fragment size = 1024 bytes (32 msec)
finished
- Gram #0: read
[grammars]
  # 0: [active     ]    8 words,   4 categories,    5 nodes (new)
- Grammar update check
- Gram #0: installed
- update completed
[grammars]
  # 0: [active     ]    8 words,   4 categories,    5 nodes
  Grobal:               8 words,   4 categories,    5 nodes
------------- System Info begin -------------
Julian rev.3.4.2 (fast)

Files:
    hmmfilename=onomatope/../model/phone_m/hmmdefs_ptm_gid.binhmm
    hmmmapfilename=onomatope/../model/phone_m/logicalTri
    vocabulary filename=onomatope/onomatope.dict
    DFA grammar filename=onomatope/onomatope.dfa

Acoustic analysis condition:
	   sample period =  625 ns      (16000 Hz)
	     window size =  400 samples (25.0 ms)
	     frame shift =  160 samples (10.0 ms)
	    delta window =    2 frames  (20.0 ms) around
	        hi freq. = OFF
	        lo freq. = OFF
	  energy measure = (_E) log energy
    spectral subtraction = off

HMM Info:
    7946 models, 3131 states, 8256 mixtures are defined
	      model type = tied-mixture, context dependency handling ON
	    codebook num = 129
	max codebook size= 0
      training parameter = MFCC_E_N_D_Z
	   vector length = 25
	cov. matrix type = DIAGC
	   duration type = NULLD
	     mixture num = 64

Dictionary Info:
        vocabulary size  = 8 words, 22 models
        average word len = 2.8 models, 8.2 states
       maximum state num = 12 nodes per word
       transparent words = not exist
       words under class = not exist

Lexicon tree info:
	 total node num =     66
	  root node num =      8
	  leaf node num =      8

DFA grammar info:
      5 nodes, 5 arcs, 4 terminal(category) symbols
      category-pair matrix size is 2 bytes

Weights and words: 
	(-penalty1) IW penalty1 = +0.0
	(-penalty2) IW penalty2 = +0.0
	(-cmalpha)CM alpha coef = 0.050000
	(-sp)shortpause HMM name= "sp" specified, "sp" applied (physical)
	  found sp category IDs = 3

Search parameters: 
	      1st pass decoding = on-the-fly with last CMN
	        1st pass method = 1-best approx. generating indexed trellis
	(-b) trellis beam width = 42
	(-n)search candidate num= 1
	(-s)  search stack size = 500
	(-m)    search overflow = after 2000 hypothesis poped
	(-b2)  pass2 beam width = 30
	(-lookuprange)lookup range= 5  (tm-5 <= t <tm+5)
	(-sb)2nd scan beamthres = 80.0 (in logscore)
	(-gprune)Gauss. pruning = beam
	(-tmix)   mixture thres = 2 / 0
	(-n)        search till = 1 candidates found
	(-output)    and output = 1 candidates out of above
	 IWCD handling:
	   1st pass: approximation (use average prob. of same LC)
	   2nd pass: loose (apply when hypo. is popped and scanned)
	 all possible words will be expanded in 2nd pass
	 build_wchmm2() used
	 lcdset limited by word-pair constraint
	progressive output on 1st pass
	 output word confidence measure based on search-time scores

System I/O configuration:
	    speech input source = microphone
	         sampling freq. = 16000 Hz
	        threaded A/D-in = supported, on
	  zero frames stripping = on
	        silence cutting = on
	            level thres = 2000 / 32767
	        zerocross thres = 60 / sec.
	            head margin = 300 msec.
	            tail margin = 400 msec.
	       remove DC offset = off
	     reject short input = off
	short pause segmentation= off
	       result output to = tty (standard out)
	       progout interval = 300 msec

------------- System Info end -------------

	************************************************************
	* NOTICE: The first input may not be correctly recoginized *
	*         since no CMN parameter is available on startup.  *
	************************************************************


pass1_best: <s>
pass1_best: <s>
pass1_best: <s>
sentence1: <s> <giza> </s>

pass1_best: <s> 
pass1_best: <s> 
pass1_best: <s>  </s>
sentence1: <s>  </s>

pass1_best: <s>
pass1_best: <s> <ten> <sp>
pass1_best: <s> <ten> <sp>
sentence1: <s> <ten> </s>

pass1_best: <s>
pass1_best: <s> <ten> </s>
pass1_best: <s> <ten> <sp> <ten>
pass1_best: <s> <ten> <sp> <ten> <sp>
pass1_best: <s> <ten> <sp> <ten> <sp>
sentence1: <s> <ten> <ten> </s>

pass1_best: <s>
pass1_best: <s>
pass1_best: <s>
sentence1: <s> <ten> </s>

pass1_best: <s> 
pass1_best: <s> <ten> <ten>
pass1_best: <s> <ten> <ten> <ten>
pass1_best: <s> <ten> <ten> <ten> <ten> </s>
pass1_best: <s> <ten> <ten> <ten> <ten> </s>
sentence1: <s> <ten> <ten> <ten> <ten> </s>

pass1_best: <s> <ten>
pass1_best: <s> <ten> <ten>
pass1_best: <s> <ten> <ten> <ten> <sp>
pass1_best: <s> <ten> <ten> <ten> <ten> </s>
pass1_best: <s> <ten> <ten> <ten> <ten> <sp>
sentence1: <s> <ten> <ten> <ten> <ten> </s>

pass1_best: <s>
pass1_best: <s>
pass1_best: <s> <ten> <sp> <giza>
pass1_best: <s> <ten> <sp> <giza> <giza>
pass1_best: <s> <ten> <sp> <giza> <giza> <giza> <sp>
pass1_best: <s> <ten> <sp> <giza> <giza> <giza> <giza> </s>
pass1_best: <s> <ten> <sp> <giza> <giza> <giza> <giza> </s>
sentence1: <s> <ten> <giza> <ten> <giza> </s>

pass1_best: <s>
pass1_best: <s>
pass1_best: <s>
sentence1: <s> <giza> </s>

pass1_best: <s>
pass1_best: <s>
sentence1: <s> <giza> </s>

pass1_best: <s>
pass1_best: <s>
pass1_best: <s>
pass1_best: <s>  </s>
sentence1: <s>  </s>

pass1_best: <s>
pass1_best: <s>
pass1_best: <s>
sentence1: <s> <giza> </s>

pass1_best: <s>
pass1_best: <s> ɥ </s>
pass1_best: <s> ɥ </s>
sentence1: <s> ɥ </s>

pass1_best: <s>
pass1_best: <s>  </s>
pass1_best: <s>  </s>
sentence1: <s>  </s>

pass1_best: <s>
pass1_best: <s>
pass1_best: <s>
sentence1: <s> <ten> </s>

pass1_best: <s>
pass1_best: <s> 
sentence1: <s> <ten> </s>
