SpeakGoodChinese tone recognizer

The Tone recognizer is an autonomous module. It is implemented
completely in Praat scripts. These are run on praat executables
either in the background, or bij way of sendpraat commands.

The main application calls the scripts with the praat executables.
Sound files and resulting texts are written to file 
(lastExample.wav, lastResult.txt, feedback.txt). There are
also some scripts with supporting functions.

The feedback advice is stored in the feedback directory and the
real advice is generated by ToneRecognition.praat.
Currently only positive advice (for tone X you should produce Y).
But corrective advice would be possible after adapting 
ToneRecognition.praat 

The remainder of the files is used for testing the tone models
and the recognizer. They generally interface to SGC_ToneProt.praat
or ToneScript.praat.

The crucial tone modelling is done in ToneScript.praat. This script
determines syllable structure, duration, and tone models. The actual
numbers for synthesizing the tone pitch tracks are read from
ToneRules.praat. This latter script encodes the rules in Praat
script if-else-endif rules. If you plan to change the tone models,
the starting point would be the ToneRules.praat script.

Collecting usage and perfomance data, and creating example audio

It is possible to record all utterances and write the recognition
results to a logFile.txt file. This option is not available from
the GUI. Currently, it is switched on by creating a file
in the SGC_ToneProt/log directory with the name logPerformance.txt 
(you can rename an existing stub file DoNotlogPerformance.txt to
logPerformance.txt). As long as there exists a file 
SGC_ToneProt/log/logPerformance.txt, every processed utterance
(audio and result) is stored in the directory SGC_ToneProt/log

EXECUTABLES
praatcon.exe               : Praat background executable for XP

TONE RECOGNIZER
SGC_ToneProt.praat         : Main script
ToneRecognition.praat      : The recognizer function
ToneScript.praat           : Tone generator pinyin -> Tone model
ToneRules.praat            : "Rules" that determine tone shapes and duration
                             (if you want to alter the tone models, start here)

SUPPORTING SCRIPTS
DrawToneContour.praat      : Generate and draw a tone model
HumToneContour.praat       : Generate and hum a tone model

TESTING SCRIPTS
CreateFullToneSet.praat    : Create a set of all tone shapes for a reiterated syllable
SGC_ToneProt.tcl           : A TCL/TK interface to test real interactive recognition
TestToneRecognition.praat  : Run the recognizer on files in a directory
ReferenceToneScript.praat  : Generate a Pitch object from the pinyin
ReplayToneLogFile.praat    : Replay the log entries generated by SGC_ToneProt.tcl

TEXTS etc
feedback                   : Directory with the feedback text
feedback.txt               : The last feedback text generated
lastExample.wav            : The last sound used in recognition
lastResult.txt             : The last recognition result
README.txt                 : This text
SGC_protWordList.txt       : A wordlist used by SGC_ToneProt.tcl