Kun Zhou
> Hi Guys, > > first of all, thanks for sharing this great research. I have a question. Is it possible to offer a python "code" way to train /...
> @jxzhanggg is there any update on this? I'd like to use this as a baseline for other work (without needing to train from scratch) Hi I publish the pre-trained...
Hi, in this code, the speech duration is predeiced by the attention mechanism.
> Hi @jxzhanggg, > > I am trying to achieve Voice Conversion with this algorithm applied to prosody training. This means that I want to convert a reference audio (Speaker...
> @jucasansao Hi，did u try the algorithms and get perfect transformation of prosodic features of reference speakers? Now I'm try to do this work by this way. Hi, I did...
Hi Thanks for your questions! 1/ Yes the strenght_embedding is predicted by learned ranking function. 0- most weak; 1-most strong; 2/ Thanks a lot!! I have corrected the uppder bound...
Hey, it doesn't contain evaluation scripts.
I was using sprocket for mcd calculation: https://github.com/k2kobayashi/sprocket
> hello.could you tell me how to get these features.i will be appreciate.  Hey these features are deep features obtained from the last projection layer of a pre-trained SER...
Hi Josh! Thank you :) I will do it!