- first, put all your wav files in wav dir;
- second, go to extract_features dir and extract features;
- third, go to copy_synthesis dir and validate your features using copy synthesis;
- (option)fourth, go to make_cmp dir and composite your features to cmp files (for nn training);
- (option)fifth, move your binary label here and make frame-aligned prepared_label and prepared_cmp(for nn training);
charlottecuc / extract_features_using_world Goto Github PK
View Code? Open in Web Editor NEWThis project forked from syang1993/extract_features_using_world
using world vocoder to extract features and make data for training neural networks