OZSpeech: One-step Zero-shot Speech Synthesis with Learned-Prior-Conditioned Flow Matching

Hieu-Nghia Huynh-Nguyen, Ngoc Son Nguyen, Huynh Nguyen Dang +3

Text-to-speech (TTS) systems have seen significant advancements in recent years, driven by improvements in deep learning and neural network architectures. Viewing the output speech…