Hi,all
I have several questions about HTS CMU English TTS demo.
1.the mgc extraction is finished by SPTK tools.However, the total frame number of mgc is different from the f0 . why? I think they should keep exactly the same.
2. anyone can tell me how do snack split a utterance to several frames? why in the Makefile do we need to add a headfile(80points) and a tailfile(400points) to a pcm file.
3. In the f0 extraction file "getf0.tcl", only frameshift(80points) is set, what about the framelength, how do the snack tools set the framelength?
Fly