Hi srilm users,<br><br>Now I'm using the 'lattice-tool' to rescore the lattice, my goal is using a Factor Language Model(FLM) score to replace the original language model score in the word lattice.<br><br>1) First in the baseline system, I used conventional Bigram LM to do speech recognition and generate the htk word lattice (we name it "Lattice_1"). Then I try to use a conventional Trigram LM to rescore the "Lattice_1", using:<br>
<br> "lattice-tool -in-lattice Lattice_1 -unk -vocab [voc_file] -read-htk -no-nulls -no-htk-nulls -lm [Trigram_file] -htk-lmscale 15 -htk-logbase 2.71828183 -posterior-scale 15 -write-htk -out-lattice Lattice_2"<br>
<br>I just want to use the new Trigram LM score to replace the old LM score in "Lattice_1", so I think "Lattice_2" and "Lattice_1" should have the same size, just each word's LM score will be different. But I found the size of "Lattice_2" are larger than "Latttice_1". Did I miss something? How can I only replace the LM score without expanding the size of the lattice?<br>
<br><br><br>2) I used a Trigram in FLM format to rescore "Lattice_1":<br><br> First I converted all word nodes (HTk format) to FLM representation;<br><br> Then rescored with:<br><br> "
lattice-tool -in-lattice Lattice_1 -unk -vocab [voc_file] -read-htk -no-nulls
-no-htk-nulls -factored -lm [FLM_specification_file] -htk-lmscale
15 -htk-logbase 2.71828183 -posterior-scale 15 -write-htk
-out-lattice Lattice_3"<br><br> I think "Lattice_2" and "Lattice_3" should be the same, since the perplexity of using Trigram and using Trigram in FLM format are same. However, they are different. Did I miss something?<br>
<br><br><br> 3) Also I checked the accuracy from the decoding result of using "Lattice_2" and "Lattice_3", the result are:<br><br> viterbi decode result is the same;<br> n-best list are almost same, but using "Lattice_2" is better than using "Lattice_3";<br>
posterior decode result is quite different, using "Lattice_2" is better than using "Lattice_3";<br><br> Did I miss something when I using FLM to rescore the lattice?<br><br><br>
<br>Thank you very much!<br>Yuan<br>