This content is not included in
your SAE MOBILUS subscription, or you are not logged in.
Super-Resolution of Sound Source Radiation Using Microphone Arrays and Artificial Intelligence
Technical Paper
2023-01-1142
ISSN: 0148-7191, e-ISSN: 2688-3627
Annotation ability available
Sector:
Language:
English
Abstract
To empirically estimate the radiation of sound sources, a measurement with microphone arrays is required. These are used to solve an inverse problem that provides the radiation characteristics of the source. The resolution of this estimation is a function of the number of microphones used and their position due to spatial aliasing. To improve the radiation resolution for the same number of microphones compared to standard methods (Ridge and Lasso), a method based on normalizing flows is proposed that uses neural networks to learn empirical priors from the radiation data. The method then uses these learned priors to regularize the inverse source identification problem. The effects of different microphone arrays on the accuracy of the method is simulated in order to verify how much additional resolution can be obtained with the additional prior information.
Topic
Citation
Gomes Lobato, T. and Sottek, R., "Super-Resolution of Sound Source Radiation Using Microphone Arrays and Artificial Intelligence," SAE Technical Paper 2023-01-1142, 2023, https://doi.org/10.4271/2023-01-1142.Also In
References
- Williams , E.G. Fourier Acoustics: Sound Radiation and Nearfield Acoustical Holography Academic Press 1999
- Williams , E.G. Regularization Methods for Near-Field Acoustical Holography J. Acoust. Soc. Am. 110 4 1976 1983 2001
- Lobato , T. , and Sottek , R. Near-Field Acoustic Holography Using Far-Field Measurements DAGA Conference Proceedings 2022
- Bellows , S.D. and Leishman , T.W. Obtaining Far-Field Spherical Directivities of Guitar Amplifiers from Arbitrarily Shaped Arrays Using the Helmholtz Equation Least-Squares Method Proc. Mtgs. Acoust. 42 2020
- Kingma , D.P. , and Dhariwal , P. https://arxiv.org/abs/1807.03039 2018
- Dinh , L. , Sohl-Dickstein , J. , and Bengio , S. Density Estimation Using Real NVP Conference Proceedings ICLR 2017
- Whang , J. , Lei , Q. , and Dimakis , A. Solving Inverse Problems with a Flow-based Noise Model Proceedings of the 38th International Conference on Machine Learning, PMLR 139 2021
- Kruse , J. , Ardizzone , L. , Rother , C. , and Köthe , U. Benchmarking Invertible Architectures on Inverse Problems Workshop on Invertible Neural Networks and Normalizing Flows, ICML 2019
- Asim , M. , Daniels , M. , Leong , O. , Ahmed , A. et al. Invertible Generative Models for Inverse Problems: Mitigating Representation Error and Dataset Bias ICML 2020
- Ardizzone , L. , Kruse , J. , Rother , C. and Köthe , U. Analyzing Inverse Problems with Invertible Neural Networks ICLR 2019
- Ardizzone , L. , Lüth , C. , Kruse , J. , Rother , C. et al. https://arxiv.org/abs/1907.02392 2019
- Ahrens , J. Database of Spherical Harmonic Representations of Sound Source Directivities 2020 10.5281/zenodo.3707708
- Falcon , W. 2022 https://www.pytorchlightning.ai2
- Visual Learning Lab Heidelberg 2022
- Loschilov , I. and Hutter , F. Decoupled Weight Decay Regularization ICLR 2019
- Murphy , K. Machine Learning: A Probabilistic Perspective The MIT Press 2012