Bridge-TTS

Official codebase for Schrodinger Bridges Beat Diffusion Models on Text-to-Speech Synthesis.

Project Page | Paper | arXiv

Bridge-TTS leverages a fully tractable Schrodinger Bridge between paired data, tailored for the TTS task. It demonstrates superior performance compared to the diffusion counterpart in both few-step and numerous-step settings.

Please refer to the paper and project page for detailed methods and results.

The code will be released upon acceptance.