PPSpeech: Phrase based Parallel End-to-End TTS System

Understand

Current end-to-end autoregressive TTS systems (e.g.

• Tacotron 2) have outperformed traditional parallel approaches on the quality of synthesized speech.
• However, they introduce new problems at the same time.
• Due to the autoregressive nature, the time cost of inference has to be proportional to the length of text, which pose a great challenge for online serving.