// /// <summary>
// /// IMPORTANT: This will crash the Lipsyncer.
// ///
// /// Get this. I only have EnglishUS and EnglishGB recognizers for my OS
// /// (win7 pro) but can output the phonemes of French and perhaps other
// /// languages.
// /// PS. My EnglishGB phonemes appear to be utterly borked.
// /// </summary>
// /// <param name="langid"></param>
// void PrintPhons(int langid)
// {
// _phoneConverter.LanguageId = langid;
// for (int i = 0; i != 100; ++i)
// logfile.Log(i + " - " + _phoneConverter.IdToPhone(i));
// }
#region methods
/// <summary>
/// Sets the Recognizer and LanguageId when the Recognizers combobox
/// selection changes.
/// @note The LanguageId is used by both TTS and SpeechRecognition.
/// </summary>
/// <param name="recognizer"></param>
/// <returns>true if the language-id is set successfully</returns>
bool SetRecognizer(Recognizer recognizer)
{
#if DEBUG
logfile.Log();
logfile.Log("SetRecognizer()");
logfile.Log(". create (SpInprocRecognizer)_recognizer");
#endif
_recognizer = new SpInprocRecognizer();
#if DEBUG
logfile.Log(". (SpInprocRecognizer)_recognizer CREATED");
#endif
_recognizer.Recognizer = (SpObjectToken)recognizer.Tok;
#if DEBUG
logfile.Log(". recognizer.Tok.Id= " + recognizer.Tok.Id);
logfile.Log(". recognizer.Description= " + recognizer.Tok.GetDescription());
logfile.Log(". recognizer.Langids= " + recognizer.Langids);
#endif
string langid = recognizer.Langids;
int pos = recognizer.Langids.IndexOf(' ');
if (pos != -1)
{
langid = langid.Substring(0, pos); // use 1st langid
}
// TODO: ComboBox dropdown for user to choose from if 2+ languages
// are supported by the current Recognizer.
int id;
if (!Int32.TryParse(langid, out id) || // safety - unless the token has "n/a" Languages.
id < 0) // TODO: check id against valid SAPI language-ids
{
if (!FxeGeneratorF.isConsole)
{
using (var d = new InfoDialog("Error", "Did not find a Language in the Recognizer's token."))
{
d.ShowDialog(FxeGeneratorF.That);
}
}
return(false);
}
_phoneConverter.LanguageId = id;
#if DEBUG
logfile.Log(". _phoneConverter.LanguageId= " + _phoneConverter.LanguageId);
logfile.Log();
#endif
StaticData.viceroy(_phoneConverter.LanguageId);
return(true);
}
/// <summary>
/// Adds the user's installed SAPI-compliant SpeechRecognizers (speech
/// recognition engines) to a specified combobox.
/// </summary>
/// <param name="co"></param>
/// <returns>true if a Recognizer was found and added to the list;
/// false if user is SoL</returns>
internal static bool AddSpeechRecognizers(ComboBox co)
{
#if DEBUG
logfile.Log();
logfile.Log("SpeechRecognizerLister.AddSpeechRecognizers()");
logfile.Log(". create (SpInprocRecognizer)_recognizer");
#endif
// NOTE: This is your SAPI5.4 SpeechRecognizer (aka SpeechRecognitionEngine) interface.
// good luck!
var sr_default = new SpInprocRecognizer();
#if DEBUG
logfile.Log(". (SpInprocRecognizer)_recognizer CREATED");
#endif
if (sr_default != null)
{
#if DEBUG
logfile.Log();
logfile.Log("Recognizer.Id= " + sr_default.Recognizer.Id);
logfile.Log("Recognizer.GetDescription()= " + sr_default.Recognizer.GetDescription());
logfile.Log();
#endif
ISpeechObjectTokens toks = sr_default.GetRecognizers();
#if DEBUG
foreach (ISpeechObjectToken tok in toks)
{
logfile.Log(". installed.Id= " + tok.Id);
logfile.Log(". installed.GetDescription()= " + tok.GetDescription());
}
logfile.Log();
#endif
int id_default = -1;
bool id_default_found = false;
var recognizers = new List <Recognizer>();
foreach (ISpeechObjectToken tok in toks)
{
if (tok.GetDescription().Contains("Microsoft Speech Recognizer")) // 8.0+ TODO: other SAPI-compliant speech engines incl/ 3rd-party
{
recognizers.Add(new Recognizer(tok));
if (!id_default_found)
{
++id_default;
if (tok.Id == sr_default.Recognizer.Id)
{
id_default_found = true;
}
}
}
}
if (recognizers.Count != 0)
{
co.DataSource = recognizers;
co.SelectedIndex = id_default;
return(true);
}
}
#if DEBUG
logfile.Log(". RECOGNIZER NOT FOUND");
#endif
return(false);
}
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
}
