public SoundDataProcessor(KeyboardInputProcessor keyboard)
{
ConfigureLogManager();
keyboardProcessor = keyboard;
kinectAudioResourse = new KinectAudioSource();
kinectAudioResourse.FeatureMode = true;
kinectAudioResourse.AutomaticGainControl = false; //Important to turn this off for speech recognition
kinectAudioResourse.SystemMode = SystemMode.OptibeamArrayOnly; //No AEC for this sample
ri = SpeechRecognitionEngine.InstalledRecognizers().Where(r => r.Id == recognizerId).FirstOrDefault();
if (ri == null)
{
Trace.WriteLine("Could not find speech recognizer: {0}. Please refer to the sample requirements.", recognizerId);
throw new System.InvalidOperationException("Could not find speech recognizer: {0}. Please refer to the sample requirements." + recognizerId);
}
sre = new SpeechRecognitionEngine(ri.Id);
speechCommands = new Choices();
speechCommands.Add("jump");
speechCommands.Add("reload");
speechCommands.Add("aim");
speechCommands.Add("knife");
speechCommands.Add("grenade");
speechCommands.Add("menu");
speechCommands.Add("pause");
speechCommands.Add("select");
speechCommands.Add("okay");
speechCommands.Add("enter");
speechCommands.Add("up");
speechCommands.Add("down");
speechCommands.Add("left");
speechCommands.Add("right");
gb = new GrammarBuilder();
gb.Culture = ri.Culture;
gb.Append(speechCommands);
grammar = new Grammar(gb);
sre.LoadGrammar(grammar);
audioSourceStream = kinectAudioResourse.Start();
sre.SetInputToAudioStream(audioSourceStream,
new SpeechAudioFormatInfo(
EncodingFormat.Pcm, 16000, 16, 1,
32000, 2, null));
sre.RecognizeAsync(RecognizeMode.Multiple);
handleRequests = new Semaphore(0, (int)SemaphoreConstants.MAX_CONCURRENT_REQUESTS);
requestSoundData = new Semaphore((int)SemaphoreConstants.MAX_CONCURRENT_REQUESTS, (int)SemaphoreConstants.MAX_CONCURRENT_REQUESTS);
dataQueue = new Queue<SoundData>();
threadExit = false;
soundProcessorThread = new Thread(SoundProcessorModule);
soundProcessorThread.Name = "SoundProcessorThread";
soundProcessorThread.SetApartmentState(ApartmentState.MTA);
soundProcessorThread.Start();
}
void BuildSpeechEngine(RecognizerInfo rec)
{
_speechEngine = new SpeechRecognitionEngine(rec.Id);
var choices = new Choices();
choices.Add("venus");
choices.Add("mars");
choices.Add("earth");
choices.Add("jupiter");
choices.Add("sun");
var gb = new GrammarBuilder { Culture = rec.Culture };
gb.Append(choices);
var g = new Grammar(gb);
_speechEngine.LoadGrammar(g);
//recognized a word or words that may be a component of multiple complete phrases in a grammar.
_speechEngine.SpeechHypothesized += new EventHandler<SpeechHypothesizedEventArgs>(SpeechEngineSpeechHypothesized);
//receives input that matches any of its loaded and enabled Grammar objects.
_speechEngine.SpeechRecognized += new EventHandler<SpeechRecognizedEventArgs>(_speechEngineSpeechRecognized);
//receives input that does not match any of its loaded and enabled Grammar objects.
_speechEngine.SpeechRecognitionRejected += new EventHandler<SpeechRecognitionRejectedEventArgs>(_speechEngineSpeechRecognitionRejected);
//C# threads are MTA by default and calling RecognizeAsync in the same thread will cause an COM exception.
var t = new Thread(StartAudioStream);
t.Start();
}
public ComponentControl()
{
this.AudioSource = new KinectAudioSource();
this.AudioSource.FeatureMode = true;
this.AudioSource.AutomaticGainControl = false;
this.AudioSource.SystemMode = SystemMode.OptibeamArrayOnly;
this.AudioSource.BeamChanged += new EventHandler<BeamChangedEventArgs>(AudioSource_BeamChanged);
this.Recognizer = SpeechRecognitionEngine.InstalledRecognizers().Where(r => r.Id == RecognizerId).FirstOrDefault();
if(this.Recognizer == null) {
throw new Exception("Could not find Kinect speech recognizer");
}
this.Engine = new SpeechRecognitionEngine(Recognizer.Id);
this.Engine.UnloadAllGrammars();
this.LoadGrammer();
this.AudioStream = this.AudioSource.Start();
this.Engine.SetInputToAudioStream(this.AudioStream, new SpeechAudioFormatInfo(EncodingFormat.Pcm, 16000, 16, 1,
32000, 2, null));
this.Engine.SpeechHypothesized += new EventHandler<SpeechHypothesizedEventArgs>(Engine_SpeechHypothesized);
this.Engine.RecognizeAsync(RecognizeMode.Multiple);
Console.WriteLine("Speech recognition initialized");
}
public SpeechRecognizer()
{
this.recognizerInfo = GetKinectRecognizer();
if (this.recognizerInfo != null)
{
this.speechRecognitionEngine = new SpeechRecognitionEngine(this.recognizerInfo.Id);
this.speechRecognitionEngine.SpeechRecognized += this.SpeechRecognitionEngine_SpeechRecognized;
this.speechRecognitionEngine.SpeechDetected += this.SpeechRecognitionEngine_SpeechDetected;
}
}
public KinectSpeechService(ISensorService<KinectSensor> sensorService)
{
_sensorService = sensorService;
IReadOnlyList<AudioBeam> audioBeamList = _sensorService.Sensor.AudioSource.AudioBeams;
System.IO.Stream audioStream = audioBeamList[0].OpenInputStream();
// create the convert stream
_convertStream = new KinectAudioStream(audioStream);
_ri = TryGetKinectRecognizer();
}
public void InitializeSpeechRecognition(RecognizerInfo recognizer, ISpeechGrammar grammar)
{
RecognizerInfo ri = recognizer;
if (ri == null)
{
MessageBox.Show(
@"There was a problem initializing Speech Recognition.
Ensure you have the Microsoft Speech SDK installed.",
"Failed to load Speech SDK",
MessageBoxButton.OK,
MessageBoxImage.Error);
return;
}
try
{
speechRecognizer = new SpeechRecognitionEngine(ri.Id);
}
catch
{
MessageBox.Show(
@"There was a problem initializing Speech Recognition.
Ensure you have the Microsoft Speech SDK installed and configured.",
"Failed to load Speech SDK",
MessageBoxButton.OK,
MessageBoxImage.Error);
}
var phrases = new Choices();
foreach(String word in grammar.GrammarWords())
{
phrases.Add(word);
}
var gb = new GrammarBuilder();
//Specify the culture to match the recognizer in case we are running in a different culture.
gb.Culture = ri.Culture;
gb.Append(phrases);
// Create the actual Grammar instance, and then load it into the speech recognizer.
var g = new Grammar(gb);
speechRecognizer.LoadGrammar(g);
speechRecognizer.SpeechRecognized += SreSpeechRecognized;
speechRecognizer.SpeechHypothesized += SreSpeechHypothesized;
speechRecognizer.SpeechRecognitionRejected += SreSpeechRecognitionRejected;
this.readyTimer = new DispatcherTimer();
this.readyTimer.Tick += this.ReadyTimerTick;
this.readyTimer.Interval = new TimeSpan(0, 0, 4);
this.readyTimer.Start();
}
/// <summary>
/// Constructor.
/// </summary>
/// <param name="kinectSensor"></param>
public KinectSpeechRecognition(KinectSensor kinectSensor)
{
this.KinectSensor = kinectSensor;
this.RecognizerInfo = this.FindRecognizerInfo();
this.SpeechRecognitionEngine = new SpeechRecognitionEngine(this.RecognizerInfo); // this.RecognizerInfo.Id ?
// Build and load grammar.
this.Dictionary = this.BuildDictionary();
this.SpeechRecognitionEngine.LoadGrammar(this.BuildGrammar(this.Dictionary));
this.RecognizedChoice = "";
this.RecognizableChoices = new List<String>();
}
public CommandListener(RecognizerInfo recognizer)
{
Compose();
Recognizer = recognizer;
engine = new SpeechRecognitionEngine(recognizer);
engine.SetInputToDefaultAudioDevice();
engine.SpeechRecognized += sre_SpeechRecognized;
engine.SpeechDetected += engine_SpeechDetected;
engine.SpeechHypothesized += engine_SpeechHypothesized;
engine.SpeechRecognitionRejected += engine_SpeechRecognitionRejected;
}
public Grammar BuildGrammar(RecognizerInfo recInfo, string anchor)
{
Choices choices = new Choices();
this.anchor = anchor;
// Build General Command Grammar
choices.Add(string.Format("{0} What time is it?", anchor));
var gb = new GrammarBuilder();
gb.Culture = recInfo.Culture;
gb.Append(choices);
return new Grammar(gb);
}
public Recognizer( string name, Choices alternateChoices )
{
info = GetRecognizer( name );
engine = new SpeechRecognitionEngine( info.Id );
builder = new GrammarBuilder();
builder.Culture = info.Culture;
builder.Append( alternateChoices );
grammar = new Grammar( builder );
engine.LoadGrammar( grammar );
engine.SpeechRecognized += Recognizer_SpeechRecognized;
engine.SpeechHypothesized += Recognizer_SpeechHypothesized;
engine.SpeechRecognitionRejected += Recognizer_SpeechRecognitionRejected;
}
public SpeechRecognizer()
{
this.commandDelegates = new SpeechCommandReceived[SharedContent.CommandStrings.Length];
for (int i = 0; i < commandDelegates.Length; i++)
{
commandDelegates[i] = null;
}
ri = SpeechRecognitionEngine.InstalledRecognizers().Where(r => r.Id == SharedContent.RecognizerId).FirstOrDefault();
if (ri == null)
{
MessageBox.Show(
"Could not find speech recognizer: {0}. Please refer to the application requirements.", SharedContent.RecognizerId);
Environment.Exit(-1);
}
}
public Grammar BuildGrammar(RecognizerInfo recInfo, string anchor)
{
Choices choices = new Choices();
this.anchor = anchor;
// Build General Command Grammar
choices.Add(string.Format("{0} What's the weather right now?", anchor));
choices.Add(string.Format("{0} What's the weather for tomorrow?", anchor));
choices.Add(string.Format("{0} What was that?", anchor));
var gb = new GrammarBuilder();
gb.Culture = recInfo.Culture;
gb.Append(choices);
return new Grammar(gb);
}
public void Initialize()
{
if(initialized)
{
return;
}
KinectAudioSource audioSource = new KinectAudioSource(); // test Kinect
ri = SpeechRecognitionEngine.InstalledRecognizers().Where(r => r.Id == RECOGNIZER_ID).FirstOrDefault();
if (ri == null)
{
throw new Exception("Could not find speech recognizer " + RECOGNIZER_ID + ".");
}
initialized = true;
}
/// <summary>
/// Method name reflects where it is supposed to be called. Loads/initializes all the resources
/// of our speech recognizer.
/// </summary>
public void LoadContent()
{
foreach (var potentialSensor in KinectSensor.KinectSensors)
{
if (potentialSensor.Status == KinectStatus.Connected)
{
this.Sensor = potentialSensor;
break;
}
}
if (this.Sensor != null)
{
try
{
// Start the sensor!
this.Sensor.Start();
}
catch (IOException)
{
// Some other application is streaming from the same Kinect sensor
this.Sensor = null;
}
}
if (this.Sensor == null)
{
return;
}
RecognizerInfo = GetKinectRecognizer();
if (RecognizerInfo != null)
{
this.SpeechEngine = new SpeechRecognitionEngine(RecognizerInfo.Id);
SetupGrammar();
SpeechEngine.SetInputToAudioStream(
Sensor.AudioSource.Start(), new SpeechAudioFormatInfo(EncodingFormat.Pcm, 16000, 16, 1, 32000, 2, null));
SpeechEngine.RecognizeAsync(RecognizeMode.Multiple);
}
}
public Grammar BuildGrammar(RecognizerInfo recInfo, string anchor)
{
Choices choices = new Choices();
this.anchor = anchor;
// Build General Command Grammar
choices.Add(string.Format("{0} What's your name?", anchor));
choices.Add(string.Format("{0} Wake up", anchor));
choices.Add(string.Format("{0} You suck", anchor));
choices.Add(string.Format("{0} Shut Up", anchor));
choices.Add(string.Format("{0} What was that?", anchor));
choices.Add(string.Format("{0} What did you say?", anchor));
choices.Add(string.Format("{0} Move upwards", anchor));
choices.Add(string.Format("{0} Give me your status", anchor));
var gb = new GrammarBuilder();
gb.Culture = recInfo.Culture;
gb.Append(choices);
return new Grammar(gb);
}
public Grammar BuildGrammar(RecognizerInfo recInfo, string anchor)
{
Choices choices = new Choices();
List<ITunesTrack> trackList = itc.GetLibrary();
this.anchor = anchor;
// Build Artist Grammar
List<string> artistList = trackList.Select(song => song.Artist).Distinct().ToList();
foreach (var artist in artistList)
{
if (artist != null)
{
choices.Add(string.Format("{0} play artist {1}", anchor, artist));
}
}
// Build Song Grammar
List<string> songList = trackList.Select(song => song.Name).Distinct().ToList();
foreach (var song in songList)
{
if (song != null)
{
var treatedSongName = song.Replace("\"", "");
choices.Add(string.Format("{0} play song {1}", anchor, treatedSongName));
}
}
// Build General Command Grammar
choices.Add(string.Format("{0} play", anchor));
choices.Add(string.Format("{0} next", anchor));
choices.Add(string.Format("{0} previous", anchor));
choices.Add(string.Format("{0} pause", anchor));
choices.Add(string.Format("{0} stop", anchor));
var gb = new GrammarBuilder();
gb.Culture = recInfo.Culture;
gb.Append(choices);
return new Grammar(gb);
}
void estableceReconocimiento()
{
ri = obtenerLP();
if (ri != null)
{
speechengine = new SpeechRecognitionEngine(ri.Id);
opciones = new Choices();
opciones.Add(new SemanticResultValue("Angulo Kinect menos veinticinco", "KINECT25NEGATIVO"));
opciones.Add(new SemanticResultValue("Angulo Kinect menos veinte", "KINECT20NEGATIVO"));
opciones.Add(new SemanticResultValue("Angulo Kinect menos quince", "KINECT15NEGATIVO"));
opciones.Add(new SemanticResultValue("Angulo Kinect menos diez", "KINECT10NEGATIVO"));
opciones.Add(new SemanticResultValue("Angulo Kinect menos cinco", "KINECT5NEGATIVO"));
opciones.Add(new SemanticResultValue("Angulo Kinect cero", "KINECT0"));
opciones.Add(new SemanticResultValue("Angulo Kinect cinco", "KINECT5"));
opciones.Add(new SemanticResultValue("Angulo Kinect diez", "KINECT10"));
opciones.Add(new SemanticResultValue("Angulo Kinect quince", "KINECT15"));
opciones.Add(new SemanticResultValue("Angulo Kinect veinte", "KINECT20"));
opciones.Add(new SemanticResultValue("Angulo Kinect veinticinco", "KINECT25"));
opciones.Add(new SemanticResultValue("Angulo Kinect restablecer", "KINECT0"));
//Esta variable creará todo el conjunto de frases y palabras en base a nuestro lenguaje elegido en la variable ri
grammarb = new GrammarBuilder { Culture = ri.Culture };
//Agregamos las opciones de palabras y frases a grammarb
grammarb.Append(opciones);
grammar = new Grammar(grammarb);
speechengine.LoadGrammar(grammar);
speechengine.SpeechRecognized += new EventHandler<SpeechRecognizedEventArgs>(speechengine_SpeechRecognized);
//speechengine inicia la entrada de datos de audio
speechengine.SetInputToAudioStream(miKinect.AudioSource.Start(), new SpeechAudioFormatInfo(EncodingFormat.Pcm, 16000, 16, 1, 32000, 2, null));
speechengine.RecognizeAsync(RecognizeMode.Multiple);
}
}
public SpeechManager()
{
// No microphones have been initialized yet
sensorActive = false;
// If there's a Kinect available, set the recognizerInfo to the one it provides
this.recognizerInfo = GetKinectRecognizer();
if (this.recognizerInfo != null)
{
this.speechRecognitionEngine = new SpeechRecognitionEngine(this.recognizerInfo.Id);
Console.WriteLine("Speech Recognition Engine set to Kinect Recognizer");
}
// Otherwise, use a new recognition engine for use with a default microhpone
else
{
this.recognizerInfo = SpeechRecognitionEngine.InstalledRecognizers().FirstOrDefault();
this.speechRecognitionEngine = new SpeechRecognitionEngine();
Console.WriteLine("Speech Recognition Engine set to default microphone");
}
this.speechRecognitionEngine.SpeechRecognized += this.speechRecognized;
this.speechRecognitionEngine.SpeechDetected += this.speechDetected;
}
/// <summary>
/// Default constructor. Sets up the voice recognizer with default settings.
///
/// Namely, default options are: en-US, default input device, listen always, confidence level at .90
/// </summary>
public VoiceRecognizer()
{
if (SpeechRecognitionEngine.InstalledRecognizers().Count == 0)
{
SetupError = "You don't appear to have any Microsoft Speech Recognizer packs installed on your system.";
State = VoiceRecognizerState.Error;
return;
}
try
{
var installedRecognizers = SpeechRecognitionEngine.InstalledRecognizers();
RecognizerInfo speechRecognizer = null;
switch (CultureInfo.InstalledUICulture.Name)
{
case "en-GB":
speechRecognizer = (installedRecognizers.FirstOrDefault(x => x.Culture.Name == "en-GB") ?? installedRecognizers.FirstOrDefault(x => x.Culture.TwoLetterISOLanguageName == "en"));
break;
case "en-US":
default:
speechRecognizer = installedRecognizers.FirstOrDefault(x => x.Culture.TwoLetterISOLanguageName == "en");
break;
}
if (speechRecognizer == null)
{
SetupError = String.Format("You don't appear to have the {0} Speech Recognizer installed. Articulate requires this recognizer to be present in order to function correctly.", "English");
State = VoiceRecognizerState.Error;
return;
}
// Setup members
ConfidenceLock = new Object();
EngineShuttingDown = new AutoResetEvent(false);
State = VoiceRecognizerState.Paused;
// Create a new SpeechRecognitionEngine instance.
Engine = new SpeechRecognitionEngine(speechRecognizer);
try
{
// Setup the audio device
Engine.SetInputToDefaultAudioDevice();
}
catch (InvalidOperationException ex)
{
// No default input device
Trace.WriteLine(ex.Message);
SetupError = "Check input device.\n\n";
State = VoiceRecognizerState.Error;
return;
}
// Set the confidence setting
ConfidenceMargin = 90;
// Create the Grammar instance and load it into the speech recognition engine.
Grammar g = new Grammar(CommandPool.BuildSrgsGrammar(speechRecognizer.Culture));
Engine.LoadGrammar(g);
// Register a handlers for the SpeechRecognized and SpeechRecognitionRejected event
Engine.SpeechRecognized += sre_SpeechRecognized;
Engine.SpeechRecognitionRejected += sre_SpeechRecognitionRejected;
Engine.RecognizeCompleted += sre_RecognizeCompleted;
StartListening();
}
catch (Exception ex)
{
// Something went wrong setting up the voiceEngine.
Trace.WriteLine(ex.Message);
SetupError = String.Format("{0}\nCurrent Culture: {1}\nAvailable Recognizers: {2}\nStack Trace:\n{3}", ex.Message, CultureInfo.InstalledUICulture.Name, SpeechRecognitionEngine.InstalledRecognizers().Select(x => x.Culture.Name).Aggregate((x, y) => x + ", " + y), ex.StackTrace);
State = VoiceRecognizerState.Error;
}
}
private void InitializeSpeechRecognition()
{
RecognizerInfo ri = GetKinectRecognizer();
if (ri == null)
{
MessageBox.Show(
@"There was a problem initializing Speech Recognition.
Ensure you have the Microsoft Speech SDK installed.",
"Failed to load Speech SDK",
MessageBoxButton.OK,
MessageBoxImage.Error);
return;
}
try
{
speechRecognizer = new SpeechRecognitionEngine(ri.Id);
}
catch
{
MessageBox.Show(
@"There was a problem initializing Speech Recognition.
Ensure you have the Microsoft Speech SDK installed and configured.",
"Failed to load Speech SDK",
MessageBoxButton.OK,
MessageBoxImage.Error);
}
var firstword = new Choices();
foreach (string value in firstWord.Keys)
{
firstword.Add(value);
}
GrammarBuilder firstword1 = new Choices(new string[] { "seir" });
firstword1.Append("surita");
firstword1.Append("fimm");
firstword1.Append("groenn");
firstword1.Append("vindr");
GrammarBuilder firstword2 = new Choices(new string[] { "oss" });
firstword2.Append("naeo");
firstword2.Append("fyor");
firstword2.Append("regin");
firstword2.Append("tinada");
firstword2.Append("varindo");
firstword2.Append("yotsun");
GrammarBuilder exit = new Choices(new string[] { "nox" });
exit.Append("eterna");
Choices first = new Choices();
first.Add(new Choices(new GrammarBuilder[] { firstword1, firstword2, exit }));
var gb = new GrammarBuilder();
gb.Culture = ri.Culture;
gb.Append(first);
var g = new Grammar(gb);
speechRecognizer.LoadGrammar(g);
speechRecognizer.SpeechRecognized += speechRecognizer_SpeechRecognized;
speechRecognizer.SpeechHypothesized += speechRecognizer_SpeechHypothesized;
speechRecognizer.SpeechRecognitionRejected += speechRecognizer_SpeechRecognitionRejected;
if (Kinect == null || speechRecognizer == null)
{
return;
}
var audioSource = this.Kinect.AudioSource;
audioSource.BeamAngleMode = BeamAngleMode.Adaptive;
var kinectStream = audioSource.Start();
speechRecognizer.SetInputToAudioStream(
kinectStream, new SpeechAudioFormatInfo(EncodingFormat.Pcm, 16000, 16, 1, 32000, 2, null));
speechRecognizer.RecognizeAsync(RecognizeMode.Multiple);
}
/// <summary>
/// Kinect enabled apps should customize which Kinect services it initializes here.
/// </summary>
/// <param name="kinectSensorManager"></param>
/// <param name="sensor"></param>
private void InitializeKinectServices(KinectSensorManager kinectSensorManager, KinectSensor sensor)
{
// Application should enable all streams first.
// configure the color stream
kinectSensorManager.ColorFormat = ColorImageFormat.RgbResolution640x480Fps30;
kinectSensorManager.ColorStreamEnabled = true;
// configure the depth stream
kinectSensorManager.DepthStreamEnabled = true;
kinectSensorManager.TransformSmoothParameters =
new TransformSmoothParameters
{
Smoothing = 0.5f,
Correction = 0.5f,
Prediction = 0.5f,
JitterRadius = 0.05f,
MaxDeviationRadius = 0.04f
};
// configure the skeleton stream
sensor.SkeletonFrameReady += OnSkeletonFrameReady;
kinectSensorManager.SkeletonStreamEnabled = true;
// initialize the gesture recognizer
gestureController = new GestureController();
gestureController.GestureRecognized += OnGestureRecognized;
kinectSensorManager.KinectSensorEnabled = true;
RecognizerInfo ri = GetKinectRecognizer();
if (null != ri)
{
// recognitionSpans = new List<Span> { forwardSpan, backSpan, rightSpan, leftSpan };
this.speechEngine = new SpeechRecognitionEngine(ri.Id);
var directions = new Choices();
//directions.Add(new SemanticResultValue("forward", "FORWARD"));
//directions.Add(new SemanticResultValue("forwards", "FORWARD"));
//directions.Add(new SemanticResultValue("straight", "FORWARD"));
//directions.Add(new SemanticResultValue("backward", "BACKWARD"));
//directions.Add(new SemanticResultValue("backwards", "BACKWARD"));
//directions.Add(new SemanticResultValue("back", "BACKWARD"));
//directions.Add(new SemanticResultValue("turn left", "LEFT"));
//directions.Add(new SemanticResultValue("turn right", "RIGHT"));
directions.Add(new SemanticResultValue("lights on", "LIGHTS_ON"));
directions.Add(new SemanticResultValue("lights off", "LIGHTS_OFF"));
directions.Add(new SemanticResultValue("screen up", "SCREEN_UP"));
directions.Add(new SemanticResultValue("screen down", "SCREEN_DOWN"));
directions.Add(new SemanticResultValue("projector on", "PROJECTOR_ON"));
directions.Add(new SemanticResultValue("projector off", "PROJECTOR_OFF"));
directions.Add(new SemanticResultValue("presentation mode", "PRESENTATION_MODE"));
directions.Add(new SemanticResultValue("blackboard mode", "BLACKBOARD_MODE"));
var gb = new GrammarBuilder {
Culture = ri.Culture
};
gb.Append(directions);
var g = new Grammar(gb);
// Create a grammar from grammar definition XML file.
//using (var memoryStream = new MemoryStream(Encoding.ASCII.GetBytes(Properties.Resources.SpeechGrammar)))
//{
// var g = new Grammar(memoryStream);
// speechEngine.LoadGrammar(g);
//}
speechEngine.LoadGrammar(g);
speechEngine.SpeechRecognized += SpeechRecognized;
speechEngine.SpeechRecognitionRejected += SpeechRejected;
speechEngine.SetInputToAudioStream(sensor.AudioSource.Start(), new SpeechAudioFormatInfo(EncodingFormat.Pcm, 16000, 16, 1, 32000, 2, null));
speechEngine.RecognizeAsync(RecognizeMode.Multiple);
}
else
{
//this.statusBarText.Text = Properties.Resources.NoSpeechRecognizer;
}
if (!kinectSensorManager.KinectSensorAppConflict)
{
// addition configuration, as needed
}
}
public void setup(string[] args /*, StreamWriter writer*/)
{
kinectSensor = KinectSensor.KinectSensors[0];
//output = writer;
source = kinectSensor.AudioSource;
//source.FeatureMode = true;
source.AutomaticGainControlEnabled = false; //Important to turn this off for speech recognition
source.EchoCancellationMode = EchoCancellationMode.None; //SystemMode.OptibeamArrayOnly; //No AEC for this sample
//RecognizerInfo ri = SpeechRecognitionEngine.InstalledRecognizers().Where(r => r.Id == RecognizerId).FirstOrDefault();
RecognizerInfo ri = getKinectRecognizer();
if (ri == null)
{
//Console.WriteLine("Could not find speech recognizer: {0}. Please refer to the sample requirements.", RecognizerId);
Console.WriteLine("Could not find speech recognizer. Please refer to the sample requirements.");
return;
}
Console.WriteLine("Using: {0}", ri.Name);
//using (var sre = new SpeechRecognitionEngine(ri.Id))
sre = new SpeechRecognitionEngine(ri.Id);
var words = new Choices();
foreach (string w in args)
{
words.Add(w);
}
gb = new GrammarBuilder();
//Specify the culture to match the recognizer in case we are running in a different culture.
gb.Culture = ri.Culture;
gb.Append(words);
// Create the actual Grammar instance, and then load it into the speech recognizer.
g = new Grammar(gb);
sre.LoadGrammar(g);
sre.SpeechRecognized += SreSpeechRecognized;
sre.SpeechHypothesized += SreSpeechHypothesized;
sre.SpeechRecognitionRejected += SreSpeechRecognitionRejected;
s = source.Start();
sre.SetInputToAudioStream(s,
new SpeechAudioFormatInfo(
EncodingFormat.Pcm, 16000, 16, 1,
32000, 2, null));
Console.Write("Recognizing: ");
foreach (string w in args)
{
Console.Write(w + " ");
}
Console.Write("\n");
startRecog();
}
public Recognizer()
{
RecognizerInfo ri = SpeechRecognitionEngine.InstalledRecognizers().Where(r => r.Id == RecognizerId).FirstOrDefault();
if (ri == null)
{
return;
}
sre = new SpeechRecognitionEngine(ri.Id);
// Build a simple grammar of shapes, colors, and some simple program control
var single = new Choices();
foreach (var phrase in SinglePhrases)
{
single.Add(phrase.Key);
}
var gameplay = new Choices();
foreach (var phrase in GameplayPhrases)
{
gameplay.Add(phrase.Key);
}
var shapes = new Choices();
foreach (var phrase in ShapePhrases)
{
shapes.Add(phrase.Key);
}
var colors = new Choices();
foreach (var phrase in ColorPhrases)
{
colors.Add(phrase.Key);
}
var coloredShapeGrammar = new GrammarBuilder();
coloredShapeGrammar.Append(colors);
coloredShapeGrammar.Append(shapes);
var objectChoices = new Choices();
objectChoices.Add(gameplay);
objectChoices.Add(shapes);
objectChoices.Add(colors);
objectChoices.Add(coloredShapeGrammar);
var actionGrammar = new GrammarBuilder();
actionGrammar.AppendWildcard();
actionGrammar.Append(objectChoices);
var allChoices = new Choices();
allChoices.Add(actionGrammar);
allChoices.Add(single);
var gb = new GrammarBuilder();
gb.Append(allChoices);
var g = new Grammar(gb);
sre.LoadGrammar(g);
sre.SpeechRecognized += sre_SpeechRecognized;
sre.SpeechHypothesized += sre_SpeechHypothesized;
sre.SpeechRecognitionRejected += new EventHandler <SpeechRecognitionRejectedEventArgs>(sre_SpeechRecognitionRejected);
var t = new Thread(StartDMO);
t.Start();
valid = true;
}
private void LoadContent()
{
kinectDevice = new Runtime();
kinectDevice.Initialize(RuntimeOptions.UseDepthAndPlayerIndex | RuntimeOptions.UseSkeletalTracking | RuntimeOptions.UseColor);
kinectDevice.SkeletonEngine.TransformSmooth = true;
kinectDevice.VideoStream.Open(ImageStreamType.Video, 2, ImageResolution.Resolution640x480, ImageType.Color);
kinectDevice.DepthStream.Open(ImageStreamType.Depth, 2, ImageResolution.Resolution320x240, ImageType.DepthAndPlayerIndex);
kinectDevice.SkeletonFrameReady += new EventHandler<SkeletonFrameReadyEventArgs>(kinectDevice_SkeletonFrameReady);
kinectDevice.VideoFrameReady += new EventHandler<ImageFrameReadyEventArgs>(kinectDevice_VideoFrameReady);
kinectAudio = new KinectAudioSource();
kinectAudio.FeatureMode = true;
kinectAudio.AutomaticGainControl = false;
kinectAudio.SystemMode = SystemMode.OptibeamArrayOnly;
ri = SpeechRecognitionEngine.InstalledRecognizers().Where(r => r.Id == RecognizerId).FirstOrDefault();
sre = new SpeechRecognitionEngine(ri.Id);
audioChoices = new Choices();
audioChoices.Add("stop");
audioChoices.Add("start");
audioChoices.Add("kinect shutdown");
audioChoices.Add("reset time");
audioChoices.Add("spree");
audioChoices.Add("reset hand");
audioChoices.Add("faster");
audioChoices.Add("slower");
grammerBuilder = new GrammarBuilder();
grammerBuilder.Culture = ri.Culture;
grammerBuilder.Append(audioChoices);
grammer = new Grammar(grammerBuilder);
sre.LoadGrammar(grammer);
sre.SpeechRecognized += new EventHandler<SpeechRecognizedEventArgs>(sre_SpeechRecognized);
sre.SetInputToAudioStream(kinectAudio.Start(), new SpeechAudioFormatInfo( EncodingFormat.Pcm, 16000,16,1,32000,2, null));
sre.RecognizeAsync(RecognizeMode.Multiple);
player = new NinjaPlayer(this);
backGround = Content.Load<Texture2D>("wood_paneling");
font = Content.Load<SpriteFont>("font");
sound = new SoundPlayer();
}
// Connect to the Kinect sensor and begin processing events.
public void InitializeKinect()
{
this.sensor = null;
// Look through all sensors and start the first connected one.
// This requires that a Kinect is connected at the time of app startup.
// To make your app robust against plug/unplug,
// it is recommended to use KinectSensorChooser provided in Microsoft.Kinect.Toolkit (See components in Toolkit Browser).
foreach (var potentialSensor in KinectSensor.KinectSensors)
{
if (potentialSensor.Status == KinectStatus.Connected)
{
this.sensor = potentialSensor;
break; // Connect to first Kinect.
}
}
if (null == this.sensor)
{
ErrorLogging.AddMessage(ErrorLogging.LoggingLevel.Error, "InitializeKinect() failed, not connected to Kinect sensor.");
return;
}
else
{
// Turn on the skeleton stream to receive skeleton frames
this.sensor.SkeletonStream.Enable();
// Add an event handler to be called whenever there is new color frame data
SkeletonFrameReady += SensorSkeletonFrameReady;
// Start the sensor!
try
{
this.sensor.Start();
}
catch (IOException)
{
ErrorLogging.AddMessage(ErrorLogging.LoggingLevel.Error, "InitializeKinect() failed, unable to Start Kinect sensor.");
this.sensor = null;
return;
}
}
RecognizerInfo ri = GetKinectRecognizer();
if (null != ri)
{
this.speechEngine = new SpeechRecognitionEngine(ri.Id);
/****************************************************************
*
* Use this code to create grammar programmatically rather than from
* a grammar file.
*
* var directions = new Choices();
* directions.Add(new SemanticResultValue("forward", "FORWARD"));
* directions.Add(new SemanticResultValue("forwards", "FORWARD"));
* directions.Add(new SemanticResultValue("straight", "FORWARD"));
* directions.Add(new SemanticResultValue("backward", "BACKWARD"));
* directions.Add(new SemanticResultValue("backwards", "BACKWARD"));
* directions.Add(new SemanticResultValue("back", "BACKWARD"));
* directions.Add(new SemanticResultValue("turn left", "LEFT"));
* directions.Add(new SemanticResultValue("turn right", "RIGHT"));
*
* var gb = new GrammarBuilder { Culture = ri.Culture };
* gb.Append(directions);
*
* var g = new Grammar(gb);
*
****************************************************************/
// Create a grammar from grammar definition XML file.
using (var memoryStream = new MemoryStream(Encoding.ASCII.GetBytes(Properties.Resources.SpeechGrammar)))
{
var g = new Grammar(memoryStream);
speechEngine.LoadGrammar(g);
}
speechEngine.SpeechRecognized += SpeechRecognized;
speechEngine.SpeechRecognitionRejected += SpeechRejected;
robotSpeech.SpeakStarted += SpeakStarted;
robotSpeech.SpeakCompleted += SpeakCompleted;
// For long recognition sessions (a few hours or more), it may be beneficial to turn off adaptation of the acoustic model.
// This will prevent recognition accuracy from degrading over time.
////speechEngine.UpdateRecognizerSetting("AdaptationOn", 0);
speechEngine.SetInputToAudioStream(
sensor.AudioSource.Start(), new SpeechAudioFormatInfo(EncodingFormat.Pcm, 16000, 16, 1, 32000, 2, null));
speechEngine.RecognizeAsync(RecognizeMode.Multiple);
}
else
{
ErrorLogging.AddMessage(ErrorLogging.LoggingLevel.Error, "InitializeKinect() failed, no speech recognizer.");
}
ErrorLogging.AddMessage(ErrorLogging.LoggingLevel.Info, "InitializeKinect() succeeded, Kinect sensor is ready.");
}
// Execute startup tasks
private void WindowLoaded(object sender, RoutedEventArgs e)
{
// Look through all sensors and start the first connected one.
// This requires that a Kinect is connected at the time of app startup.
// To make your app robust against plug/unplug,
// it is recommended to use KinectSensorChooser provided in Microsoft.Kinect.Toolkit (See components in Toolkit Browser).
foreach (var potentialSensor in KinectSensor.KinectSensors)
{
if (potentialSensor.Status == KinectStatus.Connected)
{
this.sensor = potentialSensor;
break;
}
}
if (null != this.sensor)
{
// Skeleton
// Create the drawing group we'll use for drawing
this.drawingGroupSkeleton = new DrawingGroup();
// Create an image source that we can use in our image control
this.imageSourceSkeleton = new DrawingImage(this.drawingGroupSkeleton);
// Display the drawing using our image control
ImageSkeleton.Source = this.imageSourceSkeleton;
// Turn on the skeleton stream to receive skeleton frames
this.sensor.SkeletonStream.Enable();
// Add an event handler to be called whenever there is new color frame data
this.sensor.SkeletonFrameReady += this.SensorSkeletonFrameReady;
// Ball
// Create the drawing group we'll use for drawing
this.drawingGroupBall = new DrawingGroup();
// Create an image source that we can use in our image control
this.imageSourceBall = new DrawingImage(this.drawingGroupBall);
// Display the drawing using our image control
ImageBall.Source = this.imageSourceBall;
// Turn on the skeleton stream to receive skeleton frames
ball.vel = new Vector(0, initialVel);
ball.pos = new Point();
// Racket
racket1.posList = new List <Point>();
racket1.thetaList = new List <float>();
racket2.posList = new List <Point>();
racket2.thetaList = new List <float>();
// RGB
// Turn on the color stream to receive color frames
this.sensor.ColorStream.Enable(ColorImageFormat.RgbResolution640x480Fps30);
// Allocate space to put the pixels we'll receive
this.colorPixels = new byte[this.sensor.ColorStream.FramePixelDataLength];
// This is the bitmap we'll display on-screen
this.colorBitmap = new WriteableBitmap(this.sensor.ColorStream.FrameWidth, this.sensor.ColorStream.FrameHeight, 96.0, 96.0, PixelFormats.Bgr32, null);
// Set the image we display to point to the bitmap where we'll put the image data
this.ImageRGB.Source = this.colorBitmap;
// Add an event handler to be called whenever there is new color frame data
this.sensor.ColorFrameReady += this.SensorColorFrameReady;
// Start the sensor!
try
{
this.sensor.Start();
}
catch (IOException)
{
this.sensor = null;
}
}
if (null == this.sensor)
{
this.statusBarText.Text = Properties.Resources.NoKinectReady;
}
// v----- Speech recognizer -----v //
RecognizerInfo ri = GetKinectRecognizer();
if (null != ri)
{
this.speechEngine = new SpeechRecognitionEngine(ri.Id);
var directions = new Choices();
directions.Add(new SemanticResultValue("pelota", "PELOTA")); // Grammar, Command
directions.Add(new SemanticResultValue("reset", "RESET"));
var gb = new GrammarBuilder {
Culture = ri.Culture
};
gb.Append(directions);
var g = new Grammar(gb);
// Create a grammar not from grammar definition XML file.
speechEngine.LoadGrammar(g);
speechEngine.SpeechRecognized += SpeechRecognized;
//speechEngine.SpeechRecognitionRejected += SpeechRejected;
// For long recognition sessions (a few hours or more), it may be beneficial to turn off adaptation of the acoustic model.
// This will prevent recognition accuracy from degrading over time.
////speechEngine.UpdateRecognizerSetting("AdaptationOn", 0);
speechEngine.SetInputToAudioStream(
sensor.AudioSource.Start(), new SpeechAudioFormatInfo(EncodingFormat.Pcm, 16000, 16, 1, 32000, 2, null));
speechEngine.RecognizeAsync(RecognizeMode.Multiple);
}
// ^----- Speech recognizer -----^ //
}
static bool CreateRecognizer()
{
// Was the SRE already defined ?
if (recognizer != null)
{
// Yes
recognizer = null;
}
try
{
recogInfo = null;
Console.WriteLine("\nSpeech Processor: The following Speech Recognizers are available:");
foreach (RecognizerInfo ri in SpeechRecognitionEngine.InstalledRecognizers())
{
Console.Write(" "); Console.WriteLine(ri.Description);
if (ri.Culture.Name.Equals(strCulture))
{
recogInfo = ri;
}
}
if (recogInfo != null)
{
recognizer = new SpeechRecognitionEngine(recogInfo);
Console.WriteLine("\nUsing recognizer " + recognizer.RecognizerInfo.Name + " for culture " + strCulture);
// Attach event handlers.
recognizer.SpeechDetected +=
new EventHandler<SpeechDetectedEventArgs>(
SpeechDetectedHandler);
/* recognizer.SpeechHypothesized +=
new EventHandler<SpeechHypothesizedEventArgs>(SpeechHypothesizedHandler);
recognizer.SpeechRecognitionRejected +=
new EventHandler<SpeechRecognitionRejectedEventArgs>(SpeechRecognitionRejectedHandler);
*/
recognizer.SpeechRecognized +=
new EventHandler<SpeechRecognizedEventArgs>(
SpeechRecognizedHandler);
recognizer.RecognizeCompleted +=
new EventHandler<RecognizeCompletedEventArgs>(
RecognizeCompletedHandler);
recognizer.RecognizerUpdateReached +=
new EventHandler<RecognizerUpdateReachedEventArgs>(RecognizerUpdateReachedHandler);
// Assign input to the recognizer and start asynchronous
// recognition.
recognizer.SetInputToDefaultAudioDevice();
return (true);
}
else
{
Console.WriteLine("\nSpeech Processor: could not find a recognizer for culture ..." + strCulture);
}
}
catch (Exception ex)
{
Console.WriteLine("\nSpeech Processor: unable to create Speech Recognition Engine");
}
return (false);
}
void conectaActiva()
{
//Nos aseguramos que la cuenta de sensores conectados sea de al menos 1
if (KinectSensor.KinectSensors.Count > 0)
{
//Checamos que la variable _sensor sea nula
if (this._sensor == null)
{
//Asignamos el primer sensor Kinect a nuestra variable
this._sensor = KinectSensor.KinectSensors[0];
if (this._sensor != null)
{
try
{
//Iniciamos el dispositivo Kinect
this._sensor.Start();
//Esto es opcional pero ayuda a colocar el dispositivo Kinect a un cierto angulo de inclinacion, desde -27 a 27
_sensor.ElevationAngle = 3;
//Informamos que se ha conectado e inicializado correctamente el dispositivo Kinect
//El source nuestro control imagen mandara llamar a la imagen 1.jpg , lo mismo se hace para las demas opciones
}
catch (Exception ex)
{
//Si hay algun error lo mandamos en el TextBlock statusK
}
//Creamos esta variable ri que tratara de encontrar un language pack valido haciendo uso del metodo obtenerLP
RecognizerInfo ri = obtenerLP();
//Si se encontro el language pack requerido lo asignaremos a nuestra variable speechengine
if (ri != null)
{
this.speechengine = new SpeechRecognitionEngine(ri.Id);
//Creamos esta variable opciones la cual almacenara las opciones de palabras o frases que podran ser reconocidas por el dispositivo
var opciones = new Choices();
//Comenzamos a agregar las opciones comenzando por el valor de opcion que tratamos reconocer y una llave que identificara a ese
//valor
//Por ejemplo en esta linea "uno" es el valor de opcion y "UNO" es la llave
opciones.Add("encendido", "ENCENDIDO");
//En esta linea "unidad" es el valor de opcion y "UNO" es la llave
opciones.Add("apagado", "APAGAR");
//En esta linea "dos" es el valor de opcion y "DOS" es la llave
opciones.Add("adelante", "ADELANTE");
//En esta linea "windows ocho" es el valor de opcion y "TRES" es la llave y asi sucesivamente
opciones.Add("atrás", "BACK");
opciones.Add("subir", "SUBIR");
opciones.Add("bajar", "BAJAR");
opciones.Add(new SemanticResultValue("prende", "ENCENDIDO"));
opciones.Add(new SemanticResultValue("apaga", "APAGADO"));
opciones.Add(new SemanticResultValue("sube", "SUBIR"));
opciones.Add(new SemanticResultValue("baja", "BAJAR"));
//Esta variable creará todo el conjunto de frases y palabras en base a nuestro lenguaje elegido en la variable ri
var grammarb = new GrammarBuilder {
Culture = ri.Culture
};
//Agregamos las opciones de palabras y frases a grammarb
grammarb.Append(opciones);
//Creamos una variable de tipo Grammar utilizando como parametro a grammarb
var grammar = new Grammar(grammarb);
//Le decimos a nuestra variable speechengine que cargue a grammar
this.speechengine.LoadGrammar(grammar);
//mandamos llamar al evento SpeechRecognized el cual se ejecutara cada vez que una palabra sea detectada
speechengine.SpeechRecognized += new EventHandler <SpeechRecognizedEventArgs>(speechengine_SpeechRecognized);
//speechengine inicia la entrada de datos de tipo audio
speechengine.SetInputToAudioStream(_sensor.AudioSource.Start(), new SpeechAudioFormatInfo(EncodingFormat.Pcm, 16000, 16, 1,
32000, 2, null));
speechengine.RecognizeAsync(RecognizeMode.Multiple);
}
}
else
{
// statusK1.Content = "Conectado";
}
}
}
}
static bool CreateRecognizer()
{
// Was the SRE already defined ?
if (recognizer != null)
{
// Yes
recognizer = null;
}
try
{
recogInfo = null;
Console.WriteLine("\nSpeech Processor: The following Speech Recognizers are available:");
foreach (RecognizerInfo ri in SpeechRecognitionEngine.InstalledRecognizers())
{
Console.Write(" "); Console.WriteLine(ri.Description);
if (ri.Culture.Name.Equals(strCulture))
{
recogInfo = ri;
}
}
if (recogInfo != null)
{
recognizer = new SpeechRecognitionEngine(recogInfo);
Console.WriteLine("\nUsing recognizer " + recognizer.RecognizerInfo.Name + " for culture " + strCulture);
// Attach event handlers.
recognizer.SpeechDetected +=
new EventHandler <SpeechDetectedEventArgs>(
SpeechDetectedHandler);
/* recognizer.SpeechHypothesized +=
* new EventHandler<SpeechHypothesizedEventArgs>(SpeechHypothesizedHandler);
* recognizer.SpeechRecognitionRejected +=
* new EventHandler<SpeechRecognitionRejectedEventArgs>(SpeechRecognitionRejectedHandler);
*/
recognizer.SpeechRecognized +=
new EventHandler <SpeechRecognizedEventArgs>(
SpeechRecognizedHandler);
recognizer.RecognizeCompleted +=
new EventHandler <RecognizeCompletedEventArgs>(
RecognizeCompletedHandler);
recognizer.RecognizerUpdateReached +=
new EventHandler <RecognizerUpdateReachedEventArgs>(RecognizerUpdateReachedHandler);
// Assign input to the recognizer and start asynchronous
// recognition.
recognizer.SetInputToDefaultAudioDevice();
return(true);
}
else
{
Console.WriteLine("\nSpeech Processor: could not find a recognizer for culture ..." + strCulture);
}
}
catch (Exception ex)
{
Console.WriteLine("\nSpeech Processor: unable to create Speech Recognition Engine");
}
return(false);
}
private KinectModel()
{
kinectSensor = KinectSensor.GetDefault();
timerFoundBodies.Interval = TimeSpan.FromSeconds(1.5);
timerNoBodies.Interval = TimeSpan.FromSeconds(10);
timerFoundBodies.Tick += TimerFoundBodies_Tick;
timerNoBodies.Tick += TimerNoBodies_Tick;
if (kinectSensor != null)
{
this.kinectSensor.Open();
IReadOnlyList<AudioBeam> audioBeamList = this.kinectSensor.AudioSource.AudioBeams;
Stream audioStream = audioBeamList[0].OpenInputStream();
this.convertStream = new KinectAudioStream(audioStream);
}
else
{
return;
}
ri = TryGetKinectRecognizer();
// Setup Gestures
InitGestures();
ActiveViews = new List<IReceptionistView>();
}
private SpeechRecognizer()
{
RecognizerInfo ri = GetKinectRecognizer();
this.sre = new SpeechRecognitionEngine(ri);
this.LoadGrammar(this.sre);
}
static void Main(string[] args)
{
try
{
using (var source = new KinectAudioSource())
{
source.FeatureMode = true;
source.AutomaticGainControl = false; //Important to turn this off for speech recognition
source.SystemMode = SystemMode.OptibeamArrayOnly; //No AEC for this sample
RecognizerInfo ri = SpeechRecognitionEngine.InstalledRecognizers().Where(r => r.Id == RecognizerId).FirstOrDefault();
if (ri == null)
{
Console.WriteLine("Could not find speech recognizer: {0}. Please refer to the sample requirements.", RecognizerId);
return;
}
Console.WriteLine("Using: {0}", ri.Name);
using (var sre = new SpeechRecognitionEngine(ri.Id))
{
var colors = new Choices();
colors.Add("red");
colors.Add("green");
colors.Add("blue");
var gb = new GrammarBuilder();
//Specify the culture to match the recognizer in case we are running in a different culture.
gb.Culture = ri.Culture;
gb.Append(colors);
// Create the actual Grammar instance, and then load it into the speech recognizer.
var g = new Grammar(gb);
sre.LoadGrammar(g);
sre.SpeechRecognized += SreSpeechRecognized;
sre.SpeechHypothesized += SreSpeechHypothesized;
sre.SpeechRecognitionRejected += SreSpeechRecognitionRejected;
using (Stream s = source.Start())
{
sre.SetInputToAudioStream(s,
new SpeechAudioFormatInfo(
EncodingFormat.Pcm, 16000, 16, 1,
32000, 2, null));
Console.WriteLine("Recognizing. Say: 'red', 'green' or 'blue'. Press ENTER to stop");
sre.RecognizeAsync(RecognizeMode.Multiple);
Console.ReadLine();
Console.WriteLine("Stopping recognizer ...");
sre.RecognizeAsyncStop();
}
}
}
}
catch (Exception ex)
{
Console.WriteLine(ex.Message);
}
}
public Form1()
{
InitializeComponent();
for (int i = 3; i < 255; i++)
{
this.cmbBoxIPID.Items.Add(string.Format("{0:X2}", i));
}
this.acnxConnection = new ActiveCNX();
acnxConnection.onConnect += new ActiveCNXConnectionEventHandler(acnxConnection_onConnect);
acnxConnection.onDisconnect += new ActiveCNXConnectionEventHandler(acnxConnection_onDisconnect);
acnxConnection.onError += new ActiveCNXErrorEventHandler(acnxConnection_onError);
acnxConnection.onDigital += new ActiveCNXEventHandler(acnxConnection_onDigital);
//I remembered that you can chain as many methods onto a delegate as you want, meaning we don't need a List of actions anymore.
//Now instead of initializing several lists within the dictionary, we can just initialize it with a null delegate to start and
//then add methods onto it as needed. Should be an easier syntax than dealing with the lists...
Action del = null;
audioSource.FeatureMode = true;
audioSource.AutomaticGainControl = false;
audioSource.SystemMode = SystemMode.OptibeamArrayOnly;
RecognizerInfo ri = SpeechRecognitionEngine.InstalledRecognizers().Where(r => r.Id == RecognizerId).FirstOrDefault();
if (ri == null)
{
MessageBox.Show("Could not find speech recognizer: {0}.", RecognizerId);
return;
}
this.sre = new SpeechRecognitionEngine(ri.Id);
this.transport = new Choices(
"play",
"stop",
"next channel",
"previous channel",
"cnn",
"fox");
var gb = new GrammarBuilder();
gb.Culture = ri.Culture;
gb.Append(transport);
var g = new Grammar(gb);
sre.LoadGrammar(g);
this.actionMap = new Dictionary <string, Action>()
{
{ "play", del },
{ "stop", del },
{ "pause", del },
};
actionMap["play"] += () =>
{
this.log.LogEvent("\nPlay command recognized");
this.acnxConnection.SendDigital(0, 1, true);
this.acnxConnection.SendDigital(0, 1, false);
};
actionMap["stop"] += () =>
{
this.log.LogEvent("\nStop command recognized");
this.acnxConnection.SendDigital(0, 2, true);
this.acnxConnection.SendDigital(0, 2, false);
};
actionMap["pause"] += () =>
{
this.log.LogEvent("\nPause command recognized");
this.acnxConnection.SendDigital(0, 3, true);
this.acnxConnection.SendDigital(0, 3, false);
};
//We could also do something like this, if we wanted a way to add actions at runtime; something like this
//would let us add new actions to a given command while the form was running, which might be cool
AddActionToMap("play", () => this.acnxConnection.SendDigital(1, 0, false));
//To deal with the threading issue, I've moved the speech stuff into it's own class, which is how the ShapeGame
//sample works. The Recognizer basically just takes an array of strings to set up a speech engine, and has it's
//own SpeechRecognized event that we can hook onto - it basically just mirrors the standard SpeechRecognized event.
//This means the Kinect stuff can have it's own little MTA threaded playground to fart around in, but the rest of
//the code doesn't have to deal with any messy threading issues.
recognizer = new Recognizer(this.actionMap.Keys.ToArray());
this.recognizer.SaidSomething += sre_SpeechRecognized;
}
public VoiceControlEngine(KinectSensor sensor)
{
this.sensor = sensor;
this.ri = GetKinectRecognizer();
this.spotifyController = new SpotifyController();
}
/// <summary>
/// Initializes a new instance of the <see cref="SpeechRecognizer"/> class.
/// </summary>
/// <param name="recognizerInfo">
/// Metadata used to identify the recognizer acoustic model to be used.
/// </param>
/// <param name="grammars">
/// Set of grammars to be loaded into speech recognition engine. May NOT be null.
/// </param>
private SpeechRecognizer(RecognizerInfo recognizerInfo, IEnumerable<Grammar> grammars)
{
this.ConfidenceThreshold = DefaultConfidenceThreshold;
this.speechEngine = new SpeechRecognitionEngine(recognizerInfo);
try
{
foreach (Grammar grammar in grammars)
{
speechEngine.LoadGrammar(grammar);
}
}
catch (InvalidOperationException)
{
// Grammar may not be in a valid state
this.speechEngine.Dispose();
this.speechEngine = null;
}
}
///////////////////////////////////////////////////////////////////
private void CreateGrammars(RecognizerInfo rInfo)
{
//定义操作类型
var controls = new Choices();
controls.Add("打开");
controls.Add("关闭");
controls.Add("调高");
controls.Add("降低");
//定义所操作的设备
var devices = new Choices();
devices.Add("电视");
devices.Add("红色电灯");
devices.Add("绿色电灯");
devices.Add("空调");
//定义操作参数
var param = new Choices();
param.Add("亮度");
param.Add("温度");
param.Add("频道");
param.Add("电源");
var gBulider = new GrammarBuilder();
gBulider.Culture = rInfo.Culture;
gBulider.Append(controls);
gBulider.Append(devices);
gBulider.Append(param);
gBulider.AppendWildcard();
var g = new Grammar(gBulider);
_speechRecognitionEngine.LoadGrammar(g);
var q = new GrammarBuilder { Culture = rInfo.Culture };
q.Append("退出 程序");
var quit = new Grammar(q);
_speechRecognitionEngine.LoadGrammar(quit);
}
/// <summary>
/// Execute initialization tasks.
/// </summary>
/// <param name="sender">object sending the event</param>
/// <param name="e">event arguments</param>
private void WindowLoaded(object sender, RoutedEventArgs e)
{
// Look through all sensors and start the first connected one.
// This requires that a Kinect is connected at the time of app startup.
// To make your app robust against plug/unplug,
// it is recommended to use KinectSensorChooser provided in Microsoft.Kinect.Toolkit (See components in Toolkit Browser).
foreach (var potentialSensor in KinectSensor.KinectSensors)
{
if (potentialSensor.Status == KinectStatus.Connected)
{
this.sensor = potentialSensor;
break;
}
}
objec[0] = -1;
objec[1] = -1;
objec[2] = -1;
bot[0] = 0;
bot[1] = 0;
bot[2] = 0;
if (null != this.sensor)
{
this.sensor.DepthStream.Enable(DepthImageFormat.Resolution640x480Fps30);
this.sensor.ColorStream.Enable(ColorImageFormat.RgbResolution640x480Fps30);
this.sensor.SkeletonStream.Enable();
this.colorPixels = new byte[this.sensor.ColorStream.FramePixelDataLength];
this.depthPixels = new DepthImagePixel[this.sensor.DepthStream.FramePixelDataLength];
this.colorBitmap = new WriteableBitmap(this.sensor.ColorStream.FrameWidth, this.sensor.ColorStream.FrameHeight, 96.0, 96.0, PixelFormats.Bgr32, null);
this.depthBitmap = new WriteableBitmap(this.sensor.DepthStream.FrameWidth, this.sensor.DepthStream.FrameHeight, 96.0, 96.0, PixelFormats.Bgr32, null);
this.img.Source = this.colorBitmap;
this.sensor.AllFramesReady += sensor_AllFramesReady;
try
{
// Start the sensor!
this.sensor.Start();
}
catch (IOException)
{
// Some other application is streaming from the same Kinect sensor
this.sensor = null;
}
}
if (null == this.sensor)
{
this.statusBarText.Text = Properties.Resources.NoKinectReady;
return;
}
RecognizerInfo ri = GetKinectRecognizer();
if (null != ri)
{
//recognitionSpans = new List<Span> { forwardSpan, backSpan, rightSpan, leftSpan };
this.speechEngine = new SpeechRecognitionEngine(ri.Id);
// Create a grammar from grammar definition XML file.
using (var memoryStream = new MemoryStream(Encoding.ASCII.GetBytes(Properties.Resources.SpeechGrammar)))
{
var g = new Grammar(memoryStream);
speechEngine.LoadGrammar(g);
}
speechEngine.SpeechRecognized += SpeechRecognized;
speechEngine.SpeechRecognitionRejected += SpeechRejected;
speechEngine.SetInputToAudioStream(
sensor.AudioSource.Start(), new SpeechAudioFormatInfo(EncodingFormat.Pcm, 16000, 16, 1, 32000, 2, null));
speechEngine.RecognizeAsync(RecognizeMode.Multiple);
}
else
{
this.statusBarText.Text = Properties.Resources.NoSpeechRecognizer;
}
}
protected override SpeechRecognitionEngine CreateSpeechRecognitionEngine()
{
RecognizerInfo kinectRecognizer = KinectV1Utils.GetKinectRecognizer(CultureInfo.GetCultureInfoByIetfLanguageTag("en")); //use Kinect-based recognition engine
return((kinectRecognizer != null)? new SpeechRecognitionEngine(kinectRecognizer) : base.CreateSpeechRecognitionEngine()); //fallback to recognition using default audio source
}
/// <summary>
/// Execute initialization tasks.
/// </summary>
/// <param name="sender">object sending the event</param>
/// <param name="e">event arguments</param>
private void WindowLoaded(object sender, RoutedEventArgs e)
{
// Look through all sensors and start the first connected one.
// This requires that a Kinect is connected at the time of app startup.
// To make your app robust against plug/unplug,
// it is recommended to use KinectSensorChooser provided in Microsoft.Kinect.Toolkit
foreach (var potentialSensor in KinectSensor.KinectSensors)
{
if (potentialSensor.Status == KinectStatus.Connected)
{
this.sensor = potentialSensor;
break;
}
}
if (null != this.sensor)
{
try
{
// Start the sensor!
this.sensor.Start();
}
catch (IOException)
{
// Some other application is streaming from the same Kinect sensor
this.sensor = null;
}
}
if (null == this.sensor)
{
this.statusBarText.Text = Properties.Resources.NoKinectReady;
return;
}
RecognizerInfo ri = GetKinectRecognizer();
if (null != ri)
{
recognitionSpans = new List <Span> {
forwardSpan, backSpan, rightSpan, leftSpan
};
this.speechEngine = new SpeechRecognitionEngine(ri.Id);
/****************************************************************
*
* Use this code to create grammar programmatically rather than from
* a grammar file.
*
* var directions = new Choices();
* directions.Add(new SemanticResultValue("forward", "FORWARD"));
* directions.Add(new SemanticResultValue("forwards", "FORWARD"));
* directions.Add(new SemanticResultValue("straight", "FORWARD"));
* directions.Add(new SemanticResultValue("backward", "BACKWARD"));
* directions.Add(new SemanticResultValue("backwards", "BACKWARD"));
* directions.Add(new SemanticResultValue("back", "BACKWARD"));
* directions.Add(new SemanticResultValue("turn left", "LEFT"));
* directions.Add(new SemanticResultValue("turn right", "RIGHT"));
*
* var gb = new GrammarBuilder { Culture = ri.Culture };
* gb.Append(directions);
*
* var g = new Grammar(gb);
*
****************************************************************/
// Create a grammar from grammar definition XML file.
using (var memoryStream = new MemoryStream(Encoding.ASCII.GetBytes(Properties.Resources.SpeechGrammar)))
{
var g = new Grammar(memoryStream);
speechEngine.LoadGrammar(g);
}
speechEngine.SpeechRecognized += SpeechRecognized;
speechEngine.SpeechRecognitionRejected += SpeechRejected;
speechEngine.SetInputToAudioStream(
sensor.AudioSource.Start(), new SpeechAudioFormatInfo(EncodingFormat.Pcm, 16000, 16, 1, 32000, 2, null));
speechEngine.RecognizeAsync(RecognizeMode.Multiple);
}
else
{
this.statusBarText.Text = Properties.Resources.NoSpeechRecognizer;
}
}
private static SpeechRecognitionEngine CreateSpeechRecognizer()
{
RecognizerInfo ri = GetKinectRecognizer();
if (ri == null)
{
Console.WriteLine("There was a problem initializing Speech Recognition." +
"Ensure you have the Microsoft Speech SDK installed." +
"Failed to load Speech SDK");
return(null);
}
SpeechRecognitionEngine sre;
try
{
sre = new SpeechRecognitionEngine(ri.Id);
}
catch
{
Console.WriteLine("There was a problem initializing Speech Recognition." +
"Ensure you have the Microsoft Speech SDK installed and configured." +
"Failed to load Speech SDK");
return(null);
}
var grammar = new Choices();
//grammar.Add("red");
//grammar.Add("green");
//grammar.Add("blue");
//grammar.Add("eric");
//grammar.Add("stop");
//grammar.Add("hello world");
grammar.Add("The");
grammar.Add("quick");
grammar.Add("brown");
grammar.Add("fox");
grammar.Add("jumps");
grammar.Add("over");
grammar.Add("the");
grammar.Add("lazy");
grammar.Add("dog");
grammar.Add("super");
var gb = new GrammarBuilder {
Culture = ri.Culture
};
gb.Append(grammar);
var g = new Grammar(gb);
sre.LoadGrammar(g);
sre.SpeechRecognized += new EventHandler <SpeechRecognizedEventArgs>(sre_SpeechRecognized);
sre.SpeechHypothesized += new EventHandler <SpeechHypothesizedEventArgs>(sre_SpeechHypothesized);
sre.SpeechRecognitionRejected += new EventHandler <SpeechRecognitionRejectedEventArgs>(sre_SpeechRecognitionRejected);
return(sre);
}
private SpeechRecognitionEngine CreateSpeechRecognizer()
{
RecognizerInfo ri = GetKinectRecognizer();
if (ri == null)
{
System.Windows.MessageBox.Show(
@"There was a problem initializing Speech Recognition.
Ensure you have the Microsoft Speech SDK installed.",
"Failed to load Speech SDK",
MessageBoxButton.OK,
MessageBoxImage.Error);
this.Close();
return null;
}
//SpeechRecognitionEngine sre;
try
{
speechRecognizer = new SpeechRecognitionEngine(ri.Id);
//speechRecognizer = SelectRecognizer("Kinect");
}
catch
{
System.Windows.MessageBox.Show(
@"There was a problem initializing Speech Recognition.
Ensure you have the Microsoft Speech SDK installed and configured.",
"Failed to load Speech SDK",
MessageBoxButton.OK,
MessageBoxImage.Error);
this.Close();
return null;
}
var grammar = new Choices();
grammar.Add("start");
grammar.Add("pick");
grammar.Add("select");
grammar.Add("a");
grammar.Add("navigate");
grammar.Add("b");
grammar.Add("move");
grammar.Add("stop");
grammar.Add("hold");
grammar.Add("synchronize");
var gb = new GrammarBuilder {};
gb.Append(grammar);
// Create the actual Grammar instance, and then load it into the speech recognizer.
var g = new Grammar(gb);
speechRecognizer.LoadGrammar(g);
speechRecognizer.SpeechRecognized += this.SreSpeechRecognized;
speechRecognizer.SpeechHypothesized += SreSpeechHypothesized;
speechRecognizer.SpeechRecognitionRejected += SreSpeechRecognitionRejected;
kinectSource = kinectSensorT.AudioSource;
kinectSource.BeamAngleMode = BeamAngleMode.Adaptive;
kinectSource.EchoCancellationMode = EchoCancellationMode.None; // No AEC for this sample
kinectSource.AutomaticGainControlEnabled = false; // Important to turn this off for speech recognition
st = kinectSource.Start();
//System.Windows.MessageBox.Show("audio source started");
speechRecognizer.SetInputToAudioStream(st,
new SpeechAudioFormatInfo(
EncodingFormat.Pcm, 16000, 16, 1,
32000, 2, null));
speechRecognizer.RecognizeAsync(RecognizeMode.Multiple);
return speechRecognizer;
}
private void Setup(string ip, string language, string grammar)
{
if (this.client == null)
{
this.client = new MqttClient(ip);
this.client.ProtocolVersion = MqttProtocolVersion.Version_3_1;
this.client.MqttMsgPublishReceived += this.TextToSpeech;
this.client.Subscribe(new string[] { ttsTopic }, new byte[] { MqttMsgBase.QOS_LEVEL_AT_LEAST_ONCE });
this.client.Connect(Guid.NewGuid().ToString());
}
if (this.dictationSpeechEngine == null)
{
try {
this.dictationSpeechEngine = new SpeechRecognitionEngine(new System.Globalization.CultureInfo(language));
this.dictationSpeechEngine.SpeechRecognized += this.DicatationSpeechRecognition_SpeechRecognized;
this.dictationSpeechEngine.LoadGrammar(new DictationGrammar());
this.dictationSpeechEngine.SetInputToDefaultAudioDevice();
this.dictationSpeechEngine.RecognizeAsync(RecognizeMode.Multiple);
} catch { this.LanguageStatus.Text = "failed load dictation engine"; }
}
if (this.templateSpeechEngine == null)
{
RecognizerInfo ri = null;
try {
foreach (RecognizerInfo recognizer in SpeechRecognitionEngine.InstalledRecognizers())
{
if (language.Equals(recognizer.Culture.Name, StringComparison.OrdinalIgnoreCase))
{
ri = recognizer;
break;
}
}
this.templateSpeechEngine = new SpeechRecognitionEngine(ri.Id);
string exe = Assembly.GetExecutingAssembly().Location;
grammar = exe.Substring(0, exe.LastIndexOf('\\')) + @"\..\..\Grammar\" + grammar;
if (File.Exists(grammar))
{
try {
this.templateSpeechEngine.LoadGrammar(new Grammar(grammar));
this.templateSpeechEngine.SpeechRecognized += this.TemplateSpeechRecognition_FrameArrived;
this.templateSpeechEngine.SpeechRecognitionRejected += this.TemplateSpeechRecognition_Rejected;
this.templateSpeechEngine.SetInputToDefaultAudioDevice();
this.templateSpeechEngine.RecognizeAsync(RecognizeMode.Multiple);
}
catch { this.GrammarStatus.Text = "failed load template engine"; }
}
else
{
this.GrammarStatus.Text = "failed load grammar file";
}
} catch { this.GrammarStatus.Text = "recognizer is null"; }
}
if (this.speechSynthesizer == null)
{
this.speechSynthesizer = new SpeechSynthesizer();
this.speechSynthesizer.SelectVoiceByHints(VoiceGender.Female, VoiceAge.Teen);
this.speechSynthesizer.SetOutputToDefaultAudioDevice();
this.speechSynthesizer.SpeakCompleted += this.SpeechEnd_FrameArrived;
}
if (this.kinectSensor == null)
{
this.kinectSensor = KinectSensor.GetDefault();
AudioSource audioSource = this.kinectSensor.AudioSource;
this.audioReader = audioSource.OpenReader();
this.audioReader.FrameArrived += this.Audio_FrameArrived;
this.kinectSensor.Open();
}
#if PRINT_STATUS_MESSAGE
this.appClock.Start();
#endif
}
private void StartSpeechRecognition(RecognizerInfo ri)
{
this.speechEngine = new SpeechRecognitionEngine(ri.Id);
using (var memoryStream = new MemoryStream(Encoding.ASCII.GetBytes(File.ReadAllText("SpeechGrammar.xml"))))
{
var g = new Grammar(memoryStream);
this.speechEngine.LoadGrammar(g);
}
this.speechEngine.SpeechRecognized += this.SpeechRecognized;
this.speechEngine.SpeechRecognitionRejected += this.SpeechRejected;
this.speechEngine.SetInputToAudioStream(
this.kinect.AudioSource.Start(), new SpeechAudioFormatInfo(EncodingFormat.Pcm, 16000, 16, 1, 32000, 2, null));
this.speechEngine.RecognizeAsync(RecognizeMode.Multiple);
}
/// <summary>
/// Execute initialization tasks.
/// </summary>
/// <param name="sender">object sending the event</param>
/// <param name="e">event arguments</param>
private void WindowLoaded(object sender, RoutedEventArgs e)
{
// Only one sensor is supported
this.kinectSensor = KinectSensor.GetDefault();
if (this.kinectSensor != null)
{
// open the sensor
this.kinectSensor.Open();
// grab the audio stream
IReadOnlyList <AudioBeam> audioBeamList = this.kinectSensor.AudioSource.AudioBeams;
System.IO.Stream audioStream = audioBeamList[0].OpenInputStream();
// create the convert stream
this.convertStream = new KinectAudioStream(audioStream);
}
else
{
// on failure, set the status text
this.statusBarText.Text = Properties.Resources.NoKinectReady;
return;
}
RecognizerInfo ri = TryGetKinectRecognizer();
if (null != ri)
{
this.recognitionSpans = new List <Span> {
forwardSpan, backSpan, rightSpan, leftSpan
};
this.speechEngine = new SpeechRecognitionEngine(ri.Id);
/****************************************************************
*
* Use this code to create grammar programmatically rather than from
* a grammar file.
*
* var directions = new Choices();
* directions.Add(new SemanticResultValue("forward", "FORWARD"));
* directions.Add(new SemanticResultValue("forwards", "FORWARD"));
* directions.Add(new SemanticResultValue("straight", "FORWARD"));
* directions.Add(new SemanticResultValue("backward", "BACKWARD"));
* directions.Add(new SemanticResultValue("backwards", "BACKWARD"));
* directions.Add(new SemanticResultValue("back", "BACKWARD"));
* directions.Add(new SemanticResultValue("turn left", "LEFT"));
* directions.Add(new SemanticResultValue("turn right", "RIGHT"));
*
* var gb = new GrammarBuilder { Culture = ri.Culture };
* gb.Append(directions);
*
* var g = new Grammar(gb);
*
****************************************************************/
// Create a grammar from grammar definition XML file.
using (var memoryStream = new MemoryStream(Encoding.ASCII.GetBytes(Properties.Resources.SpeechGrammar)))
{
var g = new Grammar(memoryStream);
this.speechEngine.LoadGrammar(g);
}
this.speechEngine.SpeechRecognized += this.SpeechRecognized;
this.speechEngine.SpeechRecognitionRejected += this.SpeechRejected;
// let the convertStream know speech is going active
this.convertStream.SpeechActive = true;
// For long recognition sessions (a few hours or more), it may be beneficial to turn off adaptation of the acoustic model.
// This will prevent recognition accuracy from degrading over time.
////speechEngine.UpdateRecognizerSetting("AdaptationOn", 0);
this.speechEngine.SetInputToAudioStream(
this.convertStream, new SpeechAudioFormatInfo(EncodingFormat.Pcm, 16000, 16, 1, 32000, 2, null));
this.speechEngine.RecognizeAsync(RecognizeMode.Multiple);
}
else
{
this.statusBarText.Text = Properties.Resources.NoSpeechRecognizer;
}
}
/// <summary>
/// Execute startup tasks
/// </summary>
/// <param name="sender">object sending the event</param>
/// <param name="e">event arguments</param>
private void WindowLoaded(object sender, RoutedEventArgs e)
{
// Create the drawing group we'll use for drawing
this.drawingGroup = new DrawingGroup();
// Create an image source that we can use in our image control
this.imageSource = new DrawingImage(this.drawingGroup);
// Display the drawing using our image control
Image.Source = this.imageSource;
// Look through all sensors and start the first connected one.
// This requires that a Kinect is connected at the time of app startup.
// To make your app robust against plug/unplug,
// it is recommended to use KinectSensorChooser provided in Microsoft.Kinect.Toolkit (See components in Toolkit Browser).
foreach (var potentialSensor in KinectSensor.KinectSensors)
{
if (potentialSensor.Status == KinectStatus.Connected)
{
this.sensor = potentialSensor;
break;
}
}
if (null != this.sensor)
{
// Turn on the skeleton stream to receive skeleton frames
this.sensor.SkeletonStream.Enable();
// Add an event handler to be called whenever there is new color frame data
this.sensor.SkeletonFrameReady += this.SensorSkeletonFrameReady;
// Start the sensor!
try
{
this.sensor.Start();
}
catch (IOException)
{
this.sensor = null;
}
}
if (null == this.sensor)
{
this.statusBarText.Text = Properties.Resources.NoKinectReady;
}
RecognizerInfo ri = (from recognizer in SpeechRecognitionEngine.InstalledRecognizers()
where "en-US".Equals(recognizer.Culture.Name, StringComparison.OrdinalIgnoreCase)
select recognizer).FirstOrDefault();
if (ri != null)
{
this.speechEngine = new SpeechRecognitionEngine(ri.Id);
var color = new Choices();
color.Add(new SemanticResultValue("RED", "Red"));
color.Add(new SemanticResultValue("BLUE", "Blue"));
color.Add(new SemanticResultValue("GREEN", "Green"));
color.Add(new SemanticResultValue("YELLOW", "Yellow"));
color.Add(new SemanticResultValue("QUIT", "Quit"));
var gb = new GrammarBuilder();
gb.Culture = ri.Culture;
gb.Append(color);
var g = new Grammar(gb);
speechEngine.LoadGrammar(g);
this.speechEngine.SpeechRecognized += new EventHandler <SpeechRecognizedEventArgs>(speechEngine_SpeechRecognized); speechEngine.SetInputToAudioStream(sensor.AudioSource.Start(), new SpeechAudioFormatInfo(EncodingFormat.Pcm, 16000,
16, 1, 32000, 2, null));
speechEngine.RecognizeAsync(RecognizeMode.Multiple);
}
//content.Text = "1. put your left hand over your shoulder, then use your right hand to draw a shape";
}
private void backgroundWorker1_DoWork(object sender, DoWorkEventArgs e)
{
List <string> words = (List <string>)e.Argument;
ProgessResponse response = new ProgessResponse()
{
};
using (var source = new KinectAudioSource())
{
source.FeatureMode = true;
source.AutomaticGainControl = false; //Important to turn this off for speech recognition
source.SystemMode = SystemMode.OptibeamArrayOnly; //No AEC for this sample
RecognizerInfo ri = SpeechRecognitionEngine.InstalledRecognizers().Where(r => r.Id == RecognizerId).FirstOrDefault();
if (ri == null)
{
response.Message = "Could not find speech recognizer: {0}. Please refer to the sample requirements." + RecognizerId;
backgroundWorker1.ReportProgress(0, response);
return;
}
response.Message = "Using: {0}" + ri.Name;
backgroundWorker1.ReportProgress(0, response);
using (var sre = new SpeechRecognitionEngine(ri.Id))
{
var wordChoices = new Choices();
foreach (string word in words)
{
wordChoices.Add(word);
//backgroundWorker1.ReportProgress(0, "added: " + word);
}
response.Message = "speech listener started";
backgroundWorker1.ReportProgress(0, response);
var gb = new GrammarBuilder();
//Specify the culture to match the recognizer in case we are running in a different culture.
gb.Culture = ri.Culture;
gb.Append(wordChoices);
// Create the actual Grammar instance, and then load it into the speech recognizer.
var g = new Grammar(gb);
sre.LoadGrammar(g);
sre.SpeechRecognized += SreSpeechRecognized;
sre.SpeechHypothesized += SreSpeechHypothesized;
sre.SpeechRecognitionRejected += SreSpeechRecognitionRejected;
using (Stream s = source.Start())
{
sre.SetInputToAudioStream(s, new SpeechAudioFormatInfo(EncodingFormat.Pcm, 16000, 16, 1, 32000, 2, null));
sre.RecognizeAsync(RecognizeMode.Multiple);
bool cancel = false;
while (cancel == false)
{
if (backgroundWorker1.CancellationPending)
{
// Set the e.Cancel flag so that the WorkerCompleted event
// knows that the process was cancelled.
e.Cancel = true;
cancel = true;
break;
}
Thread.Sleep(10);
}
sre.RecognizeAsyncStop();
}
}
}
}
///
/// VOZ
///
private void WindowLoaded(object sender, RoutedEventArgs e)
{
// Look through all sensors and start the first connected one.
// This requires that a Kinect is connected at the time of app startup.
// To make your app robust against plug/unplug,
// it is recommended to use KinectSensorChooser provided in Microsoft.Kinect.Toolkit (See components in Toolkit Browser).
foreach (var potentialSensor in KinectSensor.KinectSensors)
{
if (potentialSensor.Status == KinectStatus.Connected)
{
this.sensor = potentialSensor;
break;
}
}
if (null != this.sensor)
{
// Turn on the skeleton stream to receive skeleton frames
this.sensor.SkeletonStream.Enable();
// Add an event handler to be called whenever there is new color frame data
this.sensor.SkeletonFrameReady += this.SensorSkeletonFrameReady;
myKinect = KinectSensor.KinectSensors[0];
myKinect.ColorStream.Enable();
myKinect.ColorFrameReady += myKinect_ColorFrameReady;
// Start the sensor!
try
{
this.sensor.Start();
}
catch (IOException)
{
this.sensor = null;
}
}
//---------------------VOZ
//Gramatica correspondiente a los comandos de voz
RecognizerInfo ri = GetKinectRecognizer();
if (null != ri)
{
this.speechEngine = new SpeechRecognitionEngine(ri.Id);
// Use this code to create grammar programmatically rather than froma grammar file.
var directions = new Choices();
directions.Add(new SemanticResultValue("izquierdo", "CLICKIZQ"));
directions.Add(new SemanticResultValue("derecho", "CLICKDER"));
directions.Add(new SemanticResultValue("foto", "CAPTURA"));
directions.Add(new SemanticResultValue("arriba", "ARRIBA"));
directions.Add(new SemanticResultValue("abajo", "ABAJO"));
directions.Add(new SemanticResultValue("cambio", "CAMBIO"));
directions.Add(new SemanticResultValue("sube", "SUBE"));
directions.Add(new SemanticResultValue("baja", "BAJA"));
directions.Add(new SemanticResultValue("salir", "SALIR"));
var gb = new GrammarBuilder {
Culture = ri.Culture
};
gb.Append(directions);
var g = new Grammar(gb);
/*
****************************************************************/
// Create a grammar from grammar definition XML file.
//using (var memoryStream = new MemoryStream(Encoding.ASCII.GetBytes(Properties.Resources.SpeechGrammar)))
//{
// var g = new Grammar(memoryStream);
speechEngine.LoadGrammar(g);
//}
speechEngine.SpeechRecognized += SpeechRecognized;
//speechEngine.SpeechRecognitionRejected += SpeechRejected;
// For long recognition sessions (a few hours or more), it may be beneficial to turn off adaptation of the acoustic model.
// This will prevent recognition accuracy from degrading over time.
////speechEngine.UpdateRecognizerSetting("AdaptationOn", 0);
speechEngine.SetInputToAudioStream(
sensor.AudioSource.Start(), new SpeechAudioFormatInfo(EncodingFormat.Pcm, 16000, 16, 1, 32000, 2, null));
speechEngine.RecognizeAsync(RecognizeMode.Multiple);
}
//VOZ
}
void conectaActiva()
{
//Nos aseguramos que la cuenta de sensores conectados sea de al menos 1
if (KinectSensor.KinectSensors.Count > 0)
{
//Checamos que la variable _sensor sea nula
if (this.sensor == null)
{
//Asignamos el primer sensor Kinect a nuestra variable
this.sensor = KinectSensor.KinectSensors[0];
if (this.sensor != null)
{
try
{
//Iniciamos el dispositivo Kinect
this.sensor.Start();
//Esto es opcional pero ayuda a colocar el dispositivo Kinect a un cierto angulo de inclinacion, desde -27 a 27
// sensor.ElevationAngle = 3;
//Informamos que se ha conectado e inicializado correctamente el dispositivo Kinect
// Error err = new VME.Error(RecursosLocalizables.StringResources.KinectDetect, 3);
// err.Show();
}
catch (Exception ex)
{
}
//Creamos esta variable ri que tratara de encontrar un language pack valido haciendo uso del metodo obtenerLP
RecognizerInfo ri = obtenerLP();
//Si se encontro el language pack requerido lo asignaremos a nuestra variable speechengine
if (ri != null)
{
this.speechengine = new SpeechRecognitionEngine(ri.Id);
//Creamos esta variable opciones la cual almacenara las opciones de palabras o frases que podran ser reconocidas por el dispositivo
Choices opciones = new Choices();
//Comenzamos a agregar las opciones comenzando por el valor de opcion que tratamos reconocer y una llave que identificara a ese valor
//Por ejemplo en esta linea "uno" es el valor de opcion y "UNO" es la llave
opciones.Add(RecursosLocalizables.StringResources.cerrar, "UNO");
//En esta linea "dos" es el valor de opcion y "DOS" es la llave
opciones.Add(RecursosLocalizables.StringResources.Reflexes, "DOS");
opciones.Add(RecursosLocalizables.StringResources.configuracion, "TRES");
opciones.Add(RecursosLocalizables.StringResources.opciones, "TRES");
opciones.Add(RecursosLocalizables.StringResources.usuario, "TRES");
opciones.Add(RecursosLocalizables.StringResources.acercaDe1, "TRES");
opciones.Add(RecursosLocalizables.StringResources.tabInformacion, "TRES");
//En esta linea "windows ocho" es el valor de opcion y "TRES" es la llave y asi sucesivamente
opciones.Add(new SemanticResultValue("windows", "TRES"));
opciones.Add(new SemanticResultValue("new windows", "TRES"));
//Esta variable creará todo el conjunto de frases y palabras en base a nuestro lenguaje elegido en la variable ri
var grammarb = new GrammarBuilder {
Culture = ri.Culture
};
//Agregamos las opciones de palabras y frases a grammarb
grammarb.Append(opciones);
//Creamos una variable de tipo Grammar utilizando como parametro a grammarb
var grammar = new Grammar(grammarb);
//Le decimos a nuestra variable speechengine que cargue a grammar
this.speechengine.LoadGrammar(grammar);
//mandamos llamar al evento SpeechRecognized el cual se ejecutara cada vez que una palabra sea detectada
speechengine.SpeechRecognized += new EventHandler <SpeechRecognizedEventArgs>(speechengine_SpeechRecognized);
//speechengine inicia la entrada de datos de tipo audio
speechengine.SetInputToAudioStream(sensor.AudioSource.Start(), new SpeechAudioFormatInfo(EncodingFormat.Pcm, 16000, 16, 1, 32000, 2, null));
speechengine.RecognizeAsync(RecognizeMode.Multiple);
}
}
}
}
}
/// <summary>
/// Allows the game to perform any initialization it needs to before starting to run.
/// This is where it can query for any required services and load any non-graphic
/// related content. Calling base.Initialize will enumerate through any components
/// and initialize them as well.
/// </summary>
protected override void Initialize()
{
// TODO: Add your initialization logic here
//initialize Kinect SDK
nui = Runtime.Kinects[0];
nui.Initialize(RuntimeOptions.UseDepthAndPlayerIndex | RuntimeOptions.UseSkeletalTracking);
nui.SkeletonEngine.TransformSmooth = true;
TransformSmoothParameters param = new TransformSmoothParameters();
param.Smoothing = 0.2f;
param.Correction = 0.0f;
param.Prediction = 0.0f;
param.JitterRadius = 0.2f;
param.MaxDeviationRadius = 0.3f;
nui.SkeletonEngine.SmoothParameters = param;
nui.SkeletonFrameReady += new EventHandler <SkeletonFrameReadyEventArgs>(nui_SkeletonFrameReady);
//setup audio
RecognizerInfo ri = GetKinectRecognizer();
if (ri == null)
{
Console.WriteLine("Could not find Kinect speech recognizer. Please refer to the sample requirements.");
return;
}
Console.WriteLine("Using: {0}", ri.Name);
sre = new SpeechRecognitionEngine();
var models = new Choices();
models.Add("lander");
models.Add("flowers");
models.Add("car");
var gb = new GrammarBuilder();
//Specify the culture to match the recognizer in case we are running in a different culture.
gb.Culture = ri.Culture;
gb.Append(models);
// Create the actual Grammar instance, and then load it into the speech recognizer.
var g = new Grammar(gb);
sre.LoadGrammar(g);
sre.SpeechRecognized += SreSpeechRecognized;
sre.SpeechHypothesized += SreSpeechHypothesized;
sre.SpeechRecognitionRejected += SreSpeechRecognitionRejected;
source = new KinectAudioSource();
source.FeatureMode = true;
source.AutomaticGainControl = false;
source.SystemMode = SystemMode.OptibeamArrayOnly;
Stream s = source.Start();
sre.SetInputToAudioStream(s, new SpeechAudioFormatInfo(EncodingFormat.Pcm, 16000, 16, 1, 32000, 2, null));
Console.WriteLine("Recognizing. Say: 'red', 'green' or 'blue'. Press ENTER to stop");
sre.RecognizeAsync(RecognizeMode.Multiple);
handPos[0] = new Vector3(0.0f, 0.0f, 0.0f);
handPos[1] = new Vector3(0.0f, 0.0f, 0.0f);
//set up angles
shiftAngleRemote1 = shiftAngleLocal + 115.3733f;
shiftAngleRemote2 = shiftAngleLocal - 93.9733f;
//initialize hand angles
prevHandYAngle = 0.0f;
prevHandXAngle = 0.0f;
//for sphere
distortion = new Distortion(Vector3.Zero, Vector3.Backward, Vector3.Up, 1, 1);
//for cylinder
//distortion = new Distortion(Vector3.Zero, Vector3.Backward, Vector3.Up, 1, 1, distortionShift, 4);
View = Matrix.CreateLookAt(new Vector3(0, 0, 2), Vector3.Zero,
Vector3.Up);
Projection = Matrix.CreatePerspectiveFieldOfView(
MathHelper.PiOver4, 16.0f / 9.0f, 1, 500);
//setupOSC();
base.Initialize();
}
private void InitializeKinect()
{
kinectSensor.ColorStream.Enable(ColorImageFormat.RgbResolution640x480Fps30);
kinectSensor.ColorFrameReady += new EventHandler<ColorImageFrameReadyEventArgs>(kinectSensor_ColorFrameReady);
try
{
kinectSensor.Start();
// Obtain the KinectAudioSource to do audio capture
source = kinectSensor.AudioSource;
source.EchoCancellationMode = EchoCancellationMode.None; // No AEC for this sample
source.AutomaticGainControlEnabled = false; // Important to turn this off for speech recognition
ri = GetKinectRecognizer();
if (ri == null)
{
speechStatus = "Speech is fuxor'd";
}
else
{
speechStatus = "using speech and stuff";
Console.WriteLine("*** using speech");
int wait = 4;
while (wait > 0)
{
wait--;
speechStatus = "Device will be ready for speech recognition in " + wait + " seconds.";
Thread.Sleep(1000);
}
kinectSensor.Start();
}
}
catch
{
kinectStatus = "Unable to start the Kinect Sensor";
}
}
public void launchVoiceRecognizer()
{
//Get the info of the voice recognizer engine the user wants to use
//RecognizerInfo recognizer = GetKinectRecognizer();
RecognizerInfo recognizer = null;
ReadOnlyCollection <RecognizerInfo> allRecognizers = SpeechRecognitionEngine.InstalledRecognizers();
for (int i = 0; i < allRecognizers.Count; i++)
{
if (allRecognizers[i].Id == server.serverMasterOptions.audioOptions.recognizerEngineID)
{
recognizer = allRecognizers[i];
break;
}
}
if (recognizer == null)
{
throw new Exception("Couldn't find voice recognizer core.");
}
//Wait 4 seconds for the Kinect to be ready, may not be necessary, but the sample does this
//Thread.Sleep(4000);
engine = new SpeechRecognitionEngine(server.serverMasterOptions.audioOptions.recognizerEngineID);
Choices vocab = new Choices();
for (int i = 0; i < server.serverMasterOptions.voiceCommands.Count; i++)
{
vocab.Add(server.serverMasterOptions.voiceCommands[i].recognizedWord);
}
GrammarBuilder gb = new GrammarBuilder {
Culture = recognizer.Culture
};
gb.Append(vocab);
Grammar grammar = new Grammar(gb);
engine.LoadGrammar(grammar);
//Setup events
engine.SpeechRecognized += new EventHandler <SpeechRecognizedEventArgs>(engine_SpeechRecognized);
engine.SpeechHypothesized += new EventHandler <SpeechHypothesizedEventArgs>(engine_SpeechHypothesized);
engine.SpeechRecognitionRejected += new EventHandler <SpeechRecognitionRejectedEventArgs>(engine_SpeechRecognitionRejected);
//According to the speech recognition sample, this turns off adaptation of the acoustical mode, which can degrade recognizer accuracy over time
engine.UpdateRecognizerSetting("AdaptationOn", 0);
if (server.serverMasterOptions.audioOptions.sourceID >= 0 && server.serverMasterOptions.audioOptions.sourceID < server.kinects.Count)
{
KinectAudioSource source = server.kinects[server.serverMasterOptions.audioOptions.sourceID].kinect.AudioSource;
audioStream = source.Start();
engine.SetInputToAudioStream(audioStream, new Microsoft.Speech.AudioFormat.SpeechAudioFormatInfo(Microsoft.Speech.AudioFormat.EncodingFormat.Pcm, 16000, 16, 1, 32000, 2, null));
}
else
{
engine.SetInputToDefaultAudioDevice();
}
engine.RecognizeAsync(RecognizeMode.Multiple);
}
/// <summary>
/// Execute startup tasks
/// </summary>
/// <param name="sender">object sending the event</param>
/// <param name="e">event arguments</param>
private void WindowLoaded(object sender, RoutedEventArgs e)
{
brush = Brushes.White;
// Create the drawing group we'll use for drawing
this.drawingGroup = new DrawingGroup();
// Create an image source that we can use in our image control
this.imageSource = new DrawingImage(this.drawingGroup);
// Display the drawing using our image control
Image.Source = this.imageSource;
// Look through all sensors and start the first connected one.
// This requires that a Kinect is connected at the time of app startup.
// To make your app robust against plug/unplug,
// it is recommended to use KinectSensorChooser provided in Microsoft.Kinect.Toolkit (See components in Toolkit Browser).
foreach (var potentialSensor in KinectSensor.KinectSensors)
{
if (potentialSensor.Status == KinectStatus.Connected)
{
this.sensor = potentialSensor;
break;
}
}
if (null != this.sensor)
{
// Turn on the skeleton stream to receive skeleton frames
this.sensor.SkeletonStream.Enable();
// Add an event handler to be called whenever there is new color frame data
this.sensor.SkeletonFrameReady += this.SensorSkeletonFrameReady;
// Start the sensor!
try
{
this.sensor.Start();
}
catch (IOException)
{
this.sensor = null;
}
}
if (null == this.sensor)
{
this.statusBarText.Text = "Connect Kinect and try again";
return;
}
//For audio recogninzer
RecognizerInfo ri = (from recognizer in SpeechRecognitionEngine.InstalledRecognizers() where "en-US".Equals(recognizer.Culture.Name, StringComparison.OrdinalIgnoreCase) select recognizer).FirstOrDefault();
if (ri != null)
{
this.speechEngine = new SpeechRecognitionEngine(ri.Id);
//var fontsizes = new Choices();
//fontsizes.Add(new SemanticResultValue("SMALL", "Small"));
//fontsizes.Add(new SemanticResultValue("MEDIUM", "Medium"));
//fontsizes.Add(new SemanticResultValue("LARGE", "Large"));
//gb.Append(fontsizes);
var colors = new Choices();
colors.Add("yellow");
colors.Add("red");
colors.Add("pink");
colors.Add("green");
//colors.Add("quit");
//var quit = new Choices();
//quit.Add("quit");
var gb = new GrammarBuilder();
gb.Culture = ri.Culture;
gb.Append(colors);
//gb.Append(quit);
var g = new Grammar(gb);
speechEngine.LoadGrammar(g);
this.speechEngine.SpeechRecognized += new EventHandler <SpeechRecognizedEventArgs>(speechEngine_SpeechRecognized);
speechEngine.SetInputToAudioStream(sensor.AudioSource.Start(), new SpeechAudioFormatInfo(EncodingFormat.Pcm, 16000, 16, 1, 32000, 2, null));
speechEngine.RecognizeAsync(RecognizeMode.Multiple);
var q = new GrammarBuilder();
q.Append("quit");
var quit = new Grammar(q);
speechEngine.LoadGrammar(quit);
}
}
/// <summary>
/// 初始化語音辨識
/// </summary>
private void InitalizeSpeechRecognition()
{
// grab the audio stream
IReadOnlyList <AudioBeam> audioBeamList = this._sensor.AudioSource.AudioBeams;
System.IO.Stream audioStream = audioBeamList[0].OpenInputStream();
// create the convert stream
this.convertStream = new KinectAudioStream(audioStream);
//RecognizerInfo
RecognizerInfo recognizerInfo = RecognizerSelection.TryGetKinectRecognizer();
if (null != recognizerInfo)
{
//Using KinectRecognizer();
this.speechEngine = new SpeechRecognitionEngine(recognizerInfo.Id);
var grammarBuilder = new GrammarBuilder {
Culture = recognizerInfo.Culture
};
//把語音字典放進去
grammarBuilder.Append(vocabulary.Speech_Dictionary);
//Grammar
var grammar = new Grammar(grammarBuilder);
//載入文法
this.speechEngine.LoadGrammar(grammar);
// let the convertStream know speech is going active
this.convertStream.SpeechActive = true;
// For long recognition sessions (a few hours or more), it may be beneficial to turn off adaptation of the acoustic model.
// This will prevent recognition accuracy from degrading over time.
speechEngine.UpdateRecognizerSetting("AdaptationOn", 0);
try
{
if (MicrophoneSetting.Microphone_Status)
{
this.speechEngine.SetInputToDefaultAudioDevice();
}
else
{
this.speechEngine.SetInputToAudioStream(this.convertStream, new SpeechAudioFormatInfo(EncodingFormat.Pcm, 16000, 16, 1, 32000, 2, null));
}
}
catch (Exception e)
{
Console.WriteLine("輸入設備問題" + e, ToString());
}
this.speechEngine.RecognizeAsync(RecognizeMode.Multiple);
//語音辨識事件，語音辨識拒絕事件
this.speechEngine.SpeechRecognized += SpeechRecognized;
this.speechEngine.SpeechRecognitionRejected += SpeechRejected;
}
}
private bool createSpeechEngine()
{
kinectRecognizerInfo = findKinectRecognizerInfo();
if (kinectRecognizerInfo == null)
{
errorMessage = "Kinect recognizer not found";
return false;
}
try
{
recognizer = new SpeechRecognitionEngine(kinectRecognizerInfo);
}
catch
{
errorMessage = "Speech recognition engine could not be loaded";
return false;
}
return true;
}
public void StartListening(Microsoft.Speech.Recognition.RecognizerInfo recognizerInfo)
{
_ri = recognizerInfo;
}
/// <summary>
/// Execute start up tasks
/// </summary>
/// <param name="sender">object sending the event</param>
/// <param name="e">event arguments</param>
private void MainWindow_Loaded(object sender, RoutedEventArgs e)
{
// Onle one sensor is supported
this.kinectSensor = KinectSensor.GetDefault();
if (this.kinectSensor != null)
{
// open the sensor
this.kinectSensor.Open();
// grab the audio stream
var audioBeamList = this.kinectSensor.AudioSource.AudioBeams;
var audioStream = audioBeamList[0].OpenInputStream();
// create the convert stream
this.convertStream = new KinectAudioStream(audioStream);
}
else
{
return;
}
RecognizerInfo ri = GetKinectRecognizer();
if (null != ri)
{
this.speechEngine = new SpeechRecognitionEngine(ri.Id);
/****************************************************************
*
* Use this code to create grammar programmatically rather than from
* a grammar file.
*
* var directions = new Choices();
* directions.Add(new SemanticResultValue("forward", "FORWARD"));
* directions.Add(new SemanticResultValue("forwards", "FORWARD"));
* directions.Add(new SemanticResultValue("straight", "FORWARD"));
* directions.Add(new SemanticResultValue("backward", "BACKWARD"));
* directions.Add(new SemanticResultValue("backwards", "BACKWARD"));
* directions.Add(new SemanticResultValue("back", "BACKWARD"));
* directions.Add(new SemanticResultValue("turn left", "LEFT"));
* directions.Add(new SemanticResultValue("turn right", "RIGHT"));
*
* var gb = new GrammarBuilder { Culture = ri.Culture };
* gb.Append(directions);
*
* var g = new Grammar(gb);
*
****************************************************************/
// Create a grammar from grammar definition XML file.
using (var memoryStream = new MemoryStream(Encoding.ASCII.GetBytes(Properties.Resources.SpeechGrammar)))
{
var g = new Grammar(memoryStream);
this.speechEngine.LoadGrammar(g);
}
this.speechEngine.SpeechRecognized += this.SpeechRecognized;
// let the convertStream know speech is going active
this.convertStream.SpeechActive = true;
// For long recognition sessions (a few hours or more), it may be beneficial to turn off adaptation of the acoustic model.
// This will prevent recognition accuracy from degrading over time.
////speechEngine.UpdateRecognizerSetting("AdaptationOn", 0);
this.speechEngine.SetInputToAudioStream(
this.convertStream, new SpeechAudioFormatInfo(EncodingFormat.Pcm, 16000, 16, 1, 32000, 2, null));
this.speechEngine.RecognizeAsync(RecognizeMode.Multiple);
}
else
{
// NoSpeechRecognizer
}
// Face detection
for (int i = 0; i < this.bodyCount; i++)
{
if (this.faceFrameReaders[i] != null)
{
// wire handler for face frame arrival
this.faceFrameReaders[i].FrameArrived += this.Reader_FaceFrameArrived;
}
}
if (this.bodyFrameReader != null)
{
// wire handler for body frame arrival
this.bodyFrameReader.FrameArrived += this.Reader_BodyFrameArrived;
}
}
/// \brief Gets the Kinect sensor and initializes it
///
/// \return boolean. True if sensor is initalized, false otherwise.
private bool sensorInit()
{
// Obtain a KinectSensor if any are available
sensor = (from sensorToCheck in KinectSensor.KinectSensors where sensorToCheck.Status == KinectStatus.Connected select sensorToCheck).FirstOrDefault();
if (sensor == null)
{
Console.WriteLine("Could not connect to Kinect.");
return false;
}
Console.Write("Sensor Starting ... ");
sensor.Start();
Console.WriteLine("Sensor Ready");
source = sensor.AudioSource; // Obtain the KinectAudioSource to do audio capture and set options
source.EchoCancellationMode = EchoCancellationMode.CancellationAndSuppression; // No AEC
source.AutomaticGainControlEnabled = false; // Important to turn this off for speech recognition
recogInfo = GetKinectRecognizer();
if (recogInfo == null)
{
Console.WriteLine("Could not find Kinect speech recognizer.");
return false;
}
Console.WriteLine("Using: {0}", recogInfo.Name);
// NOTE: Need to wait 4 seconds for device to be ready right after initialization
int wait = 4;
while (wait > 0)
{
Console.Write("Device will be ready for speech recognition in {0} second(s).\r", wait--);
Thread.Sleep(1000);
}
Console.WriteLine(); // clear line
return true;
}
/// <summary>
///
/// </summary>
public override void StartSpeechRecognition()
{
RecognizerInfo ri = GetKinectRecognizer();
if (null == ri)
{
return;
}
// Check if selected recognizer is for Kinect
string value;
ri.AdditionalInfo.TryGetValue("Kinect", out value);
IsKinectRecognizer = "True".Equals(value, StringComparison.OrdinalIgnoreCase);
iSpeechEngine = new SpeechRecognitionEngine(ri.Id);
// Create a speech recognition grammar based on our speech events
var ear = Properties.Settings.Default.EarManager;
var choices = new Choices();
bool noChoices = true;
foreach (EventSpeech e in ear.Events.Where(e => e.GetType() == typeof(EventSpeech)))
{
if (!e.Enabled)
{
continue;
}
// For each events associates its phrases with its semantic
string[] phrases = e.Phrases.Split(new string[] { Environment.NewLine }, StringSplitOptions.None);
foreach (string phrase in phrases)
{
if (string.IsNullOrWhiteSpace(phrase))
{
// defensive
continue;
}
choices.Add(new SemanticResultValue(phrase, e.Semantic));
noChoices = false;
}
}
if (noChoices)
{
// Grammar build throws exception if no choice registered
// TODO: review error handling in that function.
// I guess we should have a Try variant.
return;
}
// Set our culture
Culture = ri.Culture;
var gb = new GrammarBuilder {
Culture = ri.Culture
};
gb.Append(choices);
var g = new Grammar(gb);
iSpeechEngine.LoadGrammar(g);
iSpeechEngine.SpeechRecognized += this.SpeechRecognized;
iSpeechEngine.SpeechRecognitionRejected += this.SpeechRejected;
// For long recognition sessions (a few hours or more), it may be beneficial to turn off adaptation of the acoustic model.
// This will prevent recognition accuracy from degrading over time.
iSpeechEngine.UpdateRecognizerSetting("AdaptationOn", 0);
iSpeechEngine.SetInputToDefaultAudioDevice();
iSpeechEngine.RecognizeAsync(RecognizeMode.Multiple);
}
// Execute initialization tasks.
private void WindowLoaded(object sender, RoutedEventArgs e)
{
// Look through all sensors and start the first connected one.
// This requires that a Kinect is connected at the time of app startup.
// To make your app robust against plug/unplug,
// it is recommended to use KinectSensorChooser provided in Microsoft.Kinect.Toolkit (See components in Toolkit Browser).
foreach (var potentialSensor in KinectSensor.KinectSensors)
{
if (potentialSensor.Status == KinectStatus.Connected)
{
this.sensor = potentialSensor;
break;
}
}
if (null != this.sensor)
{
try
{
// Start the sensor
this.sensor.Start();
}
catch (IOException)
{
// Some other application is streaming from the same Kinect sensor
this.sensor = null;
}
}
if (null == this.sensor)
{
this.statusBarText.Text = Properties.Resources.NoKinectReady;
return;
}
RecognizerInfo ri = GetKinectRecognizer();
if (null != ri)
{
recognitionSpans = new List <Span> {
forwardSpan, backSpan, stopSpan, rightSpan, leftSpan
};
//Add the spans relating to the commands to be displayed on the main window
this.speechEngine = new SpeechRecognitionEngine(ri.Id);
// Create a grammar from grammar definition XML file.
using (var memoryStream = new MemoryStream(Encoding.ASCII.GetBytes(Properties.Resources.SpeechGrammar)))
{
var g = new Grammar(memoryStream);
speechEngine.LoadGrammar(g);
}
speechEngine.SpeechRecognized += SpeechRecognized;
speechEngine.SpeechRecognitionRejected += SpeechRejected;
//For long recognition sessions (a few hours or more), it may be beneficial to turn off adaptation of the acoustic model.
//This will prevent recognition accuracy from degrading over time.
speechEngine.SetInputToAudioStream(sensor.AudioSource.Start(), new SpeechAudioFormatInfo(EncodingFormat.Pcm, 16000, 16, 1, 32000, 2, null));
speechEngine.RecognizeAsync(RecognizeMode.Multiple);
}
else
{
this.statusBarText.Text = Properties.Resources.NoSpeechRecognizer;
}
}
private bool InitializeKinect()
{
kinect.ColorStream.Enable(ColorImageFormat.RgbResolution640x480Fps30);
kinect.ColorFrameReady += new EventHandler<ColorImageFrameReadyEventArgs>(kinectSensor_ColorFrameReady);
kinect = KinectSensor.KinectSensors.FirstOrDefault();
try
{
kinect.Start();
source = kinect.AudioSource;
source.EchoCancellationMode = EchoCancellationMode.None;
source.AutomaticGainControlEnabled = false;
ri = GetKinectRecognizer();
if (ri == null)
{
Console.WriteLine("ri = 0, Kinect audio not working.");
}
else
{
Console.WriteLine("*** using speech");
int wait = 4;
while (wait > 0)
{
wait--;
Console.WriteLine("Device will be ready for speech recognition in " + wait + " seconds.");
Thread.Sleep(1000);
}
kinect.Start();
}
kinect.SkeletonStream.Enable(new TransformSmoothParameters()
{
Smoothing = 0.5f,
Correction = 0.5f,
Prediction = 0.5f,
JitterRadius = 0.05f,
MaxDeviationRadius = 0.04f
});
kinect.SkeletonFrameReady += new EventHandler<SkeletonFrameReadyEventArgs>(kinect_SkeletonFrameReady);
}
catch
{
connectedStatus = "Unable to start the Kinect Sensor";
return false;
}
return true;
}
