TY - JOUR
T1 - Generative models for sound field reconstruction
AU - Fernandez-Grande, Efren
AU - Karakonstantis, Xenofon
AU - Caviedes-Nozal, Diego
AU - Gerstoft, Peter
N1 - Publisher Copyright:
© 2023 Author(s).
PY - 2023/2
Y1 - 2023/2
N2 - This work examines the use of generative adversarial networks for reconstructing sound fields from experimental data. It is investigated whether generative models, which learn the underlying statistics of a given signal or process, can improve the spatio-temporal reconstruction of a sound field by extending its bandwidth. The problem is significant as acoustic array processing is naturally band limited by the spatial sampling of the sound field (due to the difficulty to satisfy the Nyquist criterion in space domain at high frequencies). In this study, the reconstruction of spatial room impulse responses in a conventional room is tested based on three different generative adversarial models. The results indicate that the models can improve the reconstruction, mostly by recovering some of the sound field energy that would otherwise be lost at high frequencies. There is an encouraging outlook in the use of statistical learning models to overcome the bandwidth limitations of acoustic sensor arrays. The approach can be of interest in other areas, such as computational acoustics, to alleviate the classical computational burden at high frequencies.
AB - This work examines the use of generative adversarial networks for reconstructing sound fields from experimental data. It is investigated whether generative models, which learn the underlying statistics of a given signal or process, can improve the spatio-temporal reconstruction of a sound field by extending its bandwidth. The problem is significant as acoustic array processing is naturally band limited by the spatial sampling of the sound field (due to the difficulty to satisfy the Nyquist criterion in space domain at high frequencies). In this study, the reconstruction of spatial room impulse responses in a conventional room is tested based on three different generative adversarial models. The results indicate that the models can improve the reconstruction, mostly by recovering some of the sound field energy that would otherwise be lost at high frequencies. There is an encouraging outlook in the use of statistical learning models to overcome the bandwidth limitations of acoustic sensor arrays. The approach can be of interest in other areas, such as computational acoustics, to alleviate the classical computational burden at high frequencies.
U2 - 10.1121/10.0016896
DO - 10.1121/10.0016896
M3 - Journal article
C2 - 36859132
AN - SCOPUS:85148422919
SN - 0001-4966
VL - 153
SP - 1179
EP - 1190
JO - Journal of the Acoustical Society of America
JF - Journal of the Acoustical Society of America
IS - 2
ER -