On Mon, 3 Sep 2012 09:04:22 +1000 (EST)
"Patrick Shirkey" <pshirkey(a)boosthardware.com> wrote:
On Mon, September 3, 2012 6:46 am, SxDx wrote:
----- Original Message -----
> From: "Patrick Shirkey" <pshirkey(a)boosthardware.com>
> To: linux-audio-user(a)lists.linuxaudio.org
> Sent: Saturday, September 1, 2012 11:25:26 PM
> Subject: [LAU] Synthesized voices [was :Re: [LAD] Kontakt sampler
format (and
others like EXS24)]
>
>
> On Sun, September 2, 2012 6:18 am, SxDx wrote:
> > ----- Original Message -----
> >> From: "Ralf Mardorf" <ralf.mardorf(a)alice-dsl.net>
> >> The East West Choirs sing your lyrics. It's not another Ahhhh or Ohhhh
> >> sample ;).
> >>
> >>
http://www.youtube.com/watch?v=aI5Gg2-mhmU
> >
> > any technical info on that? free software doing the same, research
papers
(easily available), anything?
As an aside, one possible way of dealing with this issue is to create your
own voices for applications like orca.
If you want a quick and easy way to get started with that process you can
run "AT Distro" in a virtual machine.
http://atdistro.com
thanks for pointing that out. I tried a bit, it's slow
in qemu (expected). But it seems orca uses espeak, and
the voice is not realistic.
You can create your own voices so the default voice should not be used as
the reference for a singing voice. Even then I was amazed by how close to
real it sounded for chanting emulation.
What we hear in the video
above is much more realistic and I wondered how they do
that. Seems it's not public knowledge.
TTS is a huge research area.
Some people are putting their work online.
http://gitorious.org/lauloid
Ah, lauloid. The beauty:
Still better than the free software song.
No, to be fair this from February, the project was created 31. January 2012 on Gitorious.
There is an audio sample in the git which has a horrible mix but it magnitudes better than
the youtube video here.
I'm going to trying to compile that now, there are many different parts in the git
repository. But it seems there is zero documentation.
Nils