What is the main idea of global conditioning?

[littleTwelve]

Now, I want to reference the implement of global conditioning in your code to edit my wavenet code in order to implement multi-speakers. But after reading your code, I am still confused about what is the main idea of global conditioning?
Let me show you how I think of it and please point out where I am wrong or give me some suggestions or guidance.
For instance, I have a data set containing 100 training samples and the length of each training sample is 2000. This data set has 4 types of samples and the labels are 0, 1, 2, 3. Now, I want to form an input vector with labels. After one-hot coding, the size of data set is 100x256x2000 (mu=256). Then after one-hot coding, the size of label of total training samples is 100x256x1. Finally, the input vector I want is is 100x256x2001, which means I should add the label vector in the form of one-hot to the end of the data set vector in the form of one-hot.

Am I right?

[littleTwelve]

Can someone help me figure out the question?

[Deleted user]

I am interested in this explanation too, because I don't understand it either.