NaturalSpeech: End-to-End Text to Speech Synthesis with Human-Level Quality

Understand

Text to speech (TTS) has made rapid progress in both academia and industry in recent years.

• Some questions naturally arise that whether a TTS system can achieve human-level quality, how to define/judge that quality and how to achieve it.
• In this paper, we answer these questions by first defining the human-level quality based on the statistical significance of subjective measure and introducing appropriate guidelines to judge it, and then developing a TTS system called NaturalSpeech that achieves human-level quality on a benchmark dataset.
• Specifically, we leverage a variational autoencoder (VAE) for end-to-end text to waveform generation, with several key modules to enhance the capacity of the prior from text and reduce the complexity of the posterior from speech, including phoneme pre-training, differentiable duration modeling, bidirectional prior/posterior modeling, and a memory mechanism in VAE.