Dear all,
I am doing objective test between synthetic voice and natural voice. According to the thread:
http://hts.sp.nitech.ac.jp/hts-users/spool/2013/msg00122.html I knew about cdist and rmse and dtw. So, at fist I used dtw for time wraping and the result of dtw is one concatenated file. How can I split the file into 2 separated files to feed into cdist and rmse?
I very appreciate your helps.