Design, implementation and evaluation of an acoustic source localization system using Deep Learning techniques

This Master Thesis presents a novel approach for indoor acoustic source localization using microphone arrays, based on a Convolutional Neural Network (CNN) that we call the ASLNet. It directly estimates the three-dimensional position of a single acoustic source using as inputs the raw audio signals...

Descripción completa

Detalles Bibliográficos
Autor: Vera Díaz, Juan Manuel|||0000-0002-6152-5789
Tipo de recurso: tesis de maestría
Fecha de publicación:2019
País:España
Institución:Universidad de Alcalá (UAH)
Repositorio:e_Buah Biblioteca Digital Universidad de Alcalá
Idioma:inglés
OAI Identifier:oai:ebuah.uah.es:10017/38642
Acceso en línea:http://hdl.handle.net/10017/38642
Access Level:acceso abierto
Palabra clave:Acoustic source localization
Microphone arrays
Deep Learning
CNN (Convolutional Neural Network)
Telecomunicaciones
Telecommunication
id ES_9cfbc1c623f0be3b3605bf7aa6522bcd
oai_identifier_str oai:ebuah.uah.es:10017/38642
network_acronym_str ES
network_name_str España
repository_id_str
spelling Design, implementation and evaluation of an acoustic source localization system using Deep Learning techniquesVera Díaz, Juan Manuel|||0000-0002-6152-5789Acoustic source localizationMicrophone arraysDeep LearningCNN (Convolutional Neural Network)TelecomunicacionesTelecommunicationThis Master Thesis presents a novel approach for indoor acoustic source localization using microphone arrays, based on a Convolutional Neural Network (CNN) that we call the ASLNet. It directly estimates the three-dimensional position of a single acoustic source using as inputs the raw audio signals from a set of microphones. We use supervised learning methods to train our network end-to-end. The amount of labeled training data available for this problem is however small. This Thesis presents a training strategy based on two steps that mitigates this problem. We first train our network using semi-synthetic data generated from close talk speech recordings and a mathematical model for signal propagation from the source to the microphones. The amount of semi-synthetic data can be virtually as large as needed. We then fine tune the resulting network using a small amount of real data. Our experimental results, evaluated on a publicly available dataset recorded in a real room, show that this approach is able to improve existing localization methods based on SRP-PHAT strategies and also those presented in very recent proposals based on Convolutional Recurrent Neural Networks (CRNN). In addition, our experiments show that the performance of the ASLNet does not show a relevant dependency on the speaker’s gender, nor on the size of the signal window being used. This work also investigates methods to improve the generalization properties of our network using only semi-synthetic data for training. This is a highly important objective due to the cost of labelling localization data. We proceed by including specific effects in the input signals to force the network to be insensitive to multipath, high noise and distortion likely to be present in real scenarios. We obtain promising results with this strategy although they still lack behind strategies based on fine-tuning.Máster Universitario en Ingeniería de Telecomunicación (M125)Pizarro Pérez, DanielUniversidad de Alcalá. Escuela Politécnica Superior20192019-01-01master thesishttp://purl.org/coar/resource_type/c_bdccNAhttp://purl.org/coar/version/c_be7fb7dd8ff6fe43info:eu-repo/semantics/masterThesisapplication/pdfhttp://hdl.handle.net/10017/38642reponame:e_Buah Biblioteca Digital Universidad de Alcaláinstname:Universidad de Alcalá (UAH)Inglésengopen accesshttp://purl.org/coar/access_right/c_abf2Attribution-NonCommercial-NoDerivatives 4.0 Internationalhttp://creativecommons.org/licenses/by-nc-nd/4.0/info:eu-repo/semantics/openAccessoai:ebuah.uah.es:10017/386422026-06-18T11:13:07Z
dc.title.none.fl_str_mv Design, implementation and evaluation of an acoustic source localization system using Deep Learning techniques
title Design, implementation and evaluation of an acoustic source localization system using Deep Learning techniques
spellingShingle Design, implementation and evaluation of an acoustic source localization system using Deep Learning techniques
Vera Díaz, Juan Manuel|||0000-0002-6152-5789
Acoustic source localization
Microphone arrays
Deep Learning
CNN (Convolutional Neural Network)
Telecomunicaciones
Telecommunication
title_short Design, implementation and evaluation of an acoustic source localization system using Deep Learning techniques
title_full Design, implementation and evaluation of an acoustic source localization system using Deep Learning techniques
title_fullStr Design, implementation and evaluation of an acoustic source localization system using Deep Learning techniques
title_full_unstemmed Design, implementation and evaluation of an acoustic source localization system using Deep Learning techniques
title_sort Design, implementation and evaluation of an acoustic source localization system using Deep Learning techniques
dc.creator.none.fl_str_mv Vera Díaz, Juan Manuel|||0000-0002-6152-5789
author Vera Díaz, Juan Manuel|||0000-0002-6152-5789
author_facet Vera Díaz, Juan Manuel|||0000-0002-6152-5789
author_role author
dc.contributor.none.fl_str_mv Pizarro Pérez, Daniel
Universidad de Alcalá. Escuela Politécnica Superior
dc.subject.none.fl_str_mv Acoustic source localization
Microphone arrays
Deep Learning
CNN (Convolutional Neural Network)
Telecomunicaciones
Telecommunication
topic Acoustic source localization
Microphone arrays
Deep Learning
CNN (Convolutional Neural Network)
Telecomunicaciones
Telecommunication
description This Master Thesis presents a novel approach for indoor acoustic source localization using microphone arrays, based on a Convolutional Neural Network (CNN) that we call the ASLNet. It directly estimates the three-dimensional position of a single acoustic source using as inputs the raw audio signals from a set of microphones. We use supervised learning methods to train our network end-to-end. The amount of labeled training data available for this problem is however small. This Thesis presents a training strategy based on two steps that mitigates this problem. We first train our network using semi-synthetic data generated from close talk speech recordings and a mathematical model for signal propagation from the source to the microphones. The amount of semi-synthetic data can be virtually as large as needed. We then fine tune the resulting network using a small amount of real data. Our experimental results, evaluated on a publicly available dataset recorded in a real room, show that this approach is able to improve existing localization methods based on SRP-PHAT strategies and also those presented in very recent proposals based on Convolutional Recurrent Neural Networks (CRNN). In addition, our experiments show that the performance of the ASLNet does not show a relevant dependency on the speaker’s gender, nor on the size of the signal window being used. This work also investigates methods to improve the generalization properties of our network using only semi-synthetic data for training. This is a highly important objective due to the cost of labelling localization data. We proceed by including specific effects in the input signals to force the network to be insensitive to multipath, high noise and distortion likely to be present in real scenarios. We obtain promising results with this strategy although they still lack behind strategies based on fine-tuning.
publishDate 2019
dc.date.none.fl_str_mv 2019
2019-01-01
dc.type.none.fl_str_mv master thesis
http://purl.org/coar/resource_type/c_bdcc
NA
http://purl.org/coar/version/c_be7fb7dd8ff6fe43
dc.type.openaire.fl_str_mv info:eu-repo/semantics/masterThesis
format masterThesis
dc.identifier.none.fl_str_mv http://hdl.handle.net/10017/38642
url http://hdl.handle.net/10017/38642
dc.language.none.fl_str_mv Inglés
eng
language_invalid_str_mv Inglés
language eng
dc.rights.none.fl_str_mv open access
http://purl.org/coar/access_right/c_abf2
Attribution-NonCommercial-NoDerivatives 4.0 International
http://creativecommons.org/licenses/by-nc-nd/4.0/
dc.rights.openaire.fl_str_mv info:eu-repo/semantics/openAccess
rights_invalid_str_mv open access
http://purl.org/coar/access_right/c_abf2
Attribution-NonCommercial-NoDerivatives 4.0 International
http://creativecommons.org/licenses/by-nc-nd/4.0/
eu_rights_str_mv openAccess
dc.format.none.fl_str_mv application/pdf
dc.source.none.fl_str_mv reponame:e_Buah Biblioteca Digital Universidad de Alcalá
instname:Universidad de Alcalá (UAH)
instname_str Universidad de Alcalá (UAH)
reponame_str e_Buah Biblioteca Digital Universidad de Alcalá
collection e_Buah Biblioteca Digital Universidad de Alcalá
repository.name.fl_str_mv
repository.mail.fl_str_mv
_version_ 1869414704677388288
score 15,300719

Similares en LA Referencia