Emre Beray Boztepe

Junior Software Developer
Avatar

Publications


  • Videolardaki Çevresel Sesleri Tanımak İçin Derin Öğrenme Tabanlı Bir Model Geliştirme (Development of a Deep Learning Based Model for Recognizing the Environmental Sounds in Videos)
    28-29 May 2022
    Doi: 10.36287

    The article has been published on SETSCI Proceeding Book (Vol. 5 no.1, year:2022, pg:53-58) in Turkish. I also presented this article at the ISAS 2022 symposium. Here, you can read the translation that I've made of this article to English: English Verison

  • An Approach for Audio-Visual Content Understanding of Video Using Deep Learning Methodology
    30 August 2022
    Doi: 10.35377

    This is also called The Avesa, and I've shared the details in the projects section. This is the article of this work, which has been written in English and has been published on Sakarya University Journal of Computer and Information Sciences (Sakarya University Journal of Computer and Information Sciences, c. 5, sayı. 2, ss. 181-207, Ağu. 2022, doi:10.35377/saucis...1139765). Here, you can check the details of the published scientific work: Article

  • A Deep Learning Approach based on Ensemble Classification Pipeline and Interpretable Logical Rules for Bilingual Fake Speech Recognition
    In the publishing phase, it is accepted.
    -

    Abstract: The essential steps of our study are to quantify and classify the differences between real and fake speech signals. In this scope, the main aim is to use the salient feature learning ability of deep learning in our study. With the use of ensemble classification pipeline, the interpretable logical rules were used for generalized reasoning with the class activation maps to discriminate the different speech classes as correctly. Fake audio samples were generated by using Deep Convolutional Generative Adversarial Neural Network. Our experiments were conducted on three different language dataset such as Turkish, English languages and Bilingual. As a result of higher classification and recognition accuracy with the use of classification pipeline as compiled into a majority voting-based ensemble classifier, the experimental results were obtained for each individual language performance approximately as 90% for training and as 80.33% for testing stages for pipeline, and it reached as 73% for majority voting results considered together with the appropriate test cases as well. To extract semantically rich rules, an interpretable logical rules infrastructure was used to infer the correct fake speech from class activations of deep learning’s generative model. Discussion and conclusion based on scientific findings are included in our study.


    • Here, you can check the details of the scientific work (The link is going to be updated after the article published):



References

Prof. Dr. Bahadır Karasulu

Prof. Zbigniew Omiotek

Prof. Michał Wydra
  • He is a professor at Lublin University of Technology. He was my tutor for some data analysis projects using Matlab that I described one of them in the project section that is called Matlab GUI Data Analysis.
  • codeSTACKr | Mail : [email protected]
  • : Google Scholar Michał Wydra

Koray Değer
  • He is a senior game developer. He is head of game development at Narcade. He was my lead while I was working for the Narcade company.
  • codeSTACKr | Mail : [email protected]

Abd-Ur Raheem
  • He is a Full Stack Developer & AI Expert. He was my tutor during my internship, during which I worked on some websites that I described in the projects section that are called Çiftlik Sistem and Atlas Labaratory System.
  • codeSTACKr | Mail : [email protected]
  • : Google Scholar Abd-Ur Raheem

Yahya Doğan
  • He is a Computer Engineer. He was my boss while I was working for the Piri Teknoloji company.
  • LinkedIn

Bilal Türk
  • He is a Computer Engineer. He was my tutor during my internship, during which I worked on some websites that I described in the projects section that is called Atlas Labaratory System.
  • codeSTACKr | Mail : [email protected]