Кафедра інформатики
Permanent URI for this community
Browse
Browsing Кафедра інформатики by Subject "bachelor's thesis"
Now showing 1 - 3 of 3
Results Per Page
Sort Options
Item Decoding Speech from ECoG with Machine Translation Models(2023) Burakov, Roman; Shvai, Nadyia; Wang, BoThis paper explores the use and improvement of brain-computer interface (BCI)- based speech neuroprostheses, devices designed to enhance communication for individuals with speech disorders. Focusing on the machine learning aspect, we address the existing challenges associated with these systems, such as the limited vocabulary and simple algorithms of previous research and the individual variances in electrode implantation sites. Our approach reframes the decoding of speech from BCI as a machine translation problem and employs existing language models for semantic knowledge transfer. This research provides an extensive analysis of current neural speech decoding and multilingual neural machine translation methods, adapts the pre-existing M2M100 neural machine translation model for decoding ECoG data into text, and introduces a state-of-the-art model for neural speech decoding that improves upon current methods in semantic text reconstructions.Item Use of augmented reality to build an interactive interior on the iOS mobile platform.(2022) Babii, Veronika; Frankiv, OleksandrThe thesis is devoted to the study of possibilities of the 3D object creation from the real-life surroundings on the Apple iOS platform. The research is based on the development of a mobile application for the iOS operating system for 3D model creation of the surroundings via the help of the LiDAR Scanner.Item Розробка алгоритму автоматичної синхронізації губ та рис обличчя у відеопотоці з аудіо(2021) Андронік, Владислав; Бучко, ОленаThis material presents the solution to generate talking face images with the use of deep learning. We conduct the research of existing literature to compose more efficient network design. The final version has additional pre-trained discriminator network to reach superior lip synchronization performance with adversarial training to improve the visual quality of images. We provide comparative analysis and ablation studies which show insights on how different components of the solution affect the result. This approach achieves comparable consistency in lip movements to other solutions in the field, but has higher visual quality.