Voice User Interfaces (VUIs) focus on their application in IT and linguistics. Our research examines the capabilities and limitations of small and multilingual BERT models in the context of speech recognition and command conversion. We evaluate the performance of these models through a series of experiments, including the application of confusion matrices to assess their effectiveness. The findings reveal that larger models like multilingual BERT theoretically offer advanced capabilities but often demand more substantial resources and well-balanced datasets. Conversely, smaller models, though less resource-intensive, may sometimes provide more practical solutions. Our study underscores the importance of dataset quality, model fine-tuning, and efficient resource management in optimising VUIS. Insights gained from this research highlight the potential of neural networks to enhance and improve user interaction. Despite challenges in achieving a fully functional interface, the study provides valuable contributions to the VUIs development and sets the stage for future advancements in integrating AI with linguistic technologies. The article describes the development of a voice user interface (VUI) capable of recognising, analysing, and interpreting the Ukrainian language. For this purpose, several neural network architectures were used, including the Squeezeformer-CTC model, as well as a modified w2v-bert-2.0-uk model, which was used to decode speech commands into text. The multilingual BERT model (mBERT) for the classification of intentions was also tested. The developed system showed the prospects of using BERT models in combination with lightweight ASR architectures to create an effective voice interface in Ukrainian. Accuracy indicators (F1 = 91.5%, WER = 12.7%) indicate high-quality recognition, which is provided even in models with low memory capacity. The system is adaptable to conditions with limited resources, particularly for educational and living environments with a Ukrainian-speaking audience.

This project aims to enhance online experiences quality by giving users greater control over the content they encounter daily. The proposed solution is particularly valuable for parents seeking to safeguard their children, educational institutions striving to foster a more conducive learning environment, and individuals prioritising ethical internet usage. It also supports users who wish to limit their exposure to misinformation, including fake news, propaganda, and disinformation. Through the implementation of a browser extension, this system will contribute to a safer internet, reducing users' vulnerability to harmful content and promoting a more positive and productive online environment. The primary objective of this work is to develop a browser extension that automatically detects and censors inappropriate text and images on web pages using artificial intelligence (AI) technologies. The extension will enable users to personalise censorship settings, including the ability to define custom prohibited words and toggle the filtering of text and images. Accuracy estimates for various classifiers such as Random Forest (0.879), Logistic Regression (0.904), Decision Tree (0.878), Naive Bayes (0.315), and KNN (0.832) were performed.