A neural network approach to predicting the reverberation time, RT60, at the conceptual design stage of auditoria, and churches is presented. The results of investigations previously carried out indicated that there was a good basis for using trained neural networks to predict the reverberation time for unoccupied enclosures but that 15 input variables were required to achieve the desired accuracy. As the number of input variables that can be readily identified and quantified at the early design stage is small, the objective of this work is to reduce network size and to obtain optimal neural networks. The results showed that the generalization performance of neural networks with simplified internal representation is efficient. Generally, the reverberation time prediction accuracy of the network models, for the six enclosures ‘tested’, is within the range of the subjective difference limen (ΔT/T ≈ 5%).
Get full access to this article
View all access options for this article.
References
1.
SabineW.C., (1992) Collected Papers on Acoustics, Reprinted by Dover Publication, Inc.1964, New York.
2.
BeranekL.L., (1996) Concert and Opera Halls: How They Sound, Acoustical Society of America, Woodbury, New York.
3.
GompertsM.C., (1965/66) “Do the Classical Reverberation Formulae Still Have a Right for Existence?, Acustica, 16 (5), 256–268.
4.
KostenC.W., (1965/66) “New Method for the Calculation of the Reverberation time of halls for public assembly,”Acustica, 16 (6), 325–330.
5.
SchroederM.R., (1973) “Computer Models for Concert Hall Acoustics,”AJP, 41, 461–471.
6.
CoxT.J.DaviesW.J., and LamY.W., (1993) “The Sensitivity of Listeners to Early Sound Field Changes in Auditoria,”Acustica, 79, 27–41.
7.
VorlanderMichael, (1995) “International Round Robin on Room Acoustical Computer Simulation,” 15th International Congress on Acoustics Trondheim, Norway 26–30 June, 689–692.
NannarielloJ., and FrickeF.R., (1999) “The prediction of reverberation time using neural network analysis,”Applied Acoustics, 58, 305–325.
10.
SteinR., (1993) “Selecting Data for Neural Networks,”AI Expert, 8(2), 42–47.
11.
MozerM.C., and SmolenskyP., (1989) “Using relevance to reduce network size automatically,”Connection Science, 1(1), 3–16.
12.
BradelyJ.S., and SoulodreG.A., (1995) “Objective measures of listener envelopment,”J. Acoust. Soc. Amer., 98(5), 2590–2597.
13.
GadeA.C., (1991) “Prediction of Room Acoustical Parameters,”A paper presented on the 121st Meeting of the Acoust. Soc. Amer., Baltimore, May 1991.
14.
GadeA.C., (1996) “Room acoustic properties of concert halls: Quantifying the influence of size, shape, and absorption area,” 3rd ASA/ASJ meeting, Honolulu, paper 5aAA1, 1–6.
15.
NannarielloJ., and FrickeF.R., “The use of neural network analysis to predict the acoustic performance of large rooms: Part I Predictions of the parameter G utilizing numerical simulations,”Applied Acoustics, 62(8), 917–950.
16.
NannarielloJ., and FrickeF.R., “The use of neural network analysis to predict the acoustic performance of large rooms: Part II Predictions of the of the acoustical attributes of concert halls utilizing measured data,”Applied Acoustics, 62(8), 951–977.
17.
FloodI., and KartamN., (1994) “Neural Networks in Civil Engineering I: Principles and Understanding,”Journal of Computing in Civil Engineering, 8(2), ASCE, 131–148.
18.
LippmannR.P., (1987) “An introduction to computing with neural nets,”IEEE ASSP Magazine, April, 4–22.
19.
HertzJ.KroghA., and PalmerR.G., (1991) Introduction to the theory of neural computation. Addison-WesleyNew York.
20.
FausettL., (1994) Fundamental of Neural Networks. Prentice Hall, New York.
21.
NelsonM.M., and IllingworthW.T., (1991) A Practical Guide to Neural Nets, Addison-Wesley, New York.
22.
BaillieD., and MathewJ., (1994) “Diagnosis rolling element bearing faults with artificial neural network”Acoustics Australia, 22(3), 79–84.
23.
SimpsonP.K., (1990) Artificial Neural Systems: Foundations, Paradigms, Applications, and Implementations, Pergamon Press, New York.
24.
SteinR., “Preprocessing Data for Neural Networks” (1993) AI Expert, March 1993, 32–37.
25.
TickleA.B.AndrewsR.GoleaM., and JoachimD., (1997) Rule extraction from trained artificial neural networks, In: Neural Network Analysis, Architecture and Applications, Edit, BrowneA., Institute of Physics Publishing, Bristol and Philadelphia.
26.
STATISTICA Neural Networks, (1999) StatSoft Inc, Tulsa, OK.
27.
GadeA.C., (1991) “Prediction of Room Acoustical Parameters,” A paper presented on the 121st Meeting of the Acoust. Soc. Amer., Baltimore, May 1991.
28.
NannarielloJ., and FrickeF.R., (2001) “A neural network analysis of the effect of geometric variables on concert hall G values”Applied acoustics, 62(12), 1397–1410.
29.
FrickeF.R., (2000) “Concert Hall Acoustics: An Alternative Approach”Building Acoustics, 7(4), 233–246.
30.
BarronM., (1993) Auditorium acoustics and architectural design, E & FN Spon, London.
31.
BrookR., (1991) Rooms for Speech and Music, IN: Handbook for sound Engineers, the New Audio Cyclopedia, Second Edition, BallouG. (edit), Chapter 7, Howard W. Sams & Company, New Jersey.
32.
MartinA.J., and MorrisE.B., (1999) Artificial Neural Networks and Multivariate Statistics, In: Statistics and Neural Networks: Advances at the Interface, Edit, KayJ.W., and TitteringtonD.M., Oxford University Press, Inc., New York.
33.
NannarielloJ., and FrickeF.R., (2001) “A neural-computation method of predicting the early interaural cross-correlation coefficient, IACCE3, for auditoria,”Applied Acoustics, (in press).
