Recently there has been a lot of interest in non-autoregressive (non-AR)
models for speech synthesis, such as FastSpeech 2 and diffusion models. Unlike
AR models, these models do not have autoregressive dependencies among outputs
which makes inference efficient. This paper expands the range of available
non-AR models with another member called energy-based models (EBMs). The paper
describes how noise contrastive estimation, which relies on the comparison
between positive and negative samples, can be used to train EBMs. It proposes a
number of strategies for generating effective negative samples, including using
high-performing AR models. It also describes how sampling from EBMs can be
performed using Langevin Markov Chain Monte-Carlo (MCMC). The use of Langevin
MCMC enables to draw connections between EBMs and currently popular diffusion
models. Experiments on LJSpeech dataset show that the proposed approach offers
improvements over Tacotron 2.

这篇论文描述了如何使用基于能量的模型（EBMs）通过噪声对比估计训练，并通过 Langevin Markov Chain Monte-Carlo（MCMC）进行采样，从而扩展了非自回归模型在语音合成中的应用。在 LJSpeech 数据集上的实验证明，该方法在 Tacotron 2 上取得了一定改进。