The Speech Group at FEEIT published their newest results in Macedonian speech synthesis on their webpage. These initial results with the system named “Vezilka” push the envelope on naturalness in Macedonian Text-to-Speech synthesis. The system is under active development and is based on the newest deep learning methods.
The Speech Group has a long and rich tradition and expertise in speech technology, specifically speech synthesis and recognition, as well as analysis and processing. The group functions within the Institute of Electronics , and is closely integrated with the DIPteam.
Besides the permanent research staff, the group also includes master students from the programmes of Multimedia Technologies and Digital Signal Processing, as well as bachelor students following courses from the programme KHIE .