[SRILM User List] Computing nbest-error rate from HTK MLF files

[E]

Thanks for the response Andreas.

I will share my script once its ready. 


This "oracle" WER seems like a very crude way of computing nbest-error to me. Suppose a reference word is located in [0,  1] seconds, one can look at all the alternatives in the nbest list (all words that significantly overlap with reference word) and choose the word that best matches. 


So basically one will extract "most accurate" segments from each nbest hypothesis in order to get a new "oracle" hypothesis.


Do you know if people have done that kind of thing while computing nbest error?


Thanks,
Ethan
-------------- next part --------------
An HTML attachment was scrubbed...
URL: <http://www.speech.sri.com/pipermail/srilm-user/attachments/20130424/650642f8/attachment.html>