Generative adversarial networks (GANs) have been indicated their superiority in usage of the real-time speech synthesis. Nevertheless, most of them make use of deep convolutional layers as their backbone, which may cause the absence of previous signal information. However, the generation of speech signals invariably require preceding waveform samples in its reconstruction, as the lack of this can lead to artifacts in generated speech. To address this conflict, in this paper, we propose an improved model: a post auto-regressive (AR) GAN vocoder with a self-attention layer, which merging self-attention in an AR loop. It will not participate in inference, but can assist the generator to learn temporal dependencies within frames in training. Furthermore, an ablation study was done to confirm the contribution of each part. Systematic experiments show that our model leads to a consistent improvement on both objective and subjective evaluation performance.

翻译：生成对抗网络（GANs）已在实时语音合成中展现出优越性。然而，多数GANs采用深度卷积层作为主干网络，这可能导致先前信号信息的缺失。然而，语音信号的生成始终需要先前的波形样本来进行重建，缺乏这些信息会导致生成语音中出现伪影。为解决这一矛盾，本文提出一种改进模型：带有自注意力层的后自回归（AR）GAN声码器，该模型在AR循环中融合了自注意力机制。该模块不参与推理过程，但可在训练中辅助生成器学习帧间时间依赖性。此外，我们通过消融研究验证了各组成部分的贡献。系统性实验表明，本模型在客观和主观评估性能上均呈现出一致性提升。