Please use this identifier to cite or link to this item: http://dx.doi.org/10.14279/depositonce-8779
Main Title: On sound source localization of speech signals using deep neural networks
Author(s): Roden, Reinhild
Moritz, Niko
Gerlach, Stephan
Weinzierl, Stefan
Goetze, Stefan
Type: Conference Object
Language Code: en
Abstract: In recent years artificial neural networks are successfully applied especially in the context of automatic speech recognition. As information processing systems, neural networks are trained by, e.g., backpropagation or restricted Boltzmann machines to classify patterns at the input of the system. The current work presents the implementation of a deep neural network (DNN) architecture for acoustic source localization.
URI: https://depositonce.tu-berlin.de/handle/11303/9746
http://dx.doi.org/10.14279/depositonce-8779
Issue Date: 2015
Date Available: 9-Aug-2019
DDC Class: 534 Schall und verwandte Schwingungen
620 Ingenieurwissenschaften und zugeordnete Tätigkeiten
Subject(s): speech
deep neural network
DNN
interaural level di erence
ILD
interaural phase difference
IPD
interaural time delay
ITD
Sponsor/Funder: EC/FP7/318381/EU/Experimenting Acoustics in Real environments using Innovative Test-beds/EAR-IT
EC/FP7/284628/EU/Sounds for Energy Control of Buildings/S4ECoB
EC/FP7/609180/EU/Energy efficient & Cost competitive retrofitting solutions for Shopping buildings/ECOSHOPPING
License: http://rightsstatements.org/vocab/InC/1.0/
Proceedings Title: Fortschritte der Akustik - DAGA 2015: 41. Jahrestagung für Akustik, 16. - 19. März 2015 in Nürnberg
Publisher: Deutsche Gesellschaft für Akustik e.V.
Publisher Place: Berlin
Page Start: 1510
Page End: 1513
ISBN: 978-3-939296-08-9
Appears in Collections:FG Audiokommunikation » Publications

Files in This Item:
File Description SizeFormat 
roden_etal_2015.pdf1.13 MBAdobe PDFThumbnail
View/Open


Items in DepositOnce are protected by copyright, with all rights reserved, unless otherwise indicated.