Filters








1,230 Hits in 8.4 sec

Prediction of Object Geometry from Acoustic Scattering Using Convolutional Neural Networks [article]

Ziqi Fan, Vibhav Vineet, Chenshen Lu, T.W. Wu, Kyla McMullen
2021 arXiv   pre-print
The present work proposes a method to infer object geometry from scattering features by training convolutional neural networks.  ...  Acoustic scattering is strongly influenced by boundary geometry of objects over which sound scatters.  ...  [22] proposed to predict acoustic scattering from objects using a convolutional neural network (CNN). The CNN was trained using images representing object geometry and acoustic fields.  ... 
arXiv:2010.10691v3 fatcat:jempbcwad5eztidlbxkgoi5g7y

Fast acoustic scattering using convolutional neural networks [article]

Ziqi Fan, Vibhav Vineet, Hannes Gamper, Nikunj Raghuvanshi
2020 arXiv   pre-print
We propose training a convolutional neural network to map from a convex scatterer's cross-section to a 2D slice of the resulting spatial loudness distribution.  ...  Diffracted scattering and occlusion are important acoustic effects in interactive auralization and noise control applications, typically requiring expensive numerical simulation.  ...  CONCLUSION AND OUTLOOK We investigated the application of convolutional neural networks (CNNs) to the problem of acoustic scattering from arbitrary convex prism shapes.  ... 
arXiv:1911.01802v3 fatcat:4d5wxh3nqzc6dkrvddzdtmj47i

A Texture Superpixel Approach to Semantic Material Classification for Acoustic Geometry Tagging

Mattia Colombo, Alan Dolhasz, Carlo Harvey
2021 Extended Abstracts of the 2021 CHI Conference on Human Factors in Computing Systems  
Among factors affecting realism of acoustic simulations is the mapping between an environment's geometry, and acoustic information of materials represented.  ...  The most frequent label from predicted texture patches determines the acoustic material assigned to the input mesh.  ...  Advances in acoustic modelling propose automatic tagging of acoustic data to scene geometry using convolutional neural networks to tag acoustic materials from stereo photographs of real environments [  ... 
doi:10.1145/3411763.3451657 fatcat:hzxs54wgxfarxh6wsa2fyd4su4

A Generative deep learning approach for shape recognition of arbitrary objects from phaseless acoustic scattering data [article]

W. W. Ahmed, M. Farhat, P.-Y. Chen, X. Zhang, Y. Wu
2022 arXiv   pre-print
The strategy exploits deep neural networks to learn the mapping between the latent space of a two-dimensional acoustic object and the far-field scattering amplitudes.  ...  We propose and demonstrate a generative deep learning approach for the shape recognition of an arbitrary object from its acoustic scattering properties.  ...  Acknowledgements The work described in here is supported by King Abdullah University of Science and Technology (KAUST) Artificial Intelligence Initiative Fund and KAUST Baseline Research Fund No.  ... 
arXiv:2207.05433v1 fatcat:t3jm5n3wlvf6zckzmp6ulzq6r4

SINR: Deconvolving Circular SAS Images Using Implicit Neural Representations [article]

Albert Reed, Thomas Blanford, Daniel C. Brown, Suren Jayasuriya
2022 arXiv   pre-print
We can characterize resolution by modeling CSAS imaging as the convolution between a scene's underlying point scattering distribution and a system-dependent point spread function (PSF).  ...  We propose a self-supervised pipeline (does not require training data) that leverages an implicit neural representation (INR) for deconvolving CSAS images.  ...  This approach utilizes a single PSF to perform the convolution, and gives the responsibility of handling its spatially varying properties to our neural network predicting a complex scene of scatterers.  ... 
arXiv:2204.10428v1 fatcat:trdibcxz3javjb3jqg37txyzam

Acoustic Cloak Design via Machine Learning [article]

Thang Tran, Feruza Amirkulova, Ehsan Khatami
2021 arXiv   pre-print
Here, we work with sets of cylindrical objects confined in a region of space and use machine learning methods to streamline the design of 2D configurations of scatterers with minimal TSCS demonstrating  ...  The design of acoustic cloaks using scattering cancellation has traditionally involved the optimization of metamaterial structure based on direct computer simulations of the total scattering cross section  ...  Acknowledgements TT, FA, and EK acknowledge Small Grant Project (SGP) grant support from San Jose State University.  ... 
arXiv:2111.01230v1 fatcat:oagfumqxjbesfalyolpnpcxa6u

2019 Index IEEE/ACM Transactions on Audio, Speech, and Language Processing Vol. 27

2019 IEEE/ACM Transactions on Audio Speech and Language Processing  
., +, TASLP Dec. 2019 1970-1984 Neural Predictive Coding Using Convolutional Neural Networks Toward Unsupervised Learning of Speaker Characteristics.  ...  Zhang, Z., +, TASLP Nov. 2019 1664-1674 Neural Predictive Coding Using Convolutional Neural Networks Toward Unsupervised Learning of Speaker Characteristics.  ... 
doi:10.1109/taslp.2020.2971902 fatcat:j66uwjyqlfbmtgda6zhzlswpva

Point-based Acoustic Scattering for Interactive Sound Propagation via Surface Encoding [article]

Hsien-Yu Meng, Zhenyu Tang, Dinesh Manocha
2021 arXiv   pre-print
We show that our formulation is permutation invariant and present a neural network that computes the scattering function using spherical harmonics.  ...  We present a novel geometric deep learning method to compute the acoustic scattering properties of geometric objects.  ...  [Pulkki and Svensson, 2019] propose to use a neural network to model the acoustic scattering effect from rectangular plates.  ... 
arXiv:2105.08177v1 fatcat:cqs5xneav5f6dopl6e4opvot2m

Learning Acoustic Scattering Fields for Dynamic Interactive Sound Propagation [article]

Zhenyu Tang, Hsien-Yu Meng, Dinesh Manocha
2020 arXiv   pre-print
We use geometric deep learning to approximate the acoustic scattering field using spherical harmonics.  ...  Our approach is designed for dynamic scenes and uses a neural network-based learned scattered field representation along with ray tracing to generate specular, diffuse, diffraction, and occlusion effects  ...  Neural networks have also been used to replace the expensive convolution operations for fast auralization [46] , to render the acoustic effects of scattering from rectangular plate objects for VR applications  ... 
arXiv:2010.04865v2 fatcat:y3upn5ftf5bxxbl4xsadqkk4xy

Speaker location and microphone spacing invariant acoustic modeling from raw multichannel waveforms

Tara N. Sainath, Ron J. Weiss, Kevin W. Wilson, Arun Narayanan, Michiel Bacchiani, Andrew
2015 2015 IEEE Workshop on Automatic Speech Recognition and Understanding (ASRU)  
In this paper, we present an algorithm to do multichannel enhancement jointly with the acoustic model, using a raw waveform convolutional LSTM deep neural network (CLDNN).  ...  Multichannel ASR systems commonly use separate modules to perform speech enhancement and acoustic modeling.  ...  Current acoustic models are generally neural network based where optimization is performed using a gradient learning algorithm.  ... 
doi:10.1109/asru.2015.7404770 dblp:conf/asru/SainathWWNBS15 fatcat:6evifjtjdfea3mx3rl2mjdh7wy

2020 Index IEEE/ACM Transactions on Audio, Speech, and Language Processing Vol. 28

2020 IEEE/ACM Transactions on Audio Speech and Language Processing  
., +, TASLP 2020 1745-1754 Sound Events Recognition and Retrieval Using Multi-Convolutional-Channel Sparse Coding Convolutional Neural Networks.  ...  Lee, T., +, TASLP 2020 2412-2426 Sound Events Recognition and Retrieval Using Multi-Convolutional-Channel Sparse Coding Convolutional Neural Networks.  ... 
doi:10.1109/taslp.2021.3055391 fatcat:7vmstynfqvaprgz6qy3ekinkt4

2021 Index IEEE Signal Processing Letters Vol. 28

2021 IEEE Signal Processing Letters  
-that appeared in this periodical during 2021, and items from previous years that were commented upon or corrected in 2021.  ...  The primary entry includes the coauthors' names, the title of the paper or other item, and its location, specified by the publication abbreviation, year, month, and inclusive pagination.  ...  ., +, LSP 2021 1505-1509 Electromagnetic wave scattering Space Target Attitude Estimation From ISAR Image Sequences With Key Point Extraction Network.  ... 
doi:10.1109/lsp.2022.3145253 fatcat:a3xqvok75vgepcckwnhh2mty74

Echo-Reconstruction: Audio-Augmented 3D Scene Reconstruction [article]

Justin Wilson and Nicholas Rewkowski and Ming C. Lin and Henry Fuchs
2021 arXiv   pre-print
Reflected sound and images from the video are input into our audio (EchoCNN-A) and audio-visual (EchoCNN-AV) convolutional neural networks for surface and sound source detection, depth estimation, and  ...  We propose Echoreconstruction, an audio-visual method that uses the reflections of sound to aid in geometry and audio reconstruction for virtual conferencing, teleimmersion, and other AR/VR experience.  ...  We use these distinct, reflecting sounds to design a staged approach of audio and audio-visual convolutional neural networks.  ... 
arXiv:2110.02405v1 fatcat:ej7ey5c645cbren37hflg42v5q

2021 Index IEEE Journal of Oceanic Engineering Vol. 46

2021 IEEE Journal of Oceanic Engineering  
-that appeared in this periodical during 2021, and items from previous years that were commented upon or corrected in 2021.  ...  The primary entry includes the coauthors' names, the title of the paper or other item, and its location, specified by the publication abbreviation, year, month, and inclusive pagination.  ...  ., JOE Jan. 2021 236-260 Real-Time Object Detection for AUVs Using Self-Cascaded Convolutional Neural Networks.  ... 
doi:10.1109/joe.2021.3122747 fatcat:g4vktyf3wjbb7dmviaosvx32oe

Seabed classification using physics-based modeling and machine learning

Christina Frederick, Soledad Villar, Zoi-Heleni Michalopoulou
2020 Journal of the Acoustical Society of America  
For higher accuracy, one-dimensional convolutional neural networks are employed.  ...  Second, the high-frequency model of the scattering from a rough, two-layer seafloor is considered. Again, four different sediment possibilities are classified with machine learning.  ...  S.V. is partly supported by NSF DMS Grant Nos. 1913134, EOARD FA9550-18-1-7007, and the Simons Algorithms and Geometry (A and G) Think Tank.  ... 
doi:10.1121/10.0001728 pmid:32873029 fatcat:nox5swr5izbhthfpomiecfkbem
« Previous Showing results 1 — 15 out of 1,230 results