bool UseDictation; // Declare boolean variable for storing pronunciation dictation grammar setting
public void main()
{
// Reset relevant VoiceAttack text variables
VA.SetText("~~RecognitionError", null);
VA.SetText("~~RecognizedText", null);
VA.SetText("~~SAPIPhonemes", null);
VA.SetText("~~SAPIPhonemesRaw", null);
//VA.SetText("~~FalseRecognitionFlag", null);
// Retrieve the desired word data contained within VoiceAttack text variable
string ProcessText = null; // Initialize string variable for storing the text of interest
if (VA.GetText("~~ProcessText") != null) // Check if user provided valid text in input variable
{
ProcessText = VA.GetText("~~ProcessText"); // Store text of interest held by VA text variable
}
else
{
VA.SetText("~~RecognitionError", "Error in input text string (SAPI)"); // Send error detail back to VoiceAttack as text variable
return; // End code processing
}
// Retrieve path to speech grammar XML file from VoiceAttack
GrammarPath = VA.GetText("~~GrammarFilePath");
// Retrieve path to voice recognition input wav file from VoiceAttack
AudioPath = VA.GetText("~~AudioFilePath");
// Check if TTS engine is voicing the input for the speech recognition engine
if (VA.GetBoolean("~~UserVoiceInput") == false)
{
//VA.WriteToLog("creating wav file");
if (TextToWav(AudioPath, ProcessText) == false) // Create wav file with specified path that voices specified text (with text-to-speech) and check if the creation was NOT successful
{
return; // Stop executing the code
}
}
// Create speech recognizer and associated context
SpInprocRecognizer MyRecognizer = new SpInprocRecognizer(); // Create new instance of SpInprocRecognizer
SpInProcRecoContext RecoContext = (SpInProcRecoContext)MyRecognizer.CreateRecoContext(); // Initialize the SpInProcRecoContext (in-process recognition context)
try // Attempt the following code
{
// Open the created wav in a new FileStream
FileStream = new SpFileStream(); // Create new instance of SpFileStream
FileStream.Open(AudioPath, SpeechStreamFileMode.SSFMOpenForRead, true); // Open the specified file in the FileStream for reading with events enabled
// Set the voice recognition input as the FileStream
MyRecognizer.AudioInputStream = FileStream; // This will internally "speak" the wav file for input into the voice recognition engine
// Set up recognition event handling
RecoContext.Recognition += new _ISpeechRecoContextEvents_RecognitionEventHandler(RecoContext_Recognition); // Register for successful voice recognition events
RecoContext.FalseRecognition += new _ISpeechRecoContextEvents_FalseRecognitionEventHandler(RecoContext_FalseRecognition); // Register for failed (low confidence) voice recognition events
if (VA.GetBoolean("~~ShowRecognitionHypothesis") == true) // Check if user wants to show voice recognition hypothesis results
{
RecoContext.Hypothesis += new _ISpeechRecoContextEvents_HypothesisEventHandler(RecoContext_Hypothesis); // Register for voice recognition hypothesis events
}
RecoContext.EndStream += new _ISpeechRecoContextEvents_EndStreamEventHandler(RecoContext_EndStream); // Register for end of file stream events
// Set up the grammar
grammar = RecoContext.CreateGrammar(); // Initialize the grammar object
UseDictation = (bool?)VA.GetBoolean("~~UseDictation") ?? false; // Set UserDictation based on value from VoiceAttack boolean variable
if (UseDictation == true) // Check if pronunciation dictation grammar should be used with speech recognition
{
//grammar.DictationLoad("", SpeechLoadOption.SLOStatic); // Load blank dictation topic into the grammar
grammar.DictationLoad("Pronunciation", SpeechLoadOption.SLOStatic); // Load pronunciation dictation topic into the grammar so that the raw (unfiltered) phonemes may be retrieved
grammar.DictationSetState(SpeechRuleState.SGDSActive); // Activate dictation grammar
}
else
{
grammar.CmdLoadFromFile(GrammarPath, SpeechLoadOption.SLODynamic); // Load custom XML grammar file
grammar.CmdSetRuleIdState(0, SpeechRuleState.SGDSActive); // Activate the loaded grammar
}
Application.Run(); // Starts a standard application message loop on the current thread
}
catch // Handle exceptions in above code
{
VA.SetText("~~RecognitionError", "Error during voice recognition setup (SAPI)"); // Send error detail back to VoiceAttack as text variable
return; // Stop executing the code
}
finally // Runs whether an exception is encountered or not
{
MyRecognizer = null; // Set to null in preparation for garbage collection
FileStream.Close(); // Close the input FileStream
FileStream = null; // Set to null in preparation for garbage collection
// Close up recognition event handling
RecoContext.Recognition -= new _ISpeechRecoContextEvents_RecognitionEventHandler(RecoContext_Recognition); // Unregister for successful voice recognition events
RecoContext.FalseRecognition -= new _ISpeechRecoContextEvents_FalseRecognitionEventHandler(RecoContext_FalseRecognition); // Unregister for failed (low confidence) voice recognition events
if (VA.GetBoolean("~~ShowRecognitionHypothesis") == true) // Check if user wanted to show voice recognition hypothesis results
{
RecoContext.Hypothesis -= new _ISpeechRecoContextEvents_HypothesisEventHandler(RecoContext_Hypothesis); // Unregister for voice recognition hypothesis events
}
RecoContext.EndStream -= new _ISpeechRecoContextEvents_EndStreamEventHandler(RecoContext_EndStream); // Unregister for end of file stream events
RecoContext = null; // Set to null in preparation for garbage collection
}
//VA.WriteToLog("voice recognition complete"); // Output info to event log
}
/// <summary>
/// Generate() will be called only once if there is no typed-text; it
/// should use dictation. Generate() will be called a second time if
/// there is typed-text; the second pass should use both dictation and
/// context-free-grammar (ie, Command and Control: a Rule that's based
/// on the typed-text).
/// </summary>
void Generate()
{
#if DEBUG
logfile.Log();
logfile.Log("Generate() _generato= " + _generato);
#endif
_offset = 0;
Confidence_def_count = 0;
// was "2" but MS doc says not needed on its end.
// and I don't see grammar id #2 defined on this end either.
_recoGrammar = _recoContext.CreateGrammar();
// _recoGrammar.DictationLoad(); // ("Pronunciation") <- causes orthemes to print as phonemes instead of words
switch (_generato)
{
case Generator.Dictati:
if (_recoGrammar.Rules.FindRule(RULE) != null)
{
#if DEBUG
logfile.Log(". set Rule INACTIVE");
#endif
_recoGrammar.CmdSetRuleState(RULE, SpeechRuleState.SGDSInactive);
}
#if DEBUG
logfile.Log(". set Dictation ACTIVE");
#endif
_recoGrammar.DictationSetState(SpeechRuleState.SGDSActive);
break;
case Generator.Dialogi:
#if DEBUG
logfile.Log(". set Dictation INACTIVE");
#endif
_recoGrammar.DictationSetState(SpeechRuleState.SGDSInactive);
if (_recoGrammar.Rules.FindRule(RULE) == null)
{
#if DEBUG
logfile.Log(". . add \"" + RULE + "\" Rule");
#endif
ISpeechGrammarRule rule = _recoGrammar.Rules.Add(RULE,
SpeechRuleAttributes.SRATopLevel,
1);
rule.InitialState.AddWordTransition(null,
_text,
" ",
SpeechGrammarWordType.SGLexical,
RULE,
1);
_recoGrammar.Rules.Commit();
}
#if DEBUG
logfile.Log(". set Rule ACTIVE");
#endif
_recoGrammar.CmdSetRuleState(RULE, SpeechRuleState.SGDSActive);
// logfile.Log(". max alternates(pre)= " + _recoContext.CmdMaxAlternates);
// _recoContext.CmdMaxAlternates = 3;
// logfile.Log(". max alternates(pos)= " + _recoContext.CmdMaxAlternates);
break;
}
#if DEBUG
logfile.Log(". create (SpFileStream)_fs");
#endif
_fs = new SpFileStream();
#if DEBUG
logfile.Log(". (SpFileStream)_fs CREATED");
#endif
// _fs.Format.Type = SpeechAudioFormatType.SAFT44kHz16BitMono;
#if DEBUG
logfile.Log(". Open Wavefile _fs");
#endif
_fs.Open(Wavefile);
#if DEBUG
logfile.Log(". _fs.Format.Type= " + _fs.Format.Type); // SpeechAudioFormatType.SAFT44kHz16BitMono
SpWaveFormatEx data = _fs.Format.GetWaveFormatEx();
logfile.Log(". . SamplesPerSec= " + data.SamplesPerSec);
logfile.Log(". . BitsPerSample= " + data.BitsPerSample);
logfile.Log(". . AvgBytesPerSec= " + data.AvgBytesPerSec);
logfile.Log(". . Channels= " + data.Channels);
logfile.Log(". . BlockAlign= " + data.BlockAlign);
logfile.Log(". . FormatTag= " + data.FormatTag);
logfile.Log(". . ExtraData= " + data.ExtraData);
// filestream byte-data ->
// int bytes, pos = 0;
// object o = new byte[2];
// while ((bytes = _fs.Read(out o, 2)) > 0)
// {
// var buffer = (byte[])o;
// logfile.Log(pos + " : " + buffer[1] + " " + buffer[0]); // treat as little-endian shorts
// pos += bytes;
// }
// _fs.Seek(0);
logfile.Log(". assign _fs to _recognizer.AudioInputStream");
#endif
_recognizer.AudioInputStream = _fs; // <- start Recognition <--
#if DEBUG
logfile.Log("Generate() DONE");
logfile.Log();
#endif
}