Estimation of Azimuth and Elevation for Multiple Acoustic Sources Using Tetrahedral Microphone Arrays and Convolutional Neural Networks

A method for multiple acoustic source localization using a tetrahedral microphone array and a convolutional neural network (CNN) is presented. Our method presents a novel approach for the estimation of acoustic source direction of arrival (DoA), both azimuth and elevation, utilizing a non-coplanar m...

Descripción completa

Guardado en:

Detalles Bibliográficos
Autores principales:	Saulius Sakavičius, Artūras Serackis
Formato:	article
Lenguaje:	EN
Publicado:	MDPI AG 2021
Materias:	acoustic source localization multiple source localization machine learning tetrahedral sensor arrays Electronics TK7800-8360
Acceso en línea:	https://doaj.org/article/97be8e8cbd2348618994e6fa20d96ef4
Etiquetas:	Agregar Etiqueta Sin Etiquetas, Sea el primero en etiquetar este registro!

id	oai:doaj.org-article:97be8e8cbd2348618994e6fa20d96ef4
record_format	dspace
spelling	oai:doaj.org-article:97be8e8cbd2348618994e6fa20d96ef42021-11-11T15:37:09ZEstimation of Azimuth and Elevation for Multiple Acoustic Sources Using Tetrahedral Microphone Arrays and Convolutional Neural Networks10.3390/electronics102125852079-9292https://doaj.org/article/97be8e8cbd2348618994e6fa20d96ef42021-10-01T00:00:00Zhttps://www.mdpi.com/2079-9292/10/21/2585https://doaj.org/toc/2079-9292A method for multiple acoustic source localization using a tetrahedral microphone array and a convolutional neural network (CNN) is presented. Our method presents a novel approach for the estimation of acoustic source direction of arrival (DoA), both azimuth and elevation, utilizing a non-coplanar microphone array. In our approach, we use the phase component of the short-time Fourier transform (STFT) of the microphone array’s signals as the input feature for the CNN and a DoA probability density map as the training target. Our findings imply that our method outperforms the currently available methods for multiple sound source DoA estimation in both accuracy and speed.Saulius SakavičiusArtūras SerackisMDPI AGarticleacoustic source localizationmultiple source localizationmachine learningtetrahedral sensor arraysElectronicsTK7800-8360ENElectronics, Vol 10, Iss 2585, p 2585 (2021)
institution	DOAJ
collection	DOAJ
language	EN
topic	acoustic source localization multiple source localization machine learning tetrahedral sensor arrays Electronics TK7800-8360
spellingShingle	acoustic source localization multiple source localization machine learning tetrahedral sensor arrays Electronics TK7800-8360 Saulius Sakavičius Artūras Serackis Estimation of Azimuth and Elevation for Multiple Acoustic Sources Using Tetrahedral Microphone Arrays and Convolutional Neural Networks
description	A method for multiple acoustic source localization using a tetrahedral microphone array and a convolutional neural network (CNN) is presented. Our method presents a novel approach for the estimation of acoustic source direction of arrival (DoA), both azimuth and elevation, utilizing a non-coplanar microphone array. In our approach, we use the phase component of the short-time Fourier transform (STFT) of the microphone array’s signals as the input feature for the CNN and a DoA probability density map as the training target. Our findings imply that our method outperforms the currently available methods for multiple sound source DoA estimation in both accuracy and speed.
format	article
author	Saulius Sakavičius Artūras Serackis
author_facet	Saulius Sakavičius Artūras Serackis
author_sort	Saulius Sakavičius
title	Estimation of Azimuth and Elevation for Multiple Acoustic Sources Using Tetrahedral Microphone Arrays and Convolutional Neural Networks
title_short	Estimation of Azimuth and Elevation for Multiple Acoustic Sources Using Tetrahedral Microphone Arrays and Convolutional Neural Networks
title_full	Estimation of Azimuth and Elevation for Multiple Acoustic Sources Using Tetrahedral Microphone Arrays and Convolutional Neural Networks
title_fullStr	Estimation of Azimuth and Elevation for Multiple Acoustic Sources Using Tetrahedral Microphone Arrays and Convolutional Neural Networks
title_full_unstemmed	Estimation of Azimuth and Elevation for Multiple Acoustic Sources Using Tetrahedral Microphone Arrays and Convolutional Neural Networks
title_sort	estimation of azimuth and elevation for multiple acoustic sources using tetrahedral microphone arrays and convolutional neural networks
publisher	MDPI AG
publishDate	2021
url	https://doaj.org/article/97be8e8cbd2348618994e6fa20d96ef4
work_keys_str_mv	AT sauliussakavicius estimationofazimuthandelevationformultipleacousticsourcesusingtetrahedralmicrophonearraysandconvolutionalneuralnetworks AT arturasserackis estimationofazimuthandelevationformultipleacousticsourcesusingtetrahedralmicrophonearraysandconvolutionalneuralnetworks
_version_	1718435000201773056

Estimation of Azimuth and Elevation for Multiple Acoustic Sources Using Tetrahedral Microphone Arrays and Convolutional Neural Networks

Ejemplares similares