Several recent end-to-end text-to-speech (TTS) models enabling single-stage training and parallel sampling have been proposed, but their sample quality does not match that of two-stage TTS systems. In this work, we present a parallel end-to-end TTS method that generates more natural sounding audio than current two-stage models. Our method adopts variational inference augmented with normalizing flows and an adversarial training process, which improves the expressive power of generative modeling. We also propose a stochastic duration predictor to synthesize speech with diverse rhythms from input text. With the uncertainty modeling over latent variables and the stochastic duration predictor, our method expresses the natural one-to-many relationship in which a text input can be spoken in multiple ways with different pitches and rhythms. A subjective human evaluation (mean opinion score, or MOS) on the LJ Speech, a single speaker dataset, shows that our method outperforms the best publicly available TTS systems and achieves a MOS comparable to ground truth.
翻译:最近提出了几个端到端文字语音模型(TTS),这些模型能够进行单阶段培训和平行取样,但其样本质量与两阶段TS系统不相匹配。在这项工作中,我们提出了一种平行端到端TTS方法,该方法产生比目前两阶段模型更自然的音频。我们的方法采用变式推论,通过正常流和对称培训过程来增强变异模型的表达力。我们还提出了一个随机时间预测器,用输入文本的不同节奏合成语音。随着对潜在变量和随机持续时间预测器的不确定性建模,我们的方法体现了一种自然的一至端至端关系,在这种关系中,文字输入可以用不同方向和节奏以多种方式进行。对LJ Session的主观人类评价(平均评分,即MOS),这是一个单一的语音数据集,它显示我们的方法超越了最佳的公开 TTS系统,并实现了与地面真理相近的MOS。