Although neural text-to-speech (TTS) models have attracted a lot of attention
and succeeded in generating human-like speech, there is still room for
improvements to its naturalness and architectural efficiency. In this work, we
propose a novel non-autoregressive TTS model, namely Diff-TTS, which achieves
highly natural and efficient speech synthesis. Given the text, Diff-TTS
exploits a denoising diffusion framework to transform the noise signal into a
mel-spectrogram via diffusion time steps. In order to learn the mel-spectrogram
distribution conditioned on the text, we present a likelihood-based
optimization method for TTS. Furthermore, to boost up the inference speed, we
leverage the accelerated sampling method that allows Diff-TTS to generate raw
waveforms much faster without significantly degrading perceptual quality.
Through experiments, we verified that Diff-TTS generates 28 times faster than
the real-time with a single NVIDIA 2080Ti GPU.

本文介绍了一种新型非自回归 TTS 模型 Diff-TTS，以噪声信号与扩散时间步长探索去噪扩散框架，同时引入基于可能性的 TTS 优化方法，利用加速采样方法提高波形合成速度，实验证明 Diff-TTS 单独搭载一枚 NVIDIA 2080Ti 显卡比实时生成快 28 倍，并且质量良好。