[hts-users:01602] Re: GV causes clipping

[Leon Zhang <leonzh@xxxxxxxxxxxxx>]

I am interesting at the voice quality improvement by GV, who can tell me your observation? I am using lsp to build HTS system, is GV able to improve voice quality too?

-----Original Message-----
From: Heiga ZEN (Byung Ha CHUN) [mailto:heiga.zen@xxxxxxxxxxxxxxxxx]
Sent: Wednesday, July 30, 2008 9:33 PM
To: hts-users@xxxxxxxxxxxxxxx
Subject: [hts-users:01589] Re: GV causes clipping

Hi,

Geoffrey Wilfart wrote:

> I had something similar, and noticed that, at least under Unix, when you
> cast an out-of-(short) range double to a short, it systematically gets
> -32768 as a value.
>
> I did fix this by normalizing the sample values before casting them to
> shorts.

It's one of the possible solutions but we have to finish synthesizing
before playing speech.  It causes long delay and it is a critical
problem on some applications.

Personally I think that reducing the GV factor (as Nicholas mentioned)
is a reasonable solution for this problem.

Best regards,

Heiga ZEN (Byung Ha CHUN)

--
Heiga ZEN (Byung Ha CHUN)
Speech Technology Group
Cambridge Research Lab
Toshiba Research Europe
phone: +44 1223 436975

______________________________________________________________________
This email has been scanned by the MessageLabs Email Security System.
For more information please visit http://www.messagelabs.com/email
______________________________________________________________________