[hts-users:00551] Re: help in SPTK(Now HMGenS)
- Subject: [hts-users:00551] Re: help in SPTK(Now HMGenS)
- From: Mohammed Samir <msamirhb@xxxxxxxxx>
- Date: Tue, 6 Mar 2007 02:36:52 -0800 (PST)
- Domainkey-signature: a=rsa-sha1; q=dns; c=nofws; s=s1024; d=yahoo.com; h=Message-ID:X-YMail-OSG:Received:Date:From:Subject:To:In-Reply-To:MIME-Version:Content-Type:Content-Transfer-Encoding; b=CWqNODHRYrL31LGb+i+zXE6CVvmc8aca9SBipVKvW4jTVcQ7u0D23OpVr2FewRcfM6hhjeBemxmahpZWj7xMIblYYJ8c9UZOVtV87XDbAZzq9S9Su/iyFXBPzApzwKL/R4YLCwLrRFoK+VKg3EucBCae9ig9f1lVIYIuub3aZ0I= ;
--- "Heiga ZEN (Byung Ha CHUN)" <zen@xxxxxxxxxxxxxxxx>
wrote:
> Hi
>
> Mohammed Samir wrote:
>
> > I thought that I can generate parameters from
> state
> > duration pdf and then use mlsa filter to
> synthesize
> > .(thats all what I want for this single
> phoneme)can it
> > be done?
>
> If you are using mel-cepstral coefficients, yes.
> If you are using MFCC, no.
>
> > also in this experement I didn't use
> > dynamic feature
>
> In that case you will get sequences of mean vectors.
>
> > and if I want i think that I will add
> > this option in the config file input of HCopy.
>
> I don't recommend you to use HCopy.
> Use SPTK's mcep and window.pl included in the
> HTS-demo.
> Please refer demo for detail.
>
> Regards,
>
So I will use SPTK's mcep to generate mel-cepstral
coffcients. then how I will continue to produce HMM?
can I use this mcep(s) with HInit and HRest with -g
option of HTK?
____________________________________________________________________________________
Expecting? Get great news right away with email Auto-Check.
Try the Yahoo! Mail Beta.
http://advision.webevents.yahoo.com/mailbeta/newmail_tools.html
- Follow-Ups
-
- [hts-users:00552] Re: help in SPTK(Now HMGenS), Heiga ZEN (Byung Ha CHUN)
- References
-
- [hts-users:00550] Re: help in SPTK(Now HMGenS), Heiga ZEN (Byung Ha CHUN)