Institutional Repository of Vilnius University
Voice command recognition using local resources /
Abstract
dc:descriptionThis research explores the development of a voice command recognition system integrated into a To-Do List application, enabling users to manage tasks through voice interactions. Supporting multiple languages, including English, Russian, Ukrainian, Lithuanian, and Spanish, the system leverages the Whisper model for speech-to-text conversion and the OpenAI API for intelligent, natural language responses. Tasks are managed in an SQLite3 database, providing an efficient and lightweight backend. Key features include Voice Commands for task management actions like creating, deleting, and modifying tasks, and a Voice Assistant for answering user queries. By enabling hands-free interaction, the system enhances accessibility and productivity, particularly for users with limited mobility or those seeking convenience. Built with Python and libraries such as PyAudio and Whisper, it offers robust functionality and a user-friendly experience. The system demonstrates strong multilingual support and effective integration of voice recognition and natural language processing technologies. Future improvements could focus on advanced NLP capabilities, expanded functionality (e.g., reminders and calendar integration), and performance optimization. This work highlights the potential of voice-driven interfaces in personal productivity tools and accessibility solutions.
Degree
thesis:*- Grantor dc:publisher
- Institutional Repository of Vilnius University
- Year dc:date
- 2025
Author and committee
dc:creator, dc:contributor.*- Author dc:creator
-
- Shtyvola, Mykhailo,
Subjects
dc:subject × 1Rights
dc:rights- Statement dc:rights
-
- info:eu-repo/semantics/openAccess
- Language dc:language
- eng
Identifiers
dc:identifier.*- Repository record dc:identifier
- https://repository.vu.lt/VU:ELABAETD229558683&prefLang=en_US