The effectiveness of using a pretrained deep learning neural networks for object classification in underwater video

P Szymak, P Piskur, K Naus - Remote Sensing, 2020 - mdpi.com
Video image processing and object classification using a Deep Learning Neural Network
(DLNN) can significantly increase the autonomy of underwater vehicles. This paper …

Voiceprint identification for limited dataset using the deep migration hybrid model based on transfer learning

C Sun, Y Yang, C Wen, K **e, F Wen - Sensors, 2018 - mdpi.com
The convolutional neural network (CNN) has made great strides in the area of voiceprint
recognition; but it needs a huge number of data samples to train a deep neural network. In …

[PDF][PDF] Assessing the degree of nativeness and Parkinson's condition using Gaussian processes and deep rectifier neural networks

T Grósz, R Busa-Fekete, G Gosztolya… - … Annual Conference of …, 2015 - inf.u-szeged.hu
Abstract The Interspeech 2015 Computational Paralinguistics Challenge includes two
regression learning tasks, namely the Parkinson's Condition Sub-Challenge and the Degree …

Laughter classification using Deep Rectifier Neural Networks with a minimal feature subset

G Gosztolya, B András, T Neuberger… - Archives of …, 2016 - acoustics.ippt.gov.pl
Laughter is one of the most important paralinguistic events, and it has specific roles in
human conversation. The automatic detection of laughter occurrences in human speech can …

[PDF][PDF] Detecting the intensity of cognitive and physical load using AdaBoost and Deep Rectifier Neural Networks

G Gosztolya, T Grósz, R Busa-Fekete… - … Annual Conference of …, 2014 - researchgate.net
Abstract The Interspeech ComParE 2014 Challenge consists of two machine learning tasks,
which have quite a small number of examples. Due to our good results in ComParE 2013 …

Automatic close captioning for live hungarian television broadcast speech: A fast and resource-efficient approach

Á Varga, B Tarján, Z Tobler, G Szaszák, T Fegyó… - Speech and Computer …, 2015 - Springer
In this paper, the application of LVCSR (Large Vocabulary Continuous Speech Recognition)
technology is investigated for real-time, resource-limited broadcast close captioning. The …

QR code localization using deep neural networks

T Grósz, P Bodnár, L Tóth… - 2014 IEEE International …, 2014 - ieeexplore.ieee.org
Usage of computer-readable visual codes became common in our everyday life at industrial
environments and private use. The reading process of visual codes consists of two steps …

[PDF][PDF] Enhancing constructive neural network performance using functionally expanded input data

JRB Junior, M do Carmo Nicoletti - Journal of Artificial Intelligence and …, 2016 - sciendo.com
Constructive learning algorithms are an efficient way to train feedforward neural networks.
Some of their features, such as the automatic definition of the neural network (NN) …

Efficient visual code localization with neural networks

P Bodnár, T Grósz, L Tóth, LG Nyúl - Pattern Analysis and Applications, 2018 - Springer
The use of computer-readable visual codes became common in our everyday life both in
industrial environments and for private use. The reading process of visual codes consists of …

[PDF][PDF] Domain adaptation of deep neural networks for automatic speech recognition via wireless sensors

G Gosztolya, T Grósz - Journal of Electrical Engineering, 2016 - sciendo.com
Wireless sensors are recent, portable, low-powered devices, designed to record and
transmit observations of their environment such as speech. To allow portability they are …