HTK Chapter 3 - Section 1 - Step 3

Below paragraphs are belong to 

• HTKBooks, 
  
• 苏统华, 哈尔滨工业大学人工智能研究室, 2006年10月30日, 
  
• Howard Hung-Ju Chou, Intelligence Information Retrieval Lab., NCKU, Taiwan(R.O.C.).

Environment: 

• HTK 3.4 
  
• Cygwin NT-5.1 1.5.25

Section 1 is Data Preparation - 資料準備

• Step 1 - the Task Grammer 辨識模型要用的文法資料(gram->wdnet)
  
• Step 2 - the Dictionary  辨識模型要用的字典資料 (利用字典將wlist裡的單字翻譯為phones字串, one -> w ah n)
• Step 3 - Recording the Data 錄製辨識用的語音檔 (產生劇本並依照劇本錄製*.wav)
  

Now, we can use the tool HSGen to generate the experimental sentences constructing by the lattice file.

For example, 

$ HSGen -l -n 200 wdnet dict > testpromts

The HSGen will generate 200 entries of training sentences and save them in testpromts file by wdnet.

-------------------------------------------

$HSGen -l -n 140 wdnet /dict/dict1 > labels/trainprompts

-------------------------------------------

-------------------------------------------

$HSGen -l -n 15 wdnet /dict/dict1 > labels/testprompts

-------------------------------------------

So we can generate two files, trainprompts and testprompts, 140 entries and 15 entries respectively.

• trainprompts

=======================

S0001 DIAL EIGHT FIVE 

S0002 DIAL ZERO ZERO EIGHT SIX OH ONE ZERO NINE THREE FIVE EIGHT FIVE THREE THREE NINE ZERO 

S0003 DIAL ZERO SIX ZERO EIGHT THREE ZERO EIGHT SEVEN SEVEN THREE FIVE ONE TWO TWO FOUR NINE SIX 

S0004 CALL DAVE WOOD 

S0005 CALL STEVE YOUNG 

S0006 DIAL NINE OH THREE NINE ONE ZERO ONE NINE NINE OH THREE THREE FOUR TWO FOUR SEVEN FOUR ZERO ZERO SIX ONE ZERO ONE FOUR ZERO NINE TWO 

S0007 DIAL NINE FOUR TWO NINE OH 

S0008 DIAL SEVEN EIGHT SIX ONE EIGHT ZERO NINE ZERO SIX SIX SIX ONE ONE THREE 

S0009 PHONE DAVE WOOD 

S0010 CALL TYLER 

....

=======================

• testprompts

=======================

T0001 PHONE LAW 

T0002 PHONE JULIAN TYLER 

T0003 CALL JULIAN TYLER 

T0004 CALL WOOD 

T0005 PHONE LAW 

T0006 PHONE STEVE YOUNG 

T0007 PHONE STEVE YOUNG 

T0008 DIAL FIVE FIVE TWO SIX SEVEN SIX EIGHT 

T0009 PHONE PHIL LEE 

T0010 DIAL TWO EIGHT FOUR SIX THREE ZERO OH OH EIGHT NINE FOUR NINE 

T0011 DIAL NINE SIX OH NINE SIX THREE SIX EIGHT THREE OH 

T0012 CALL DAVE WOOD 

T0013 PHONE YOUNG 

T0014 DIAL ONE OH OH ZERO EIGHT TWO OH 

T0015 PHONE WOOD

=======================

Then use HSLab to record the wav files.