Acoustic Virtual Reality: The Artificial Neural Networks Approach

  • Jose Francisco Lucio
  • Roberto Tenenbaum
  • Julio Torres
Keywords: Acoustic Virtual Reality, Auralization, Artificial Neural Networks, Binaural Impulse Responses, Room Acoustics Numeric Simulation

Abstract

This work presents a new approach to obtain the Binaural Impulse Responses (BIRs) for an auralization system by using a committee of artificial neuronal networks (ANNs). The proposed method is capable to reconstruct the desired modified Head Related Impulse Responses (HRIRs) by means of spectral modification and spatial interpolation. In order to cover the entire auditory reception space, without increasing the network’s architecture complexity, a structure with multiple RNAs (committee) was adopted, where each network operates in la specific reception region (bud). The modeling error, in the frequency domain, is investigated considering the logarithmic nature of the human hearing. It was observed that the proposed methodology obtained a computational gain of approximately 62%, in terms of processing time reduction, compared to the classical signal processing method used to obtain auralizations.
The applicability of the new method in auralization systems is validated by comparative analysis of the results, which includes the BIR’s generation and calculation of one binaural acoustic parameter (IACF), showing very low magnitude errors. 

DOI

Downloads

Download data is not yet available.

References

BLAUERT, J., 1997. Spatial Hearing. The MIT Press, Cambridge.

WERSNYI, G., 2009. Effect of emulated head-tracking for reducing localization errors in virtual audio simulation IEEE Transactions On Audio, Speech, And Language Processing, Vol. 17, n. 2, pp. 247–252.

TEBELSKIS, J., 1995. Speech Recognition using Neuronal Networks. Ph.D. Thesis - Carnegie Mellon University, Pittsburgh.

MINGO, L. F.; GIMÉNEZ, V.; CASTELLANOS, J., 1999 Interpolation of boolean functions with enhanced neuronal networks. In: Second Conference on Computer Science and Information Technologies.

CSIT’99. Yerevan, Armenia. p. 17–22.

BISHOP, C., 2005. Neuronal Networks for Pattern Recognition. Oxford: Oxford University Press.

ALMEIDA, F., PASSARI, A., 2006. Aplicação de redes neurais na previsão de vendas no varejo. Revista de Administração - RAUSP, v. 41, n. 3, p. 257–272.

HOLMES, J., HOLMES, W., 2001. Speech Synthesis and Recognition. 11 New Fetter Lane, London: Taylor & Francis. 213–218 p.

HARASZY, Z., IANCHIS, D., TIPONUT, V., 2009. Generation of the head related transfer functions using artificial neuronal networks. 13th WSEAS International Conference on CIRCUITS, p. 114–118.

HU, H.; ZHOU, L.; MA H. & WU, Z., 2008. HRTF personalization based on artificial neuronal network in individual virtual auditory space. Applied Acoustics, v. 69, n. 2, p. 163–172.

RUMELHART, D., MCCLELLAND, J., the PDP Research Group, 1986. Parallel Distributed Processing: Explorations in the Microstructure of Cognition. MIT Press, 328–330 p.

LUCIO NARANJO, J.F.L., 2014. Inteligência Computacional Aplicada na Geração de Respostas Impulsivas Biauriculares e em Aurilização de Salas. Ph.D. Thesis, Universidade do Estado do Rio de Janeiro, Nova Friburgo.

TORRES, J.C.B., PETRAGLIA, M.R., AND TENENBAUM, R.A., 2004. An Efficient wavelet-based HRTF for auralization Acta Acustica united with Acustica, Vol. 90(1), 108–120.

TENENBAUM, R.A., CAMILO, T.S., TORRES J.C.B. AND GERGES, S.N.Y., 2007a. Hybrid method for numerical simulation of room acoustics with auralization: Part 1 - Theoretical and numerical aspects. J. Brazilian Soc. Mech. Sci. Engin., Vol. 29(2), 211–221.

TENENBAUM, R.A., CAMILO, T.S., TORRES J.C.B. AND STUTZ, L.T., 2007b Hybrid method for numerical simulation of room acoustics: Part 2 - Validation of the computational code RAIOS 3. J. Brazilian Soc. Mech. Sci. Engin., Vol. 29(2), 222–231.

VORLÄNDER, M., 2008. Auralization: Fundamentals of Acoustics, Modeling, Simulation, Algorithms and Acoustic Virtual Reality Springer, Berlin

Published
2015-05-29
How to Cite
[1]
J. Lucio, R. Tenenbaum, and J. Torres, “Acoustic Virtual Reality: The Artificial Neural Networks Approach”, LAJC, vol. 2, no. 1, May 2015.
Section
Research Articles for the Regular Issue