Disentangled Speaker Representations in Neural Text-to-Speech Synthesis

Based on Facebook's Voiceloop model.

I use four architectures:

Name		Name	Last commit message	Last commit date
Latest commit History 206 Commits
docs		docs
img		img
notebooks		notebooks
scripts		scripts
training_logs		training_logs
.gitignore		.gitignore
LICENSE		LICENSE
README.md		README.md
README_VoiceLoop.md		README_VoiceLoop.md
data.py		data.py
dtw.py		dtw.py
eval_curves.py		eval_curves.py
eval_mcd.py		eval_mcd.py
evaluate_loss_func_for_notebook.py		evaluate_loss_func_for_notebook.py
generate.py		generate.py
model.py		model.py
notebook_utils.py		notebook_utils.py
speaker_recognition.py		speaker_recognition.py
train.py		train.py
training_monitor.py		training_monitor.py
utils.py		utils.py

RichardSterry/msc-project