This paper describes Tacotron 2, a neural network architecture for speech synthesis directly from text. The system is composed of a recurrent sequence-to-sequence feature prediction network that maps character embeddings to mel-scale spectrograms, followed by a modified WaveNet model acting as a vocoder to synthesize timedomain waveforms from those spectrograms. Our model achieves a mean opinion score (MOS) of 4.53 comparable to a MOS of 4.58 for professionally recorded speech. To validate our design choices, we present ablation studies of key components of our system and evaluate the impact of using mel spectrograms as the input to WaveNet instead of linguistic, duration, and F0 features. We further demonstrate that using a compact acoustic intermediate representation enables significant simplification of the WaveNet architecture.

该论文阐述了 Tacotron 2 的神经网络框架，该框架可以从文本中直接合成语音，其系统由一种递归的序列到序列的特征预测网络和一个修改的 WaveNet 模型组成，能够实现与专业录制的语音相当的平均意见分数 (MOS)。

通过在Mel频谱预测上调节WaveNet，进行自然语音合成