Meaning of _o and _l in residual_encoder

deterministic-algorithms-lab / Cross-Lingual-Voice-Cloning

Tacotron 2 - PyTorch implementation with faster-than-realtime inference modified to enable cross lingual voice cloning.

BSD 3-Clause "New" or "Revised" License

358 stars 58 forks source link

Meaning of _o and _l in residual_encoder #5

Closed tshmak closed 4 years ago

tshmak commented 4 years ago

Hi @Jeevesh8 thanks a lot for your code!

I am trying to understand the paper more. Can you please clarify the meaning of the subscripts _o and _l in residual_encoder.py? I see that you are using two residual encoders and concatenating them, and they serve different purposes.

Thanks a lot!

Tim

Jeevesh8 commented 4 years ago

They mean observed and latent respectively @tshmak . You can read this paper .