معرفی
Joanna Równicka is a Researcher with a Master's degree in Biomedical Engineering from AGH University of Science and Technology (AGH-UST) and a PhD in Speech Technology from the University of Edinburgh's Centre for Speech Technology Research. She currently works as a Research Engineer in London, focusing on deep learning applications for speech recognition and related tasks.
- Education: MSc in Biomedical Engineering (AGH-UST), PhD in Speech Technology (University of Edinburgh)
- Research Focus: Deep representation learning, speech enhancement, speaker recognition, voice synthesis, and voice conversion
Her work explores advanced deep learning techniques for speech processing, including robust speech recognition, text-to-speech synthesis, and speaker profiling. Recent publications highlight innovations in octave convolutions, embeddings for speaker adaptation, and quality estimation in multi-speaker synthesis.
Joanna's earlier research, including publications on medical applications of mathematics and emergency call center systems, demonstrates interdisciplinary expertise bridging biomedical engineering and speech technology.
