Abstract: Current sEMG-based speech generation methods primarily rely on large-scale datasets from single participants, which imposes a burden on users. Moreover, previous research methods often ...

Small and fast: only 123M parameters. High-quality voice cloning: state-of-the-art performance in speaker similarity, intelligibility, and naturalness. Multi-lingual: support Chinese and English.

Abstract: Recent advances in automatic speech recognition (ASR) have led to substantial improvements in system accuracy and robustness, particularly in converting speech signals into text sequences.