Does your generator provide any random noise as input? or it generates the same pose based on the same audio input? I'm working on a similar sequence generation project. I'm curious how you put the randomness into sequence.
In the current implementation we do not condition on any randomness. However, I believe it may be useful in future work, as for any particular speech sequence we believe there could be few possible gestures.
Hello Amir,
Does your generator provide any random noise as input? or it generates the same pose based on the same audio input? I'm working on a similar sequence generation project. I'm curious how you put the randomness into sequence.
Thanks.