Zobrazeno 1 - 10
of 23
pro vyhledávání: '"Abdullah Kucuk"'
Publikováno v:
Journal of Imaging, Vol 9, Iss 10, p 214 (2023)
Colour correction is the process of converting RAW RGB pixel values of digital cameras to a standard colour space such as CIE XYZ. A range of regression methods including linear, polynomial and root-polynomial least-squares have been deployed. Howeve
Externí odkaz:
https://doaj.org/article/4e3b8aca92034c7dbc36ad221157da9c
Publikováno v:
IEEE Access, Vol 8, Pp 197047-197058 (2020)
In this article, we present a real-time convolutional neural network (CNN)-based Speech source localization (SSL) algorithm that is robust to realistic background acoustic conditions (noise and reverberation). We have implemented and tested the propo
Externí odkaz:
https://doaj.org/article/acb76dcd136a42c18fa97ab8d21bda0e
Publikováno v:
IEEE Access, Vol 7, Pp 169969-169978 (2019)
In this paper, we present a real-time convolutional neural network (CNN) based approach for speech source localization (SSL) using Android-based smartphone and its two built-in microphones under noisy conditions. We propose a new input feature set -
Externí odkaz:
https://doaj.org/article/196c25dfd9034f8b93f339d5e80ecbde
Publikováno v:
London Imaging Meeting. 3:74-79
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_________::220489bd8db7e6b6a6ceda066bcb7fdd
https://doi.org/10.2352/lim.2022.1.1.17
https://doi.org/10.2352/lim.2022.1.1.17
Publikováno v:
London Imaging Meeting. 3:79-83
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_________::0e5881821096c7bfb643cf7bbef77936
https://doi.org/10.2352/lim.2022.1.1.18
https://doi.org/10.2352/lim.2022.1.1.18
Publikováno v:
IEEE Access, Vol 8, Pp 197047-197058 (2020)
IEEE access : practical innovations, open solutions
IEEE access : practical innovations, open solutions
In this article, we present a real-time convolutional neural network (CNN)-based Speech source localization (SSL) algorithm that is robust to realistic background acoustic conditions (noise and reverberation). We have implemented and tested the propo
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_dedup___::12aea6dd9f0cc50b01eaa87b3f9f26d6
https://ieeexplore.ieee.org/document/9239325/
https://ieeexplore.ieee.org/document/9239325/
Publikováno v:
IEEE Access
IEEE Access, Vol 7, Pp 169969-169978 (2019)
IEEE Access, Vol 7, Pp 169969-169978 (2019)
In this paper, we present a real-time convolutional neural network (CNN) based approach for speech source localization (SSL) using Android-based smartphone and its two built-in microphones under noisy conditions. We propose a new input feature set -
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_dedup___::dd16b3bfa8c12b84e1524377204386ec
https://doi.org/10.1109/access.2019.2955049
https://doi.org/10.1109/access.2019.2955049
Autor:
Issa M. S. Panahi, Abdullah Kucuk
Publikováno v:
MLSP
IEEE Int Workshop Mach Learn Signal Process
IEEE Int Workshop Mach Learn Signal Process
This work proposes a convolutional recurrent neural network (CRNN) based direction of arrival (DOA) angle estimation method, implemented on the Android smartphone for hearing aid applications. The proposed app provides a ‘visual’ indication of th
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_dedup___::d32ffbc61f46568caf0b02b405ee68a1
https://doi.org/10.1109/mlsp49062.2020.9231693
https://doi.org/10.1109/mlsp49062.2020.9231693
Autor:
Metin Ozgul, Abdullah Kucuk
Publikováno v:
Ceramics International. 42:19119-19123
The effects of B 2 O 3 doping on the dielectric and piezoelectric properties of 0.94(Bi 0.5 Na 0.5 ) TiO 3 -0.06BaTiO 3 (BNT-6BT) ceramics were investigated. Pre-reacted BNT-6BT powders synthesized by solid state reaction method were doped with B 3+
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_________::9816c737974ab2c1a1fd3061c7a36a74
https://doi.org/10.1016/j.ceramint.2016.09.073
https://doi.org/10.1016/j.ceramint.2016.09.073
Autor:
Issa M. S. Panahi, Abdullah Kucuk
Publikováno v:
Proc Meet Acoust
Deep neural network (DNN) techniques are gaining popularity due to performance boost in many applications. In this work we propose a DNN-based method for finding the direction of arrival (DOA) of speech source for hearing study improvement and hearin
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_dedup___::0759ebffcd20ae3ea9ef2811680c6858
https://doi.org/10.1121/2.0001256
https://doi.org/10.1121/2.0001256