A unified deep learning framework for short-duration speaker verification in adverse environments

Y Jung, Y Choi, H Lim, H Kim - IEEE Access, 2020 - ieeexplore.ieee.org
Speaker verification (SV) has recently attracted considerable research interest due to the
growing popularity of virtual assistants. At the same time, there is an increasing requirement …

Mass: Microphone array speech simulator in room acoustic environment for multi-channel speech coding and enhancement

R Cheng, C Bao, Z Cui - Applied sciences, 2020 - mdpi.com
Featured Application The proposed MASS can simulate multiple signals collected by
microphone array in room acoustic environment for multi-channel speech coding and …

Self-adaptive soft voice activity detection using deep neural networks for robust speaker verification

Y Jung, Y Choi, H Kim - 2019 IEEE Automatic Speech …, 2019 - ieeexplore.ieee.org
Voice activity detection (VAD), which classifies frames as speech or non-speech, is an
important module in many speech applications including speaker verification. In this paper …

A new software defined network (SDN) in IoTs based deep learning techniques

AHI Alajdah - 2022 - openaccess.altinbas.edu.tr
In the study, a new SDN in IoTs using deep learning techniques is used. In the first stage, the
DBN applied to the input data to extract effective features of malware. The DBN consist of …

Computer network trafic classification based AI techniques

MA Ali - 2022 - openaccess.altinbas.edu.tr
Identifying and categorizing network traffic is the initial step in determining what sorts of
applications are traveling via the network. An internet service provider or network operator …

5G data communication defect detection on the internet of things using advanced deep learning techniques

ANM Mahmood - 2022 - openaccess.altinbas.edu.tr
In telecommunication, 5G is a fifth-generation broadband cellular network technology
standard that mobile operators around the world began rolling out in 2019 and is the …

[PDF][PDF] Распознавание речи на основе сверточных нейронных сетей

РЮ Белоруцкий, СВ Житник - Вопросы радиоэлектроники, 2019 - scholar.archive.org
Рассматривается задача распознавания речи человека в виде записанных на
диктофон сигналов произнесенных цифр от 1 до 10. Использован метод …

Hybrid method based deep belief networks for malware detection in IoTs

RIA Allaban - 2022 - openaccess.altinbas.edu.tr
Malware is any software deliberately intended to reason disturbance to a computer,
attendant, customer, or computer network, escape secluded information, improvement illegal …

A new cybersecurity application using hybrid machine learning method

M Çevik - 2022 - openaccess.altinbas.edu.tr
The adoption of security measures against cyber attacks has become a necessity for
everyone in the current conditions. Applying and implementing these requirements in the …

Predicting brain tumours using artificial neural networks

LAJ Shnawa - 2022 - openaccess.altinbas.edu.tr
Segmenting a picture means cutting it up into individual parts. One of the most challenging
jobs in image processing, it has significant real-world implications. It has several …