[hts-users:00354] about " decision trees"
- Subject: [hts-users:00354] about " decision trees"
- From: "lei liu" <wenshiliu@xxxxxxxxx>
- Date: Wed, 28 Jun 2006 16:45:45 +0800
- Domainkey-signature: a=rsa-sha1; q=dns; c=nofws; s=beta; d=gmail.com; h=received:message-id:date:from:to:subject:mime-version:content-type; b=fykIeVbOo9/pwJTA6/FSWUjkc46fFY59p3HfjCZxISQNCfzdDbq4xWXVbIlWXJA85teGxRkbao0lari6Mjs6iPGKvE6ox+GtJ5heHxOF+lMRasR7wq4YRL+QHGP9s0YQM6b3bUJ3shGWPlBmhvYaV65HSZTWcm99nucglydYTzQ=
Hi,
I have read the " tree-dur.inf" ,"tree-lf0.inf" ," tree-mcep.inf" in the " HTS voices for Festival" .
and I found there is only one tree for duratoin ( state 2) ,
but for f0 and mcep , there are 5 trees (state 2 ,3 4, 5, 6 ) .
why?
-----------------------
in the "inf " file, the tree is as followed:
pau[2]
{
-1 Pos_C-Syl_in_C-Phrase(Bw)==1 -2 -9
}
-1 is the index of the node ,
-2 is the index of node->yes
-9 is the index of node-> no
why the index are all the negative?
------------------------------------------
There is only one tree for every state in the "inf" file.
does it mean the tree is used by all the phoneme.
for example ,
the phoneme 'a' , 'b' , 'c'.
the second states of 'a' ,'b','c' are used to generate the tree of state 2 in the "tree-mcep.inf",
and then they use the same tree to generate voice.
before i read the "inf" file ,
I thought that there is a tree for one phoneme.
for example
the phoneme ' b - a+ c ' ' a - a+ c ' ' b - a+ a ' ................. ,
the second states of them are use to generate the tree for phoneme a ' s state 2
and also
' a -b+ c' ' a -b+ b' ...................
there is a tree for them.
-------------------
Best regards
- Follow-Ups
-
- [hts-users:00355] Re: about " decision trees", Heiga ZEN (Byung Ha CHUN)
- [hts-users:00356] Re: about " decision trees", Nicholas Volk