This paper introduces an improved duration informed attention neural network (DurIAN-E) for expressive and high-fidelity text-to-speech (TTS) synthesis. Inherited from the original DurIAN model, an auto-regressive model structure in which the alignments between the input linguistic information and the output acoustic features are inferred from a duration model is adopted. Meanwhile the proposed DurIAN-E utilizes multiple stacked SwishRNN-based Transformer blocks as linguistic encoders. Style-Adaptive Instance Normalization (SAIN) layers are exploited into frame-level encoders to improve the modeling ability of expressiveness. A denoiser incorporating both denoising diffusion probabilistic model (DDPM) for mel-spectrograms and SAIN modules is conducted to further improve the synthetic speech quality and expressiveness. Experimental results prove that the proposed expressive TTS model in this paper can achieve better performance than the state-of-the-art approaches in both subjective mean opinion score (MOS) and preference tests.

翻译：本文提出了一种改进的时长感知注意力神经网络（DurIAN-E），用于表现力强且高保真的文本到语音合成。该模型继承自原始DurIAN模型，采用自回归模型结构，其中输入语言信息与输出声学特征之间的对齐关系通过时长模型推断得出。同时，所提出的DurIAN-E利用多个堆叠的基于SwishRNN的Transformer块作为语言编码器。在帧级编码器中引入风格自适应实例归一化层以提升表现力建模能力；还构建了结合去噪扩散概率模型（用于梅尔频谱图）与SAIN模块的去噪器，进一步提高合成语音的质量和表现力。实验结果表明，本文提出的表现力TTS模型在主观平均意见分和偏好测试中均能取得优于现有先进方法的性能。