[hts-users:00767] Re: Questions on training and flat pitch pattern
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.
About pitch training my opinion is that proper high-level intonation
markup like ToBI is much more important. Although generalized variation
was also mentioned as a possible improvement.
- Follow-Ups
-
- [hts-users:00769] Re: Questions on training and flat pitch pattern, Alexander Gutkin
- References
-
- [hts-users:00764] Questions on training and flat pitch pattern, Lee Sillon
- [hts-users:00765] Re: Questions on training and flat pitch pattern, Heiga ZEN (Byung Ha CHUN)
- [hts-users:00766] Re: Questions on training and flat pitch pattern, Junichi Yamagishi