[hts-users:01142] Re: HTS2.1beta-HVite
Hi;
As a follow-up to this thread:
If one wanted to align some unseen acoustic observations
with some HSMM states, would the conversion suggested
by Simon with the use of HVite be the best way to achieve this,
or would one have to hack HERest to export the affiliation
between the states and the cumulated frames with best occupancy,
or would there just be another better solution?
Thanks;
-*- Sacha K. -*-
Simon King wrote:
Heiga ZEN (Byung Ha CHUN) wrote:
You can use HVite of HTS-2.1beta with *HMMs*.
and it is straightforward to convert your HSMMs to HMMs. Here is my recipe:
- in your HSMM, there is a dummy transition matrix which is probably
shared by all models (this is what the HTS demo scripts do), so untie
it, then retie so it is shared between models for the same centre phone
(for example). Then, modify the transition matrices so they are the
usual band-diagonal form (self transition and forward transition for all
emitting states). Here is my .hed file for doing that using HHEd (models
with 5 emitting states):
TR 2
UT {*.transP}
TI T_aa {(*-aa+*).transP}
TI T_ae {(*-ae+*).transP}
TI T_ah {(*-ah+*).transP}
[... etc for all phones]
AT 2 2 0.9 {*.transP}
AT 2 3 0.1 {*.transP}
AT 3 3 0.9 {*.transP}
AT 3 4 0.1 {*.transP}
AT 4 4 0.9 {*.transP}
AT 4 5 0.1 {*.transP}
AT 5 5 0.9 {*.transP}
AT 5 6 0.1 {*.transP}
AT 6 6 0.9 {*.transP}
AT 6 7 0.1 {*.transP}
- next, train the transition matrices - do one or two rounds of EM. You
could tell HERest to only update the transition matrices (-u t) and
leave the Gaussians unchanged, if you want your HMMs to be as similar as
possible to your HSMMs
Simon
______________________________________________________________________
This email has been scanned by the MessageLabs Email Security System.
For more information please visit http://www.messagelabs.com/email
______________________________________________________________________
--
Dr.Sacha Krstulovic - Research Engineer
Toshiba Research Europe Limited
Cambridge Research Laboratory
Speech Technology Group
208 Science Park, Milton Road
Cambridge CB4 0GZ - United Kingdom
E-mail: sacha@xxxxxxxxxxxxxxxxx
______________________________________________________________________
This email has been scanned by the MessageLabs Email Security System.
For more information please visit http://www.messagelabs.com/email
______________________________________________________________________begin:vcard
fn:Sacha Krstulovic
n:Krstulovic;Sacha
org:Toshiba Research Europe Limited - Cambridge Research Laboratory;Speech Technology Group
adr:;;260 Science Park, Milton Road;Cambridge;;CB4 0WE;United Kingdom
email;internet:sacha@xxxxxxxxxxxxxxxxx
title:Research Engineer
tel;work:+44 1223 436 978
tel;fax:+44 1223 436 909
x-mozilla-html:FALSE
url:http://www.toshiba-europe.com/research/crl/
version:2.1
end:vcard
- Follow-Ups
-
- [hts-users:01143] Re: HTS2.1beta-HVite, Heiga ZEN (Byung Ha CHUN)
- References
-
- [hts-users:01135] HTS2.1beta-HVite, zhizheng wu
- [hts-users:01136] Re: HTS2.1beta-HVite, Heiga ZEN (Byung Ha CHUN)
- [hts-users:01137] Re: HTS2.1beta-HVite, zhizheng wu
- [hts-users:01138] Re: HTS2.1beta-HVite, Heiga ZEN (Byung Ha CHUN)
- [hts-users:01140] Re: HTS2.1beta-HVite, Heiga ZEN (Byung Ha CHUN)
- [hts-users:01141] Re: HTS2.1beta-HVite, Simon King