Acoustic Characterization of Rooms Using Reverberation Time Estimation Based on Supervised Learning Algorithm

The measurement of reverberation time is an essential procedure for the characterization of the acoustic performance of rooms. The values returned by these measurements allow us to predict how the sound will be transformed by the walls and furnishings of the rooms. The measurement of the reverberation time is not an easy procedure to carry out and requires the use of a space in an exclusive way. In fact, it is necessary to use instruments that reproduce a sound source and instruments for recording the response of the space. In this work, an automatic procedure for estimating the reverberation time based on the use of artificial neural networks was developed. Previously selected sounds were played, and joint sound recordings were made. The recorded sounds were processed with the extraction of characteristics, then they were labeled by associating to each sound the value of the reverberation time in octave bands of that specific room. The obtained dataset was used as input for the training of an algorithm based on artificial neural networks. The results returned by the predictive model suggest using this methodology to estimate the reverberation time of any closed space, using simple audio recordings without having to perform standard measurements or calculate the integration explicitly.

[1]  M. Vorländer.  Computer simulations in room acoustics: concepts and uncertainties. , 2013, The Journal of the Acoustical Society of America.

[2]  F. Jacobsen,et al.  The coherence of reverberant sound fields. , 2000, The Journal of the Acoustical Society of America.

[3]  Jorge J. Moré,et al.  The Levenberg-Marquardt algo-rithm: Implementation and theory , 1977 .

[4]  D. Marquardt.  An Algorithm for Least-Squares Estimation of Nonlinear Parameters , 1963 .

[5]  R. H. Molina,et al.  Reverberation time measurements of a neonatal incubator , 2020 .

[6]  Mario Pacas,et al.  Application of the Welch-Method for the Identification of Two- and Three-Mass-Systems , 2008, IEEE Transactions on Industrial Electronics.

[7]  Ernesto Redondo Domínguez,et al.  Learning Room Acoustics by Design : A Project-Based Experience , 2019 .

[8]  Mohammad Bagher Menhaj,et al.  Training feedforward networks with the Marquardt algorithm , 1994, IEEE Trans. Neural Networks.

[9]  Robert Höldrich,et al.  Modeling a Spherical Loudspeaker System as Multipole Source , 2007 .

[10]  Xinghuo Yu,et al.  A general backpropagation algorithm for feedforward neural networks learning , 2002, IEEE Trans. Neural Networks.

[11]  Leo L. Beranek.  Audience and Seat Absorption in Large Halls , 1960 .

[12]  M. Bartlett.  Periodogram analysis and continuous spectra. , 1950, Biometrika.

[13]  Gino Iannace,et al.  Acoustic enhancement of a modern church , 2019 .

[14]  L. Tronchin,et al.  Evaluation of Acoustic Similarities in Two Italian Churches Honored to S. Dominic , 2020 .

[15]  M. Ali,et al.  An artificial neural network approach to modelling absorbent asphalts acoustic properties , 2020 .

[16]  F. Marulo,et al.  Artificial neural network-based models for predicting the sound absorption coefficient of electrospun poly(vinyl pyrrolidone)/silica composite , 2020 .

[17]  Adam Glowacz,et al.  Acoustic fault analysis of three commutator motors , 2019, Mechanical Systems and Signal Processing.

[18]  Hideki Tachibana,et al.  Visualization of sound propagation and scattering in rooms , 2002 .

[19]  Anthony M. Zador,et al.  A critique of pure learning and what artificial neural networks can learn from animal brains , 2019, Nature Communications.

[20]  Michael Vorländer,et al.  Uncertainties of Measurements in Room Acoustics , 1995 .

[21]  Spatial cross-correlation of acoustic pressures in steady and decaying reverberant sound fields , 1976 .

[22]  J. Rao,et al.  The estimation of the mean squared error of small-area estimators , 1990 .

[23]  P. Welch.  The use of fast Fourier transform for the estimation of power spectra: A method based on time averaging over short, modified periodograms , 1967 .

[24]  A. Khintchine.  Korrelationstheorie der stationären stochastischen Prozesse , 1934 .

[25]  Leo L. Beranek,et al.  Concert halls and opera houses : music, acoustics, and architecture , 2005 .

[26]  J. S. Bradley,et al.  Review of objective room acoustics measures and future needs , 2011 .

[27]  Gerhard Nahler,et al.  Pearson Correlation Coefficient , 2020, Definitions.

[28]  Sander M. Bohte,et al.  Editorial: Artificial Neural Networks as Models of Neural Information Processing , 2017, Front. Comput. Neurosci..

[29]  N. Wiener.  Generalized harmonic analysis , 1930 .

[30]  Miomir Mijic,et al.  A simple impulse sound source for measurements in room acoustics , 2008 .

[31]  Gino Iannace,et al.  The Acoustics of the Holy Family Church in Salerno , 2020 .

[32]  R Abdullah,et al.  Potential acoustic treatment analysis using sabine formula in unoccupied classroom , 2020 .

[33]  Alastair H. Moore,et al.  Estimation of Room Acoustic Parameters: The ACE Challenge , 2016, IEEE/ACM Transactions on Audio, Speech, and Language Processing.

[34]  Richard Taylor.  Interpretation of the Correlation Coefficient: A Basic Review , 1990 .

[35]  Gino Iannace,et al.  The acoustics of ancient catacombs in Southern Italy , 2020, Building Acoustics.

[36]  Manolis I. A. Lourakis.  A Brief Description of the Levenberg-Marquardt Algorithm Implemented by levmar , 2005 .

[37]  Anjar Wanto,et al.  Analysis of Backpropagation Algorithm in Predicting the Most Number of Internet Users in the World , 2019, Jurnal Online Informatika.

[38]  Di He,et al.  A Gram-Gauss-Newton Method Learning Overparameterized Deep Neural Networks for Regression Problems , 2019, ArXiv.

[39]  Hao Yu,et al.  Levenberg—Marquardt Training , 2011 .