keonlee9420/styler

Official repository of STYLER: Style Factor Modeling with Rapidity and Robustness via Speech Decomposition for Expressive and Controllable Neural Text to Speech, INTERSPEECH 2021

styler's Issues

pre-trained model

can you share pre-trained model?
thx a lot

Low resource languages that won't work with MFA?

Is there a way to fine tune a model or training two languages side by side such that a very low resource language can be trained with the voices of a high resource language?

Undefined names

Hi, I noticed some undefined names around the code:

synthesize.py:495:67: F821 undefined name 'reference'
noise_mixer_refs.py:56:42: F821 undefined name 'eps'
noise_mixer_refs.py:59:40: F821 undefined name 'eps'

some questions about figures

Thanks for sharing the code of interesting work!

Which part of the code should I check to make following figures (F0 contours, female vs male)?

About the pre-process

Hi, I want to ask the trimming operation whether is very important for training your model? Furthermore, can you share the scripts to trimming VCTK dataset?

some questions

1.in paper, why output of encoder （text_encoding) upsample and downsample?
2. what is the meaning of text_encoding_neck+pitch_encoding、text_encoding_neck+energy_encoding？
why not cat？