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

[hts-users:01991] Re: HVite in HTS-SLT-demo

Did your *.lab files follow the correct format? At least the following format works for manually specifying a duration for each state:

start time    end time    .state[state number]    full-context label

For instance,

0000000 1100000 .state[2] x-SIL+h
1100000 2250000 .state[3] x-SIL+h
2250000 3000000 .state[4] x-SIL+h
3000000 4400000 .state[5] x-SIL+h
4400000 4650000 .state[6] x-SIL+h
4650000 4850000 .state[2] SIL-h+iy
4850000 5050000 .state[3] SIL-h+iy
5050000 5350000 .state[4] SIL-h+iy
5350000 5450000 .state[5] SIL-h+iy
5450000 5550000 .state[6] SIL-h+iy

Hui LIANG (Tienshyang)

--- On Sun, 24/5/09, Udhyakumar N <udhay@xxxxxxx> wrote:

> From: Udhyakumar N <udhay@xxxxxxx>
> Subject: [hts-users:01987] Re: HVite in HTS-SLT-demo
> To: hts-users@xxxxxxxxxxxxxxxx
> Date: Sunday, 24 May, 2009, 12:07 AM
> I didnt realize the HTS-SLT-Demo trained HSMMs instead of HMMs. I
> tweaked the transition probabilities (as Simon King suggested) and
> the HVite alignment works fine now. I dumped all the state-level
> alignments to the label files and used them in HMGenS with -s option.
> HMGenS crashed with "segmentation fault" error.
> I am running HTS on 64-bit fedora 7. Here is the actual
> command and output (I omitted all the duration info as the
> state-alignments in lab files are used for duration).