Denoising diffusion probabilistic models (DDPMs) are expressive generative
models that have been used to solve a variety of speech synthesis problems.
However, because of their high sampling costs, DDPMs are difficult to use in
real-time speech processing applications. In this paper, we introduce
DiffGAN-TTS, a novel DDPM-based text-to-speech (TTS) model achieving
high-fidelity and efficient speech synthesis. DiffGAN-TTS is based on denoising
diffusion generative adversarial networks (GANs), which adopt an
adversarially-trained expressive model to approximate the denoising
distribution. We show with multi-speaker TTS experiments that DiffGAN-TTS can
generate high-fidelity speech samples within only 4 denoising steps. We present
an active shallow diffusion mechanism to further speed up inference. A
two-stage training scheme is proposed, with a basic TTS acoustic model trained
at stage one providing valuable prior information for a DDPM trained at stage
two. Our experiments show that DiffGAN-TTS can achieve high synthesis
performance with only 1 denoising step.

本文介绍了一种新的基于 Denoising Diffusion Generative Adversarial Networks 的文本到语音模型 (DiffGAN-TTS)，该模型通过多说话人 TTS 实验表明，仅需 4 个去噪步骤即可生成高保真度语音样本，并提出了一个两阶段训练方案，可在仅 1 个去噪步骤下实现高质量的语音合成性能。