[Subject Prev][Subject Next][Thread Prev][Thread Next][Date Index][Thread Index]

[hts-users:03331] Re: About the Monophone Models


On 6 Jun 2012, at 10:22, Simon King wrote:

> because there are no trainable transition parameters in this model topology

of course the other explanation could be that you have an explicit duration model (HSMM) and therefore the transition matrix is not meaningful - you didn't specify whether you're using HMMs or HSMMs

Simon


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


Follow-Ups
[hts-users:03332] Re: About the Monophone Models, Kwan Lisa
References
[hts-users:03329] About the Monophone Models, Kwan Lisa
[hts-users:03330] Re: About the Monophone Models, Simon King