what's the difference from this paper?

[xinqipony]

Hey Rui Shu,
I really learn lots from your post, recently I read a candidate paper for ICLR 2019:
https://openreview.net/pdf?id=rygkk305YQ

'HIERARCHICAL GENERATIVE MODELING FOR
CONTROLLABLE SPEECH SYNTHESIS

which use GMVAE too, I compared it to yours in gmvae.py, what's in the paper is quite confusing for get y from sampled z, have you ever read it too?

[RuiShu]

Thanks for sharing the link. Unfortunately I haven't read that paper. There are a number of ways to implement GMVAE, so it's hard to say a priori what's the best way :-) I'll check out the paper later!