原paper
https://arxiv.org/pdf/1609.03499.pdf

关键的句子：

1. At training time, the conditional predictions for all timesteps can be made in parallel because all timesteps of ground truth x are known. When generating with the model, the predictions are sequential: after each sample is predicted, it is fed back into the network to predict the next sample.

2. Temporal Convolution.

总结：
WaveNet中蕴含的causal卷积的哲学，最实用（或者说只适用的）场景就是text-to-speech。而像多步时间序列预测这种场景，原始的不用causual卷积，普通的CNN也是可以做到的。