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

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

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