Re: [Kaldi-users] How to improve the performance by adjusting Kaldi decoding parameters

[Mailing l. u. f. U. C. a. U. <kal...@li...>]

I don't like having word insertion penalties, as it's one more
parameter to tune and as far as I know it doesn't buy you much-- this
is why it's not directly supported.  An easy way to do it would be to
use fstprint and fstcompile to convert HCLG.fst to text and back, and
use an awk script to, whenever you see that there is a word label
(output symbol is nonzero), add a constant to the cost (the last field
on the line).
Dan

> Hi, Dan
>       I do appreciate your direction.
>       Could you tell me how to setup word insertion penalty in
> gmm-decode-faster?
>
>
> Best regards,
>
> hlwang
>
>
> At 2012-04-20 10:46:19,"Mailing list used for User Communication and Updates" <kal...@li...> wrote:
>>>        I am going to compare the decoding  performance using difference
>>> parameters by Kaldi.
>>
>>That's great!
>>
>>>        I have got some results, but I can't obtain an exact conclusion.
>>>        1) What is the biggest difference between  gmm-decode-faster and
>>> gmm-decode-kaldi? gmm-decode-kaldi can generate lattice, whilst
>>> gmm-decode-faster can't. I found the performances of gmm-decode-faster and
>>> gmm-decode-kaldi are almost same.
>>
>>I think you mean the other way round, no?  Anyway the normal method to
>>do lattice
>>generation is gmm-latgen-faster, which is derived from
>>gmm-decode-faster.  gmm-decode-kaldi was
>>intended to be a highly optimized decoder, but in the end some of
>>those optimization techniques did
>>not work as well as we had hoped.
>>
>>>        2) How do the decoding parameters of  gmm-decode-faster effect the
>>> performance? I found the acoustic-scale can obviously effect the
>>> performance, but other parameters almost have no effect.  In general,
>>> max-active=16000, beam=16.0, is the best one.
>>
>>I would be cautious about saying that something is the best one.
>>Surely it depends
>>what point in the speed/accuracy tradeoff you want.
>>
>>>        3) The beam in gmm-decode-faster is difference with that in Hvite in
>>> the scale.  How to adjust the beam to get an optimal result.
>>
>>The difference is the acoustic scale.  The beam divided by the
>>acoustic scale should be
>>comparable to a HVite beam.
>>
>>>        4) How to optimize the generated WFST to improve decoding
>>> performance? What are the  important matters needing to pay attention in
>>> composition, determination and minimization operations in Kaldi's WFST
>>> generation?
>>
>>This is a very big subject.  There are many methods.
>>One is simply using a smaller WFST by using a smaller
>>language model, and then rescoring with a larger one.  There are two paths here:
>>either do lattice rescoring, or use the "biglm" decoder.  I would
>>appreciate it if you could
>>find out which approach is faster, as I have not had time.  In
>>general, I think such
>>experiments should take the form of generating speed/accuracy curves
>>and seeing which
>>curve lies above or below the other.
>>
>>Search for "hbka.pdf" and read it, to learn the general principles and
>>theory of WFSTs-- although
>>that is a rather technical presentation.
>>
>>Dan
>>
>>
>>> hlwang
>>>
>>>
>>>
>>> ------------------------------------------------------------------------------
>>> For Developers, A Lot Can Happen In A Second.
>>> Boundary is the first to Know...and Tell You.
>>> Monitor Your Applications in Ultra-Fine Resolution. Try it FREE!
>>> http://p.sf.net/sfu/Boundary-d2dvs2
>>> _______________________________________________
>>> Kaldi-users mailing list
>>> Kal...@li...
>>> https://lists.sourceforge.net/lists/listinfo/kaldi-users
>>>
>>
>>------------------------------------------------------------------------------
>>For Developers, A Lot Can Happen In A Second.
>>Boundary is the first to Know...and Tell You.
>>Monitor Your Applications in Ultra-Fine Resolution. Try it FREE!
>>http://p.sf.net/sfu/Boundary-d2dvs2
>>_______________________________________________
>>Kaldi-users mailing list
>>Kal...@li...
>>https://lists.sourceforge.net/lists/listinfo/kaldi-users
>
>
>
> ________________________________
> 网易Lofter，专注兴趣，分享创作！
> ------------------------------------------------------------------------------
> For Developers, A Lot Can Happen In A Second.
> Boundary is the first to Know...and Tell You.
> Monitor Your Applications in Ultra-Fine Resolution. Try it FREE!
> http://p.sf.net/sfu/Boundary-d2dvs2
>
> _______________________________________________
> Kaldi-users mailing list
> Kal...@li...
> https://lists.sourceforge.net/lists/listinfo/kaldi-users
>