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

[hts-users:02497] Re: using of HVite


Hi,

no I haven't touched the transfer matrix. I've forgotten that
monophones'models are in HSMMs. I will try Simon King solution and then
post after.

Thanks for the help

Sebastien

Le vendredi 28 mai 2010 à 23:16 +0800, 康世胤 a écrit :
> Have you tried to modify the transfer matrix for each model in
> monophone.mmf ?
> 
> 
> 2010/5/28 Sébastien Le Maguer <Sebastien.Le_maguer@xxxxxxxx>
>         Hi Mero,
>         
>         thanks for this answer. Unfortunately, I've got the same
>         problem with
>         the corrected dictionnary. Could it be because I'm trying to
>         aligning
>         monophone ?
>         
>         
>         Sebastien
>         
>         Le vendredi 28 mai 2010 à 07:53 -0700, meron a écrit :
>         
>         > the mono dict needs to have each phoneme twice per line
>         >
>         > e.g. :
>         >
>         > ah    ah
>         > m     m
>         >
>         > etc.
>         >
>         > Cheers
>         > meron
>         >
>         >
>         > --- On Fri, 5/28/10, Sébastien Le Maguer
>         > <Sebastien.Le_maguer@xxxxxxxx> wrote:
>         >
>         >         From: Sébastien Le Maguer
>         <Sebastien.Le_maguer@xxxxxxxx>
>         >         Subject: [hts-users:02492] using of HVite
>         >         To: hts-users@xxxxxxxxxxxxxxx
>         >         Date: Friday, May 28, 2010, 7:47 AM
>         >
>         >         Hi,
>         >
>         >         I've got a problem with HVite. It always returns "No
>         tokens
>         >         survived to final node of network". I would like to
>         find how
>         >         monophones are aligned.
>         >
>         >         I used this command :
>         >
>         >         ./../tools/bin/HVite -A -B -C configs/trn.cnf -D -y
>         lab -T 1
>         >         -o SW -f -a -H models/qst001/ver1/cmp/monophone.mmf
>         -I
>         >         data/labels/mono.mlf -i test/gen_align.mlf -S
>         >         data/scp/train.scp data/dict/mono.dict
>         data/lists/mono.list
>         >
>         >         mono.dict contains the same things that mono.list
>         and all
>         >         other files are generated from the HTS 2.1 demo (For
>         the
>         >         moment, I'm using HTS 2.1).
>         >
>         >         Here are samples of the messages I have:
>         >
>         >         Aligning File:
>         >         <...>/demo/base/data/cmp/cmu_us_arctic_slt_b0538.cmp
>         >         Created lattice with 31 nodes / 30 arcs from label
>         file
>         >         No tokens survived to final node of network
>         >         Aligning File:
>         >         <...>/demo/base/data/cmp/cmu_us_arctic_slt_b0539.cmp
>         >         Created lattice with 32 nodes / 31 arcs from label
>         file
>         >         No tokens survived to final node of network
>         >
>         >         I think I'm misunderstanding something.
>         >
>         >         Thanks
>         >         Sebastien
>         >
>         
>         
>         
>         
>         
> 
> 
> 
> -- 
> 康世胤
> Shiyin Kang
> 
> kangshiyin@xxxxxxxxx
> Mobile: +86-13810352340
> Tel: +86-10-62775251
> 
> FIT 3-522
> Lab of Human-Computer Speech Interaction,
> Department of Computer Science & Technology,
> Tsinghua University, Beijing, 100084, P.R.China



References
[hts-users:02493] Re: using of HVite, meron
[hts-users:02494] Re: using of HVite, Sébastien Le Maguer
[hts-users:02496] Re: using of HVite, 康世胤