[hts-users:00769] Re: Questions on training and flat pitch pattern

["Alexander Gutkin" <alexander.gutkin@xxxxxxxxx>]

On 8/7/07, Nickolay V. Shmyrev <nshmyrev@xxxxxxxxx> wrote:
> В Втр, 07/08/2007 в 16:59 +0100, Junichi Yamagishi пишет:
> > Hi,
> >
> > On 2007/08/07, at 16:45, Heiga ZEN (Byung Ha CHUN) wrote:
> >
> > > Lee Sillon wrote (2007/08/08 0:10):
> > >
> > >> 1. If the training corpus is larger (for example,10,000
> > >> sentences), the training process will crash because of memory
> > >> consuming(about 2GB). Could it be solved?
> > >
> > > I guess tree-based clustering (HHEd) consumes huge memory for
> > > larger training data. You can use low-memory implementation of tree-
> > > based clustering by specifying -r option.
> >
> > I've trained HMMs for HMM-based speech synthesis from 23,000 sentences.
>
> Oh, so much, how many hours is it? I don't believe it had manual
> segmentation :)
> Did you noticed any real improvement with so big database, for example
> Alan says that 500-1000 are enough.
>

    I assume this was used by Junichi was the adaptation work, i.e.
training the speaker-independent models. But, in general, I can't see
anything wrong with training on a large database - as long as you can
afford the resources... Probably there is no perfect recepy for the
optimal database size - it's too speaker and coverage-specific...