[hts-users:00757] Re: Problem on data preparation (building utterance file ".utt")

["Heiga ZEN (Byung Ha CHUN)" <zen@xxxxxxxxxxxxxxx>]

Hi,

ChungGu-hyung wrote (2007/08/01 16:02):

> I'm trying to make Korean speech synthesis system using HTS(also using Festival, SPTK, etc.) with Korean database.
> There are several data should be prepared for training (for example, 
> ".lab", ".raw", ".utt", ".win" files) and Utterance file(.utt) is one of them.
> I found I need six files to make Utterance file which are '.Segment', '.Syllable', '.Work', '.Phrase', '.IntEvent, '.Target'.

Actually current HTS framework does not use any information from .Target file.

> The problem is I got only '.Segment' and '.Phrase' files in my Korean database.
> So, here's my big question!
>  
> "When HTS uses utterance file during training, will it be possible (or 
> OK) to generate speech if I just build utterance file with only those 
> two files (.Segment and .Phrase)?"

Yes, but the quality of synthesized speech may become worse than that uses all of these five files.
Because you cannot use any information about syllables, words, and ToBI endtones to predict prosody (F0 and durations).

Regards,

Heiga ZEN (Byung Ha CHUN)

--
------------------------------------------------
Heiga ZEN     (in Japanese pronunciation)
Byung Ha CHUN (in Korean pronunciation)

Department of Computer Science and Engineering
Nagoya Institute of Technology
Gokiso-cho, Showa-ku, Nagoya 466-8555 Japan

http://www.sp.nitech.ac.jp/~zen
------------------------------------------------