private void ProgramSpeechInit()
{
//ルール認識 音声認識オブジェクトの生成
this.ProgramRule = new SpInProcRecoContext();
bool hit = false;
foreach (SpObjectToken recoperson in this.ProgramRule.Recognizer.GetRecognizers()) //'Go through the SR enumeration
{
string language = recoperson.GetAttribute("Language");
if (language == "411")
{ //日本語を聴き取れる人だ
this.ProgramRule.Recognizer.Recognizer = recoperson; //君に聞いていて欲しい
hit = true;
break;
}
}
if (!hit)
{
MessageBox.Show("日本語認識が利用できません。\r\n日本語音声認識 MSSpeech_SR_ja-JP_TELE をインストールしてください。\r\n");
Application.Exit();
}
//マイクから拾ってね。
this.ProgramRule.Recognizer.AudioInput = this.CreateMicrofon();
//音声認識イベントで、デリゲートによるコールバックを受ける.
//認識完了
this.ProgramRule.Recognition +=
delegate(int streamNumber, object streamPosition, SpeechLib.SpeechRecognitionType srt, SpeechLib.ISpeechRecoResult isrr)
{
string strText = isrr.PhraseInfo.GetText(0, -1, true);
ProgramRun(strText);
};
//認識失敗
this.ProgramRule.FalseRecognition +=
delegate(int streamNumber, object streamPosition, SpeechLib.ISpeechRecoResult isrr)
{
label1.Text = "？？";
show("what", 0);
};
//言語モデルの作成
this.ProgramGrammarRule = this.ProgramRule.CreateGrammar(0);
this.ProgramGrammarRule.Reset(0);
//言語モデルのルールのトップレベルを作成する.
this.ProgramGrammarRuleGrammarRule = this.ProgramGrammarRule.Rules.Add("ProgramRule",
SpeechRuleAttributes.SRATopLevel | SpeechRuleAttributes.SRADynamic);
//認証用文字列の追加.
ArrayList voicelist = list.GetProgramCommand();
foreach (string voice in voicelist)
{
this.ProgramGrammarRuleGrammarRule.InitialState.AddWordTransition(null, voice);
}
this.ProgramGrammarRuleGrammarRule.InitialState.AddWordTransition(null, Program.skinini.GetValue("skininfo", "clock", "時計に戻して"));
//ルールを反映させる。
this.ProgramGrammarRule.Rules.Commit();
}
//音声認識初期化
private void AlwaysSpeechInit()
{
//ルール認識 音声認識オブジェクトの生成
this.AlwaysRule = new SpInProcRecoContext();
bool hit = false;
foreach (SpObjectToken recoperson in this.AlwaysRule.Recognizer.GetRecognizers()) //'Go through the SR enumeration
{
string language = recoperson.GetAttribute("Language");
if (language == "411")
{ //日本語を聴き取れる人だ
this.AlwaysRule.Recognizer.Recognizer = recoperson; //君に聞いていて欲しい
hit = true;
break;
}
}
if (!hit)
{
MessageBox.Show("日本語認識が利用できません。\r\n日本語音声認識 MSSpeech_SR_ja-JP_TELE をインストールしてください。\r\n");
Application.Exit();
}
//マイクから拾ってね。
this.AlwaysRule.Recognizer.AudioInput = this.CreateMicrofon();
//音声認識イベントで、デリゲートによるコールバックを受ける.
//認識完了
this.AlwaysRule.Recognition +=
delegate(int streamNumber, object streamPosition, SpeechLib.SpeechRecognitionType srt, SpeechLib.ISpeechRecoResult isrr)
{
//音声認識終了
this.AlwaysGrammarRule.CmdSetRuleState("AlwaysRule", SpeechRuleState.SGDSInactive);
//ウィンドウをアクティブにする
this.Activate();
//聞き取り開始時間取得
starttime = Environment.TickCount & int.MaxValue;
//聞き取り開始
label1_MouseUp(null, null);
};
//言語モデルの作成
this.AlwaysGrammarRule = this.AlwaysRule.CreateGrammar(0);
this.AlwaysGrammarRule.Reset(0);
//言語モデルのルールのトップレベルを作成する.
this.AlwaysGrammarRuleGrammarRule = this.AlwaysGrammarRule.Rules.Add("AlwaysRule",
SpeechRuleAttributes.SRATopLevel | SpeechRuleAttributes.SRADynamic);
//認証用文字列の追加.
this.AlwaysGrammarRuleGrammarRule.InitialState.AddWordTransition(null, Program.skinini.GetValue("skininfo", "response", "テスト"));
//ルールを反映させる。
this.AlwaysGrammarRule.Rules.Commit();
}
//音声認識初期化
private void VoiceCommandInit()
{
//ルール認識 音声認識オブジェクトの生成
this.DialogRule = new SpInProcRecoContext();
bool hit = false;
foreach (SpObjectToken recoperson in this.DialogRule.Recognizer.GetRecognizers()) //'Go through the SR enumeration
{
string language = recoperson.GetAttribute("Language");
if (language == "411") //日本語を聴き取れる人だ
{
this.DialogRule.Recognizer.Recognizer = recoperson; //君に聞いていて欲しい
hit = true;
break;
}
}
if (!hit)
{
MessageBox.Show("日本語認識が利用できません。\r\n日本語音声認識 MSSpeech_SR_ja-JP_TELE をインストールしてください。\r\n");
Application.Exit();
}
//マイクから拾ってね。
this.DialogRule.Recognizer.AudioInput = this.CreateMicrofon();
//音声認識イベントで、デリゲートによるコールバックを受ける.
//認識完了
this.DialogRule.Recognition +=
delegate(int streamNumber, object streamPosition, SpeechLib.SpeechRecognitionType srt, SpeechLib.ISpeechRecoResult isrr) {
string strText = isrr.PhraseInfo.GetText(0, -1, true);
this.SpeechTextBranch(strText);
};
//言語モデルの作成
this.DialogGrammarRule = this.DialogRule.CreateGrammar(0);
this.DialogGrammarRule.Reset(0);
//言語モデルのルールのトップレベルを作成する.
this.DialogGrammarRuleGrammarRule = this.DialogGrammarRule.Rules.Add("DialogRule",
SpeechRuleAttributes.SRATopLevel | SpeechRuleAttributes.SRADynamic);
//認証用文字列の追加.
this.DialogGrammarRuleGrammarRule.InitialState.AddWordTransition(null, "音声入力");
this.DialogGrammarRuleGrammarRule.InitialState.AddWordTransition(null, "オーケー");
this.DialogGrammarRuleGrammarRule.InitialState.AddWordTransition(null, "キャンセル");
//ルールを反映させる。
this.DialogGrammarRule.Rules.Commit();
}
public void initialize()
{
context = new SpInProcRecoContext();
grammars.Clear();
context.Recognition += new _ISpeechRecoContextEvents_RecognitionEventHandler(context_Recognition);
context.FalseRecognition += new _ISpeechRecoContextEvents_FalseRecognitionEventHandler(context_FalseRecognition);
context.Interference += new _ISpeechRecoContextEvents_InterferenceEventHandler(context_Interference);
// grammar.DictationSetState(SpeechRuleState.SGDSActive);
context.CmdMaxAlternates = 5;
context.State = SpeechRecoContextState.SRCS_Enabled;
context.RetainedAudio = SpeechRetainedAudioOptions.SRAORetainAudio;
//if (get_property_value("PersistedBackgroundAdaptation") == 1)
//Feedback.print("cpu: " + get_property_value("ResourceUsage") + "\r\n", Feedback.Status.debug);
//Feedback.print("high: " + get_property_value("ResourceUsage") + "\r\n", Feedback.Status.debug);
//Feedback.print("medium: " + get_property_value("ResourceUsage") + "\r\n", Feedback.Status.debug);
//Feedback.print("low: " + get_property_value("ResourceUsage") + "\r\n", Feedback.Status.debug);
//Feedback.print("adaptation: " + get_property_value("AdaptationOn") + "\r\n", Feedback.Status.debug);
//set_property_value("PersistedBackgroundAdaptation", 0);
// set_property_value("AdaptationOn", 0);
// set_property_value("PersistedLanguageModelAdaptation", 0);
initialize_audio();
}
private void InitZone(int zoneNum)
{
//Set up the zone computers to transmit speech and receive audio
if (zoneNum < 3)
{
// Process.Start(@"C:\Users\Blake\Documents\Programming\CSharp\C2program\C2program\scripts\pi_speak.bat", Convert.ToString(zoneNum));
Process.Start(@"..\..\scripts\pi_speak.bat", Convert.ToString(zoneNum));
}
else
{
// Process.Start(@"C:\Users\Blake\Documents\Programming\CSharp\C2program\C2program\scripts\pi_speak_new_mic.bat", Convert.ToString(zoneNum));
Process.Start(@"..\..\scripts\pi_speak_new_mic.bat", Convert.ToString(zoneNum));
}
// Process.Start(@"C:\Users\Blake\Documents\Programming\CSharp\C2program\C2program\scripts\pi_listen.bat", Convert.ToString(zoneNum));
Process.Start(@"..\..\scripts\pi_listen.bat", Convert.ToString(zoneNum));
//Set up the voice for each zone
// rtpServer[zoneNum - 1] = new RTPServer(zoneAddresses[zoneNum - 1], 1234);
// rtpServer[zoneNum - 1].StartServer();
// SpCustomStream vStream = new SpCustomStream();
// vStream.BaseStream = rtpServer[zoneNum - 1].AudioStream;
voice[zoneNum - 1] = new C2Voice(zoneNum);
// voice[zoneNum - 1].Voice.AudioOutputStream = vStream;
//recoContext = new SpSharedRecoContext();
recoContext[zoneNum - 1] = new SpInProcRecoContext();
//set up the socket stream first
// mySrStream = new C2SRStream("192.168.2.101", 1234);
rtpClient[zoneNum - 1] = new RTPReceiver(zonePortBase + zoneNum);
rtpClient[zoneNum - 1].StartClient();
SpCustomStream stream = new SpCustomStream();
// stream.BaseStream = (System.Runtime.InteropServices.ComTypes.IStream)mySrStream;
// stream.BaseStream = (System.Runtime.InteropServices.ComTypes.IStream)rtpClient.AudioStream;
stream.BaseStream = rtpClient[zoneNum - 1].AudioStream;
//SpStream st = new SpStream();
CreateGrammar(zoneNum);
this.recoContext[zoneNum - 1].Recognizer.AudioInputStream = stream;
//this.recoContext.Recognizer.AudioInputStream = (ISpeechBaseStream) stream.BaseStream;
//this.recoContext.Recognizer.AudioInputStream = (ISpeechBaseStream)rtpClient.Stream;
//RecoContext.RetainedAudioFormat.Type = SpeechAudioFormatType.SAFT32kHz16BitMono;
if (zoneNum < 3)
{
recoContext[zoneNum - 1].RetainedAudioFormat.Type = SpeechAudioFormatType.SAFT24kHz16BitMono;
}
else
{
recoContext[zoneNum - 1].RetainedAudioFormat.Type = SpeechAudioFormatType.SAFT48kHz16BitMono;
}
//RecoContext.RetainedAudioFormat.Type = SpeechAudioFormatType.SAFT12kHz16BitMono;
//RecoContext.EventInterests = SPSEMANTICFORMAT. SRERecognition + SRESoundEnd + SREStreamEnd + SREStreamStart + SRESoundEnd;
recoContext[zoneNum - 1].Recognition += new SpeechLib._ISpeechRecoContextEvents_RecognitionEventHandler(InterpretCommand);
//RecoContext.Recognition += new _ISpeechRecoContextEvents_
recoContext[zoneNum - 1].Recognizer.SetPropertyNumber("AdaptationOn", 0); //turns adaptation off so it doesn't train to noise
}
private void ControlSpeechInit()
{
//ルール認識 音声認識オブジェクトの生成
this.ControlRule = new SpInProcRecoContext();
bool hit = false;
foreach (SpObjectToken recoperson in this.ControlRule.Recognizer.GetRecognizers()) //'Go through the SR enumeration
{
string language = recoperson.GetAttribute("Language");
if (language == "411")
{ //日本語を聴き取れる人だ
this.ControlRule.Recognizer.Recognizer = recoperson; //君に聞いていて欲しい
hit = true;
break;
}
}
if (!hit)
{
MessageBox.Show("日本語認識が利用できません。\r\n日本語音声認識 MSSpeech_SR_ja-JP_TELE をインストールしてください。\r\n");
Application.Exit();
}
//マイクから拾ってね。
this.ControlRule.Recognizer.AudioInput = this.CreateMicrofon();
//音声認識イベントで、デリゲートによるコールバックを受ける.
//認識完了
this.ControlRule.Recognition +=
delegate(int streamNumber, object streamPosition, SpeechLib.SpeechRecognitionType srt, SpeechLib.ISpeechRecoResult isrr)
{
string strText = isrr.PhraseInfo.GetText(0, -1, true);
SpeechTextBranch(strText);
};
//認識失敗
this.ControlRule.FalseRecognition +=
delegate(int streamNumber, object streamPosition, SpeechLib.ISpeechRecoResult isrr)
{
label1.Text = "？？";
show(filelist.GetPath("what", 0));
};
//言語モデルの作成
this.ControlGrammarRule = this.ControlRule.CreateGrammar(0);
this.ControlGrammarRule.Reset(0);
//言語モデルのルールのトップレベルを作成する.
this.ControlGrammarRuleGrammarRule = this.ControlGrammarRule.Rules.Add("ControlRule",
SpeechRuleAttributes.SRATopLevel | SpeechRuleAttributes.SRADynamic);
//認証用文字列の追加.
this.ControlGrammarRuleGrammarRule.InitialState.AddWordTransition(null, "プログラムを実行したい");
this.ControlGrammarRuleGrammarRule.InitialState.AddWordTransition(null, "ツイートしたい");
this.ControlGrammarRuleGrammarRule.InitialState.AddWordTransition(null, "検索したい");
this.ControlGrammarRuleGrammarRule.InitialState.AddWordTransition(null, "席をはずす");
this.ControlGrammarRuleGrammarRule.InitialState.AddWordTransition(null, "バッテリー残量は");
this.ControlGrammarRuleGrammarRule.InitialState.AddWordTransition(null, "プログラムリスト更新");
this.ControlGrammarRuleGrammarRule.InitialState.AddWordTransition(null, "設定を開いて");
this.ControlGrammarRuleGrammarRule.InitialState.AddWordTransition(null, "時計に戻して");
this.ControlGrammarRuleGrammarRule.InitialState.AddWordTransition(null, "君の名前は");
this.ControlGrammarRuleGrammarRule.InitialState.AddWordTransition(null, "疲れた");
this.ControlGrammarRuleGrammarRule.InitialState.AddWordTransition(null, "終了");
//ルールを反映させる。
this.ControlGrammarRule.Rules.Commit();
}
public C2SRold(Form1 form)
{
form1 = form;
gpio = new C2gpio(1, "");
state = State.IDLE;
voice = new C2Voice(1);
C2attentionTimer = new Timer(30000); //60 second time out for C2 to stop listening
C2attentionTimer.Elapsed += new ElapsedEventHandler(C2attentionTimer_Elapsed);
C2attentionTimer.AutoReset = false;
missunderstandCount = 0;
voice.Speak("C2 standing by and awaiting your instructions!");
//recoContext = new SpSharedRecoContext();
recoContext = new SpInProcRecoContext();
//set up the socket stream first
//IPEndPoint receiver = new IPEndPoint(new IPAddress(("192.168.2.101"), 1234);
// UdpClient udpClient = new UdpClient("192.168.2.101", 1234);
//UdpClient udpClient = new UdpClient(1234);
//udpClient.Connect(receiver);
// Socket socket = udpClient.Client;
//TcpClient tcpClient = new TcpClient("192.168.2.101", 1234);
// Socket socket = new Socket(AddressFamily.InterNetwork, SocketType.Dgram, ProtocolType.Udp);
// socket.Connect("192.168.2.101", 1234);
// if (!socket.Connected)
// {
// form1.statusMsg = "socket was never connected!";
// return;
// }
//SpMMAudioIn instream = new SpMMAudioIn();
// ASRStreamClass myAsrStream = new ASRStreamClass();
// mySrStream = new C2SRStream("192.168.2.101", 1234);
rtpClient = new RTPReceiver(1234);
rtpClient.StartClient();
SpCustomStream stream = new SpCustomStream();
// stream.BaseStream = (System.Runtime.InteropServices.ComTypes.IStream)mySrStream;
// stream.BaseStream = (System.Runtime.InteropServices.ComTypes.IStream)rtpClient.AudioStream;
stream.BaseStream = rtpClient.AudioStream;
//SpStream st = new SpStream();
//st.
//m_GrammarID = 1;
Grammar = this.recoContext.CreateGrammar(0);
Grammar.DictationLoad("", SpeechLoadOption.SLOStatic);
//our program doesn't do this
Grammar.DictationSetState(SpeechRuleState.SGDSActive);
//our program doesn't do this
// ISpeechGrammarRule CommandsRule;
// CommandsRule = Grammar.Rules.Add("CommandsRule", SpeechRuleAttributes.SRATopLevel | SpeechRuleAttributes.SRADynamic, 1);
// CommandsRule.Clear();
// object dummy = 0;
// string sCommand = "see";
// CommandsRule.InitialState.AddWordTransition(null, sCommand, " ", SpeechGrammarWordType.SGLexical, null, 0, ref dummy, 0);
// Grammar.Rules.Commit();
// Grammar.CmdSetRuleState("CommandsRule", SpeechRuleState.SGDSActive);
//stream.get
this.recoContext.Recognizer.AudioInputStream = stream;
//this.recoContext.Recognizer.AudioInputStream = (ISpeechBaseStream) stream.BaseStream;
//this.recoContext.Recognizer.AudioInputStream = (ISpeechBaseStream)rtpClient.Stream;
//RecoContext.EventInterests = SpeechRecoEvents.SREAllEvents;
//RecoContext.RetainedAudioFormat.Type = SpeechAudioFormatType.SAFT32kHz16BitMono;
recoContext.RetainedAudioFormat.Type = SpeechAudioFormatType.SAFT24kHz16BitMono;
//RecoContext.EventInterests = SPSEMANTICFORMAT. SRERecognition + SRESoundEnd + SREStreamEnd + SREStreamStart + SRESoundEnd;
recoContext.Recognition += new SpeechLib._ISpeechRecoContextEvents_RecognitionEventHandler(InterpretCommand);
//RecoContext.Recognition += new _ISpeechRecoContextEvents_
recoContext.Recognizer.SetPropertyNumber("AdaptationOn", 0);
}
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
}
// THESE MAKE ABSOLUTELY NO DIFFERENCE WHATSOEVER TO AUDIOFILE INPUT ->
// apparently.
// CFGConfidenceRejectionThreshold
// HighConfidenceThreshold
// NormalConfidenceThreshold
// LowConfidenceThreshold
// int val = 0;
// _recognizer.GetPropertyNumber("CFGConfidenceRejectionThreshold", ref val); // default 60-
// logfile.Log(". CFGConfidenceRejectionThreshold= " + val);
// _recognizer.GetPropertyNumber("HighConfidenceThreshold", ref val); // default 80+
// logfile.Log(". HighConfidenceThreshold= " + val);
// _recognizer.GetPropertyNumber("NormalConfidenceThreshold", ref val); // default 50+
// logfile.Log(". NormalConfidenceThreshold= " + val);
// _recognizer.GetPropertyNumber("LowConfidenceThreshold", ref val); // default 20+
// logfile.Log(". LowConfidenceThreshold= " + val);
// logfile.Log();
//
// _recognizer.SetPropertyNumber("CFGConfidenceRejectionThreshold", 0); // tried 100 ... results are identical to 0.
// _recognizer.GetPropertyNumber("CFGConfidenceRejectionThreshold", ref val);
// logfile.Log(". CFGConfidenceRejectionThreshold= " + val);
//
// _recognizer.SetPropertyNumber("HighConfidenceThreshold", 0);
// _recognizer.GetPropertyNumber("HighConfidenceThreshold", ref val);
// logfile.Log(". HighConfidenceThreshold= " + val);
//
// _recognizer.SetPropertyNumber("NormalConfidenceThreshold", 0);
// _recognizer.GetPropertyNumber("NormalConfidenceThreshold", ref val);
// logfile.Log(". NormalConfidenceThreshold= " + val);
//
// _recognizer.SetPropertyNumber("LowConfidenceThreshold", 0);
// _recognizer.GetPropertyNumber("LowConfidenceThreshold", ref val);
// logfile.Log(". LowConfidenceThreshold= " + val);
// logfile.Log();
internal void Start(string text)
{
#if DEBUG
logfile.Log();
logfile.Log("Start()");
#endif
// these don't all need to be cleared ->
Expected.Clear();
RatioWords_def =
RatioPhons_def =
RatioWords_enh =
RatioPhons_enh = 0.0;
_ars_def.Clear();
_ars_enh.Clear();
Confidence_def = 0f;
Confidence_def_count = 0;
if (SetRecognizer(FxeGeneratorF.That.GetRecognizer())) // <- workaround. See FxeGeneratorF.GetRecognizer()
{
_text = text;
#if DEBUG
logfile.Log(". _text= " + _text);
#endif
if (_text == String.Empty)
{
#if DEBUG
logfile.Log(". . DEFAULT - fire TtsStreamEnded event");
#endif
// if (TtsStreamEnded != null)
TtsStreamEnded();
}
else
{
#if DEBUG
logfile.Log(". . ENHANCED - call SpVoice.Speak()");
logfile.Log(". . _phoneConverter.LanguageId= " + _phoneConverter.LanguageId);
#endif
_voice.Speak(_text); // -> fire TtsEndStream when the TTS-stream ends.
_voice.WaitUntilDone(-1);
}
#if DEBUG
logfile.Log(". create (SpInProcRecoContext)_recoContext");
#endif
_recoContext = (SpInProcRecoContext)_recognizer.CreateRecoContext();
#if DEBUG
logfile.Log(". (SpInProcRecoContext)_recoContext CREATED");
#endif
_recoContext.FalseRecognition += rc_FalseRecognition;
_recoContext.Recognition += rc_Recognition;
_recoContext.EndStream += rc_EndStream;
#if DEBUG
_recoContext.Hypothesis += rc_Hypothesis;
_recoContext.StartStream += rc_StartStream;
_recoContext.SoundStart += rc_SoundStart;
_recoContext.SoundEnd += rc_SoundEnd;
_recoContext.PhraseStart += rc_PhraseStart;
_recoContext.Interference += rc_Interference;
// _recoContext.AudioLevel += rc_AudioLevel; // does not fire. SURPRISE!
// _recoContext.EventInterests = SpeechRecoEvents.SREAllEvents;
_recoContext.EventInterests = (SpeechRecoEvents)(int)SpeechRecoEvents.SREFalseRecognition
+ (int)SpeechRecoEvents.SRERecognition
+ (int)SpeechRecoEvents.SREStreamEnd
+ (int)SpeechRecoEvents.SREHypothesis
+ (int)SpeechRecoEvents.SREStreamStart
+ (int)SpeechRecoEvents.SRESoundStart
+ (int)SpeechRecoEvents.SRESoundEnd
+ (int)SpeechRecoEvents.SREPhraseStart
+ (int)SpeechRecoEvents.SREInterference;
// + (int)SpeechRecoEvents.SREAudioLevel; // does not fire. SURPRISE!
logfile.Log(". _recoContext.EventInterests= " + _recoContext.EventInterests);
#else
_recoContext.EventInterests = (SpeechRecoEvents)(int)SpeechRecoEvents.SREFalseRecognition
+ (int)SpeechRecoEvents.SRERecognition
+ (int)SpeechRecoEvents.SREStreamEnd;
#endif
/* https://docs.microsoft.com/en-us/previous-versions/windows/desktop/ee125206%28v%3dvs.85%29
* enum SpeechRecoEvents
* SREStreamEnd = 1
* SRESoundStart = 2
* SRESoundEnd = 4
* SREPhraseStart = 8
* SRERecognition = 16
* SREHypothesis = 32
* SREBookmark = 64
* SREPropertyNumChange = 128
* SREPropertyStringChange = 256
* SREFalseRecognition = 512
* SREInterference = 1024
* SRERequestUI = 2048
* SREStateChange = 4096
* SREAdaptation = 8192
* SREStreamStart = 16384
* SRERecoOtherContext = 32768
* SREAudioLevel = 65536
* SREPrivate = 262144
* SREAllEvents = 393215
*/
_generato = Generator.Dictati;
Generate();
#if DEBUG
logfile.Log("Start() DONE");
logfile.Log();
#endif
}
}
private void button3_Click(object sender, EventArgs e)
{
if (this.recRule != null)
{
return;
}
//this.button3.Enabled = false;
this.recRule = new SpInProcRecoContext();
bool hit = false;
foreach (SpObjectToken recPerson in this.recRule.Recognizer.GetRecognizers())
{
string lang = recPerson.GetAttribute("Language");
if (lang == "411")
{
this.recRule.Recognizer.Recognizer = recPerson;
hit = true;
break;
}
}
if (!hit)
{
MessageBox.Show("日本語認識が利用できません。");
}
else
{
Console.WriteLine("マイク取得開始\n");
Console.WriteLine(this.recRule.Recognizer.Status.ClsidEngine);
this.recRule.Recognizer.AudioInput = this.CreateMicrofon();
Console.WriteLine("マイク取得完了\n");
Console.WriteLine("デリゲート登録\n");
//認識の途中
this.recRule.Hypothesis +=
delegate(int streamNumber, object streamPosition, SpeechLib.ISpeechRecoResult result) {
string strText = result.PhraseInfo.GetText(0, -1, true);
this._SourceViewLabel.Text = strText;
};
//認識完了
this.recRule.Recognition +=
delegate(int streamNumber, object streamPosition, SpeechLib.SpeechRecognitionType srt, SpeechLib.ISpeechRecoResult isrr) {
string strText = isrr.PhraseInfo.GetText(0, -1, true);
this._ResultLabel.Text = strText;
};
//ストリームに何かデータが来た(?)
this.recRule.StartStream +=
delegate(int streamNumber, object streamPosition) {
this._SourceViewLabel.Text = "認識？";
this._ResultLabel.Text = "認識？";
};
//認識失敗
this.recRule.FalseRecognition +=
delegate(int streamNumber, object streamPosition, SpeechLib.ISpeechRecoResult isrr) {
this._ResultLabel.Text = "--ERROR!--";
};
Console.WriteLine("デリゲート登録完了\n");
Console.WriteLine("モデル作成\n");
//言語モデルの作成
this.recGrammerRule = this.recRule.CreateGrammar(0);
Console.WriteLine("モデル作成完了\n");
this.recGrammerRule.Reset(0);
//言語モデルのルールのトップレベルを作成する.
this.recGRGrammerRule = this.recGrammerRule.Rules.Add("TopLevelRule",
SpeechRuleAttributes.SRATopLevel | SpeechRuleAttributes.SRADynamic);
// 読み込む対象文字列をここですべて読み込んでおく必要がある
this.recGRGrammerRule.InitialState.AddWordTransition(null, "私は");
//ルールを反映させる。
this.recGrammerRule.Rules.Commit();
//音声認識開始。(トップレベルのオブジェクトの名前で SpeechRuleState.SGDSActive を指定する.)
this.recGrammerRule.CmdSetRuleState("TopLevelRule", SpeechRuleState.SGDSActive);
Console.WriteLine("音声認識開始");
}
}
