[hts-users:01344] Re: Questions: tieing the duration of 'sil' and variance flooring

[Junichi Yamagishi <jyamagis@xxxxxxxxxxxx>]

Why do you send the same mail several times?

Did you read Simon and Nicholas's answers?
Their answers are correct.

Anyway, read HTK Book first before you ask us.
Both answers are written in chapter 10.3 and 17.7.


On 2008/04/19, at 3:53, HE Qiang wrote:

> Hi, all:
>
> I trained a system with HTS, and find that there are a lot of  
> duration models for states of 'sil', this waste many tree nodes and  
> pdfs to store them. This is
> because my wav files has silence parts in the begining and ending,  
> and the length are variable. Obviously, making complicated silence  
> duration model is useless.
>
> So I want to tie the states of 'sil', making the duration fixed.  
> But I'm not familiar with HTK, could anyone give me a hint how and  
> where to write the hhed command?
>
> Another question: I want to limit the variance floor for the mgc,  
> for example to 1e-4, how could I do this? Although the config.pm  
> file has variance limit
> statement:
>   %vflr=('mgc'=>"0.01",...
> the trained pdf for mgc still has small variances:
> 0.000236, 0.000629, 0.000187...
>
> Thanks


--
The University of Edinburgh is a charitable body, registered in
Scotland, with registration number SC005336.