[SRILM User List] Does sausage-making use timing information?

Tim Kempton acp06tk at sheffield.ac.uk
Mon Mar 15 03:49:21 PDT 2010

>lattice-tool does in fact use a very different (and more efficient)
algorithm for sausage construction, and uses no time information, only the
topology of the lattice. However, the time stamps from the input lattice can
be carried over to the output sausage if the -acoustic-mesh option is used.
>> The reason I'm asking all this, is because I'd like to combine results 
>> from multiple recognizers. I like the nbest-rover approach but I'd 
>> like to make use of timing information too, partly because the output 
>> of the recognizers are very different. So I'm hoping I can combine 
>> multiple recognizer lattices (with -operation or), and then transform
this to a mesh.
>I guess I don't quite see how using times helps you in this case.  But the
procedure you suggest should work in principle.

Thanks for your reply Andreas

Yes I really like the -acoustic-mesh option for output timings.
Originally when I was looking at my mesh (a toy example constructed from two
heavily pruned lattices) I could see misalignments that could benefit from
timing information, however they could also benefit from the
-dictionary-align option, so I'll give that a go.


More information about the SRILM-User mailing list