[hts-users:00194] Re: diffrences between merge and cat

[刘 磊 <liulei_198216@xxxxxxxxxxx>]

hi,
Heiga ZEN

I greatly appreciate your and sangjin kim's help.

I have known the process of sythesizing speech as follow,

1.HTS voice which contains hts_engine  is  registered  by 
\festvox\cstr_us_ked_timit_hts.scm
 that file tells festival where is the hts voice 

 for example 
 the following command change the current voice :
 festival > (voice_cstr_us_ked_timit_hts)

2.\festvox\cstr_us_ked_timit_hts.scm  loads \hts\hts.scm ,
 \hts\hts.scm calls  \hts\htsvoice.pl which uses hts_engine to synthesize 
speech.

3.\hts\hts.scm also defines some variables by which we can modify speech 
feature, 
 such as f0.


 In the \hts\htsvoice.pl , I have found that hts_engine synthesizes speech 

 using .pdf   fles,
 does the hts_engine have the function of generating parameters from .pdf 
files or 
 the .pdf files are already the parameters format which can be used to 
synthesize speech.

 In the \festvox director
 there are some other files except cstr_us_ked_timit_hts.scm 
 such as

 cstr_us_ked_timit_hts_phoneset.scm
 cstr_us_ked_timit_hts_tokenizer.scm
 cstr_us_ked_timit_hts_tagger.scm
 cstr_us_ked_timit_hts_lexicon.scm
 cstr_us_ked_timit_hts_phrasing.scm
 cstr_us_ked_timit_hts_intonation.scm
 cstr_us_ked_timit_hts_duration.scm
 cstr_us_ked_timit_hts_f0model.scm
 cstr_us_ked_timit_hts_other.scm

 I have not found their effects in the process of synthesizing speech.
 Why the demo of "HTS voices for fetival"  provides them?

Regards,
liulei



> From: "Heiga ZEN (Byung Ha CHUN)" <zen@xxxxxxxxxxxxxxxx>
> Reply-To: hts-users@xxxxxxxxxxxxxxxxxxxxxxxxx
> To: hts-users@xxxxxxxxxxxxxxxxxxxxxxxxx
> Subject: [hts-users:00193] Re: diffrences between merge and cat
> Date: Wed, 11 Jan 2006 02:45:15 +0900
>
> Hi,
>
> liulei_198216@xxxxxxxxxxx wrote:
>
> > But  I puzzle how festival works together with hts_engine.
> >
> > I have read the "perl script" and found that hts_engine gets .lab 
> > files from /tmp/tmp.lab to systhsize speech.
> >
> > when we use "festival"  to input text from command line ,we will 
> > get real-time speech.
> > My question is
> > How does the festival  trigger  hts_engine to systhsiz speech  
> > after  .lab files are generated from festival?
> >
> > I have also read festival manul and found it systhsize speech 
> > through concatenating units,
> > but how does the hts_engine work with festival?
>
> 1. Festival extracts utterance information from an input text.
> 2. The uttrance information is saved as "utt.feats" on working 
> directory.
> 3. Festival calls htsvoice.pl.
> 4. In htsvoice.pl, the utterance information is converted to 
> corresponding context-dependent label sequence.
> 5. hts_engine is called from htsvoice.pl.
> 6. A waveform is synthesized and saved in raw audio format.
> 7. RIFF header is appended to raw audio by sox.
> 8. Resultant wav file is loaded by festival,
>
> Please see hts.scm included in our hts voices.
>
> In the next festival release (2.0?), hts_engine will be integrated 
> as a function of the festival.
>
> Regards,
>
> Heiga Zen (Byung Ha CHUN)
>
> --
>  ------------------------------------------------
>   Heiga ZEN     (in Japanese pronunciation)
>   Byung Ha CHUN (in Korean pronunciation)
>
>   Department of Computer Science and Engineering
>   Graduate School of Engineering
>   Nagoya Institute of Technology
>   Japan
>
>   e-mail: zen@xxxxxxxxxxxxxxxx
>      web: http://kt-lab.ics.nitech.ac.jp/~zen
>  ------------------------------------------------

_________________________________________________________________
与联机的朋友进行交流，请使用 MSN Messenger:  http://messenger.msn.com/cn