[hts-users:00771] Re: Questions on training and flat pitch pattern

[Junichi Yamagishi <jyamagis@xxxxxxxxxxxx>]

Hi,

On 2007/08/07, at 22:22, Alexander Gutkin wrote:
> > > 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...

Yes. The HMMs are speaker-independent model. But, the clustering  
procedures
are the same as those of speaker-dependent model.

In addition to the speaker-independent models, I've trained several
speaker-dependent HMMs from about 1 hour to about 13 hours of speech  
data.
Then, I've heard that Dr.Zen and Dr.Toda utilized much larger speech  
corpora
for training speaker-dependent HMMs in the past.

In my opinion, synthetic speech generated from HMMs using more than 3  
hours of
speech data sounds very good. It's much better than that from 1 hour  
of speech data.

Thus I agree Dr.Zen's comments. I do not think that 500-1000  
sentences are enough at all.
My impression is reversely that
"As the number of training data increases, the quality of synthetic  
speech becomes better!"

Thanks,
Junichi