Hi All,

I have Julius working with the the example Task Grammar (grammar and voca files).  What is the best way to set up Julius to recognize isolated words as accurately as possible? 

I don't need continuous speech, just one word at a time as accurately as possible, but I would like as many recognizable words as possible. 

Do I still need to make a .grammar and .voca file and convert them to .dfa and .dict using mkdfa.pl script?

I have tried using the -w dict option with the Voxforge dict file but I get a lot of errors:

Error: voca_load_wordlist: the line content was: ZUE             [ZUE]           z uw sp
Error: voca_load_wordlist: line 4194: logical phone "silB" not found
Error: voca_load_wordlist: line 4194: logical phone "ix-k+sp" not found
Error: voca_load_wordlist: line 4194: logical phone "k-sp" not found
Error: voca_load_wordlist: line 4194: logical phone "silE" not found
Error: voca_load_wordlist: the line content was: ZURICH          [ZURICH]        z uh r ix k sp
Error: voca_load_htkdict: begin missing phones
Error: voca_load_htkdict:
Error: voca_load_htkdict: aa-b+sp
Error: voca_load_htkdict: aa-ch+sp

I don't understand what the man page says about this:

-wsil  head_sil_model_name tail_sil_model_name sil_context_name

Any help or advice is greatly appreciated.

Thanks,

F

--- (Edited on 2/6/2009 11:01 pm [GMT-0600] by slidgey) ---