MLSP-Project-fall17

Project Repo for Machine Learning and Signal Processing

This is an implementation of voice conversion based on GMMs, both Full Conversion and VQ Conversion are covered.

Before running the code, please download vcc2016_training dataset first

run the Voice Conversion:

python run_VC.py

Checkout the result in result/SF1_TM1_150 folder.

Name		Name	Last commit message	Last commit date
Latest commit History 48 Commits
MLSP_final_report		MLSP_final_report
__pycache__		__pycache__
features		features
midterm_report		midterm_report
model		model
proposal		proposal
result		result
vcc2016_training		vcc2016_training
.DS_Store		.DS_Store
.gitignore		.gitignore
README.md		README.md
alignment.py		alignment.py
alignment.pyc		alignment.pyc
evaluation.py		evaluation.py
f0_transform.py		f0_transform.py
features.py		features.py
gmm.py		gmm.py
run_VC.py		run_VC.py
source.wav		source.wav
synthesizer.py		synthesizer.py
target.wav		target.wav

Provide feedback