filter Approach for Nano-Parameters Identification
  14. Understanding Low-Code Evolution, Adoption and Ecosystem for Software Development
  15. Reducing mean tardiness in a flexible job shop containing AGVs with optimized combinations of sequencing and routing rules
  16. Artificial intelligence in songwriting and composing - perspectives and challenges in creative practices
  17. Errors in Training Computer Skills
  18. Learning and Re-learning from net- based cooperative learning discourses
  19. Combining flatness based feedforward action with a fractional PI regulator to control the intake valve engine
  20. Offline question answering over linked data using limited resources
  21. Learning in the "Third Space"
  22. Schooling, local knowledge and working memory
  23. Unraveling Privacy Concerns in Complex Data Ecosystems with Architectural Thinking
  24. Using Daily Stretching to Counteract Performance Decreases as a Result of Reduced Physical Activity—A Controlled Trial
  25. Fusion of knowledge bases for better navigation of wheeled mobile robotic group with 3D TVS
  26. Reciprocal Relationships Between Dispositional Optimism and Work Experiences