Free anti-virus software 免費的防毒軟體

Famous software are with Initial-A.

有名的軟體有三A....

AVG

Eng - http://free.avg.com/download-avg-anti-virus-free-edition

The free version is almost free function....

不推薦，免費版幾乎沒功能...

Avira

Eng -http://www.free-av.com/en/download/1/avira_antivir_personal__free_antivirus.html

除了有廣告之外，評價都還不錯。

It's a good software, except the embeded advertisement.

Avast

中文 - http://www.avast.com/cnt/download-avast-home.html

中文註冊- http://www.avast.com/cnt/home-registration.php

Eng - http://www.avast.com/eng/download-avast-home.html

Eng Registration - http://www.avast.com/eng/home-registration.php

Avast記得要註冊，每過一年重新註冊一次。

Remember to regist your avast home, and apply it again after one year.

Not bad collection

http://www.freebyte.com/antivirus/

Comodo

Eng -  http://www.personalfirewall.comodo.com/download_firewall.html

ClamAV

Eng - http://w32.clamav.net/

Opensource anti-virus software. Interesting! Also with linux version.

ThreatFire

Eng - http://www.threatfire.com/download/

SCh - http://www.threatfire.com/cn/download/

HTK Chapter 3 - Section 1 - Step 4

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)
  
• Step 4 - Creating the Transcription Files 建立翻譯檔 (根據字典翻譯實驗資料
  

Because we have two words set
trainprompts
testprompts
First of all, we have to convert the two prompts files to be words files. That means
====================
S0002 DIAL ZERO ZERO EIGHT SIX OH ONE ZERO NINE THREE FIVE EIGHT FIVE THREE THREE NINE ZERO
====================
will be convert to
====================
"S0002.lab"
DIAL
ZERO
ZERO
EIGHT
SIX
OH
ONE
ZERO
NINE
THREE
FIVE
EIGHT
FIVE
THREE
THREE
NINE
ZERO
.
====================

Prompts level converts to word leavel.
How to read MLF(Master Label File), you can refer Section 6.3 in HTKbook.

Command is below,

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

$ perl  scripts/prompts2mlf labels/trainwords.mlf labels/trainprompts

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

For testwords.mlf,

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

$ perl  scripts/prompts2mlf labels/testwords.mlf labels/testprompts

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

Then use HLEd (Label Editor) to convert word level to phone level.

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

$ HLEd -l   '*'  -d dict/dict1 -i  labels/phones0.mlf   mkphones0.led   labels/trainwords.mlf

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

mkphones0.led is edit script filr to tell HLEd how to generate labels/phones0.mlf from labels/trainwords.mlf.

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

EX

IS sil sil

DE sp

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

• EX, means replace all the words in labels/trainwords.mlf to phones level.
  
• IS sil sil, means insert sil to the start and the end of utterance.
  
• DE sp, means that deleting all short-pause.

HLEd will refer the dict/dict1 to transcript each word to its phones.

To know more about HLEd, refer to Section 17.10 in HTKBook.

Then labels/trainwords.mlf will be replaced to labels/phones0.mlf. 

Like, 

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

"*/S0001.lab"

DIAL

EIGHT

FIVE

.

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

replaced to

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

"*/S0001.lab"

sil

d

ay

ax

l

ey

t

f

ay

v

sil

.

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

sil is inserted to the start and the end. DIAL is replaced to d and ay.

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.

Install LEVMAR on Cygwin

I would like to use LEVMAR on Cygwin.

LEVMAR is abbreviation of Levenberg-Marquardt nonlinear least squares algorithms in C/C++,

official website. 

First of all, you will be suggested by the author of LEVMAR to install LPACK packages,

Install LApack package from Cygwin Math category.

You also need f2c first before install levmar.

http://www.seanet.com/~bradbell/f2cAD/f2cinstall.xml

https://computation.llnl.gov/casc/Overture/henshaw/install/node8.html

I prefer the source code from 2nd URL. There are few problem when making.

Then copy the /libf2c/libf2c.a to lib, and copy /src/f2c to bin, as the instructions of 1st URL.

Then type make under levmar-2.3. You should be make succesfully. If no, watch out the error message and install what package you miss.

If succesfully, you can type ./lmdemo.exe to run the demo execution to test and get the results following,

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

$ ./lmdemo.exe

Covariance of the fit:

0.00483514 -0.00162445 -0.000548114

-0.00162445 0.000546079 0.000184356

-0.000548114 0.000184356 6.22705e-05

Results for Meyer's (reformulated) problem:

Levenberg-Marquardt returned 209 in 209 iter, reason 2

Solution: 2.481778 6.181346 3.502236

Minimization info:

1308.25 8.79459e-05 1.10765e-07 2.65846e-34 129559 209 2 273 21

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

There are another two useful math packages.

• CLAPack 3.1.1.1- http://www.netlib.org/clapack/
• ATLAS 3.6.0 - http://www.netlib.org/atlas
• ATLAS 3.8.0 - http://sourceforge.net/project/showfiles.php?group_id=23725

There is a good tutorial webpage to show how to install the 2 packages.

http://www.ifp.uiuc.edu/~nakazato/tips/cygwin_atlas.html

http://cpplapack.sourceforge.net/doc/html/pg-cygwin.html

Uninstall Cygwin Entirely

I try to uninstall Cygwin for rebuilding Mono.

There are a lot of webpage talking about uninstall Cygwin.

• http://pigtail.net/LRP/printsrv/remove-cygwin.html
  
• http://jrshelby.com/grass/remove.htm
  
• http://cygwin.com/faq/faq-nochunks.html#faq.setup.uninstall-all
  

Official instruction is best.