static void Main( string[] args )
{
// 音源を取得するインスタンスを生成する
using ( KinectAudioSource source = new KinectAudioSource() ) {
// SingleChannelAec:シングルチャネルのマイクで、エコーキャンセルを使用する
// OptibeamArrayOnly:マルチチャネルのマイクのみを使用する(エコーキャンセルを使用しない)
// OptibeamArrayAndAec:マルチチャネルのマイクと、エコーキャンセルを使用する)
// SingleChannelNsAgc:シングルチャネルのマイクのみを使用する(エコーキャンセルを使用しない)
source.SystemMode = SystemMode.OptibeamArrayOnly;
source.BeamChanged += new EventHandler<BeamChangedEventArgs>( source_BeamChanged );
using ( Stream audioStream = source.Start() ) {
Console.WriteLine( "Start... Press any key" );
byte[] buffer = new byte[4096];
Win32.StreamingWavePlayer player = new Win32.StreamingWavePlayer( 16000, 16, 1, 100 );
while ( !Console.KeyAvailable ) {
int count = audioStream.Read( buffer, 0, buffer.Length );
player.Output( buffer );
// 詳細な音源方向の信頼性がある場合、音源方向を更新する
if ( source.SoundSourcePositionConfidence > 0.9 ) {
Console.Write( "詳細な音源方向(推定) : {0}\t\tビーム方向 : {1}\r",
source.SoundSourcePosition, source.MicArrayBeamAngle );
}
}
}
}
}
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();
}
public SpeechRecognizer(string file, KinectSensor sensor)
{
this.grammarFile = file;
this.kinectSensor = sensor;
audioSource = kinectSensor.AudioSource;
audioSource.AutomaticGainControlEnabled = false;
audioSource.BeamAngleMode = BeamAngleMode.Adaptive;
Func<RecognizerInfo, bool> matchingFunc = r =>
{
string value;
r.AdditionalInfo.TryGetValue("Kinect", out value);
return "True".Equals(value, StringComparison.InvariantCultureIgnoreCase) && "en-US".Equals(r.Culture.Name, StringComparison.InvariantCultureIgnoreCase);
};
var recognizerInfo = SpeechRecognitionEngine.InstalledRecognizers().Where(matchingFunc).FirstOrDefault();
if (recognizerInfo == null)
return;
speechRecognitionEngine = new SpeechRecognitionEngine(recognizerInfo.Id);
var grammar = new Grammar(grammarFile);
speechRecognitionEngine.LoadGrammar(grammar);
audioStream = audioSource.Start();
speechRecognitionEngine.SetInputToAudioStream(audioStream, new SpeechAudioFormatInfo(EncodingFormat.Pcm, 16000, 16, 1, 32000, 2, null));
speechRecognitionEngine.AudioStateChanged += onAudioStateChanged;
speechRecognitionEngine.SpeechRecognized += onSpeechRecognized;
speechRecognitionEngine.RecognizeCompleted += onSpeechRecognizeCompleted;
speechRecognitionEngine.EmulateRecognizeCompleted += onEmulateRecognizeCompleted;
}
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");
}
private void CleanUpAudioResources()
{
if (source != null)
{
source.Stop();
source = null;
}
}
static void Main()
{
using (var source = new KinectAudioSource())
{
source.FeatureMode = true;
source.AutomaticGainControl = false;
source.SystemMode = SystemMode.OptibeamArrayOnly;
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);
using (var sre = new SpeechRecognitionEngine(ri.Id))
{
//declare commands to be used
var commands = new Choices();
commands.Add("activate");
commands.Add("off");
commands.Add("open");
commands.Add("manual");
commands.Add("hold");
commands.Add("land");
commands.Add("stabilize");
var gb = new GrammarBuilder {Culture = ri.Culture};
//Specify the culture to match the recognizer in case we are running in a different culture.
gb.Append(commands);
// 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.SpeechRecognitionRejected += SreSpeechRejected;
using (Stream s = source.Start())
{
sre.SetInputToAudioStream(s,
new SpeechAudioFormatInfo(
EncodingFormat.Pcm, 16000, 16, 1,
32000, 2, null));
Console.WriteLine("Recognizing... Press ENTER to stop");
sre.RecognizeAsync(RecognizeMode.Multiple);
Console.ReadLine();
Console.WriteLine("Stopping recognizer ...");
sre.RecognizeAsyncStop();
}
}
}
}
public CommandRecognitionAdapter(Dictionary<string, Action> callbacks)
{
this.callbacks = callbacks;
var source = new KinectAudioSource();
source.FeatureMode = true;
source.AutomaticGainControl = false;
source.SystemMode = SystemMode.OptibeamArrayOnly;
}
public AudioIn_KinectXbox(FIFOStream stream)
{
mStream = stream;
mSrc = new KinectAudioSource();
mSrc.SystemMode = SystemMode.OptibeamArrayOnly;
mThread = new Thread(new ThreadStart(KinectThreadProc));
mRunningEvent = new ManualResetEvent(false);
mRunning = false;
}
static void Main(string[] args)
{
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 = 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);
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();
}
}
}
}
static void Main(string[] args)
{
var buffer = new byte[4096];
const int recordTime = 20; //seconds
const int recordingLength = recordTime * 2 * 16000; //10 seconds, 16 bits per sample, 16khz
const string outputFileName = "out.wav";
//We need to run in high priority to avoid dropping samples
Thread.CurrentThread.Priority = ThreadPriority.Highest;
//Instantiate the KinectAudioSource to do audio capture
using (var source = new KinectAudioSource())
{
source.SystemMode = SystemMode.OptibeamArrayOnly;
//Register for beam tracking change notifications
source.BeamChanged += source_BeamChanged;
using (var fileStream = new FileStream(outputFileName, FileMode.Create))
{
using (var sampleStream = new StreamWriter(new FileStream("samples.log", FileMode.Create)))
{
WriteWavHeader(fileStream, recordingLength);
Console.WriteLine("Recording for {0} seconds", recordTime);
//Start capturing audio
using (var audioStream = source.Start())
{
//Simply copy the data from the stream down to the file
int count, totalCount = 0;
while ((count = audioStream.Read(buffer, 0, buffer.Length)) > 0 && totalCount < recordingLength)
{
for (int i = 0; i < buffer.Length; i += 2)
{
short sample = (short)(buffer[i] | (buffer[i + 1] << 8));
sampleStream.WriteLine(sample);
}
fileStream.Write(buffer, 0, count);
totalCount += count;
//If we have high confidence, print the position
if (source.SoundSourcePositionConfidence > 0.9)
Console.Write("Sound source position (radians): {0}\t\tBeam: {1}\r", source.SoundSourcePosition, source.MicArrayBeamAngle);
}
}
}
}
Console.WriteLine("Recording saved to {0}", outputFileName);
}
}
public override void ConnectedToMaster()
{
Console.WriteLine("Starting...");
sensor = (from sensorToCheck in KinectSensor.KinectSensors where sensorToCheck.Status == KinectStatus.Connected select sensorToCheck).FirstOrDefault();
if (sensor == null)
{
Console.WriteLine("\n Kinect sensor not detected !\n");
return;
}
source = sensor.AudioSource;
source.AutomaticGainControlEnabled = true;
try { sensor.Start(); }
catch (Exception)
{
Console.WriteLine("Sensor cannot Start! \n");
return;
}
source.Start();
started = true;
source.SoundSourceAngleChanged += delegate
{
if (!IsConnected) return;
bool send = false;
if (source.SoundSourceAngleConfidence > confidenceThreshold)
{
if (SoundDirectionMutex.WaitOne(0))
{
if ((Math.Abs(lastSpeechDirection - source.SoundSourceAngle) < repeatedDirectionAngle))
{
if ((System.DateTime.Now - lastSpeechDirectionTime).TotalSeconds > repeatedDirectionInterval) send = true;
}
else
{
send = true;
}
if (send)
{
Console.WriteLine("SoundLocated{ angle: " + source.SoundSourceAngle + "; confidence: " + source.SoundSourceAngleConfidence);
kinectPublisher.SoundDirectionLocated(source.SoundSourceAngle, source.SoundSourceAngleConfidence);
lastSpeechDirectionTime = DateTime.Now;
lastSpeechDirection = source.SoundSourceAngle;
}
SoundDirectionMutex.ReleaseMutex();
}
}
};
return;
}
public void Start(KinectAudioSource kinectSource)
{
this.CheckDisposed();
this.kinectAudioSource = kinectSource;
this.kinectAudioSource.AutomaticGainControlEnabled = false;
this.kinectAudioSource.BeamAngleMode = BeamAngleMode.Adaptive;
var kinectStream = this.kinectAudioSource.Start();
this.sre.SetInputToAudioStream(
kinectStream, new SpeechAudioFormatInfo(EncodingFormat.Pcm, 16000, 16, 1, 32000, 2, null));
this.sre.RecognizeAsync(RecognizeMode.Multiple);
}
private void Initialize()
{
if (_kinectSensor == null)
return;
_speechRecognizer = CreateSpeechRecognizer();
_speechRecognizer.SetInputToDefaultAudioDevice();
_speechRecognizer.RecognizeAsync(RecognizeMode.Multiple);
_kinectSensor.AllFramesReady += KinectSensorAllFramesReady;
_kinectSensor.ColorStream.Enable(ColorImageFormat.RgbResolution640x480Fps30);
_kinectSensor.Start();
_kinectAudioSource = _kinectSensor.AudioSource;
_kinectAudioSource.Start();
Message = "Kinect connected";
}
static void Main(string[] args)
{
KinectSensor sensor = KinectSensor.KinectSensors[0];
sensor.Start();
kinectaudiosource = sensor.AudioSource;
SoundTracking();
Console.WriteLine("請按下空白建結束");
while ( Console.ReadKey().Key != ConsoleKey.Spacebar)
{
}
sensor.Stop();
}
public void initSpeech()
{
kinectSource = new KinectAudioSource();
kinectSource.FeatureMode = true;
kinectSource.AutomaticGainControl = false;
kinectSource.SystemMode = SystemMode.OptibeamArrayOnly;
var rec = (from r in SpeechRecognitionEngine.InstalledRecognizers() where r.Id == RecognizerId select r).FirstOrDefault();
speechEngine = new SpeechRecognitionEngine(rec.Id);
var choices = new Choices();
choices.Add("select scalpal");
choices.Add("select syringe");
choices.Add("select suction");
choices.Add("select hand");
choices.Add("nurse scalpal");
choices.Add("nurse syringe");
choices.Add("nurse suction");
choices.Add("nurse hand");
choices.Add("show console");
choices.Add("hide console");
choices.Add("begin incision");
choices.Add("end incision");
choices.Add("inject");
GrammarBuilder gb = new GrammarBuilder();
gb.Culture = rec.Culture;
gb.Append(choices);
var g = new Grammar(gb);
speechEngine.LoadGrammar(g);
speechEngine.SpeechHypothesized += new EventHandler<SpeechHypothesizedEventArgs>(sre_SpeechHypothesized);
speechEngine.SpeechRecognized += new EventHandler<SpeechRecognizedEventArgs>(sre_SpeechRecognized);
speechEngine.SpeechRecognitionRejected += new EventHandler<SpeechRecognitionRejectedEventArgs>(sre_SpeechRecognitionRejected);
Console.WriteLine("Recognizing Speech");
stream = kinectSource.Start();
speechEngine.SetInputToAudioStream(stream,
new SpeechAudioFormatInfo(
EncodingFormat.Pcm, 16000, 16, 1,
32000, 2, null));
speechEngine.RecognizeAsync(RecognizeMode.Multiple);
}
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;
}
RecognizerInfo InitializeKinectAudio()
{
Console.Write("Getting audio source from Kinect...");
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 = GetKinectRecognizer();
if (ri == null)
{
Console.WriteLine("Could not find Kinect speech recognizer. Please refer to the sample requirements.");
return null;
}
Console.WriteLine("Audio source created");
return ri;
}
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
var colors = new Choices();
colors.Add( "red" );
colors.Add( "green" );
colors.Add( "blue" );
colors.Add( "end" );
colors.Add( "赤" );
colors.Add( "ミドリ" );
colors.Add( "あお" );
Recognizer r = new Recognizer( "ja-JP", colors );
r.SpeechRecognized += SreSpeechRecognized;
r.SpeechHypothesized += SreSpeechHypothesized;
r.SpeechRecognitionRejected += SreSpeechRecognitionRejected;
Console.WriteLine( "Using: {0}", r.Name );
using ( Stream s = source.Start() ) {
r.SetInputToAudioStream( s, new SpeechAudioFormatInfo(
EncodingFormat.Pcm, 16000, 16, 1,
32000, 2, null ) );
Console.WriteLine( "Recognizing. Say: 'red', 'green' or 'blue'. Press ENTER to stop" );
r.RecognizeAsync( RecognizeMode.Multiple );
Console.ReadLine();
Console.WriteLine( "Stopping recognizer ..." );
r.RecognizeAsyncStop();
}
}
}
catch ( Exception ex ) {
Console.WriteLine( ex.Message );
}
}
public void StartAudioStream()
{
try
{
kinectAudio = kinect.AudioSource;
kinectAudio.BeamAngleMode = BeamAngleMode.Manual;
kinectAudio.ManualBeamAngle = Math.PI / 180.0 * 10.0; //angle in radians
//kinectAudio.BeamAngleMode = BeamAngleMode.Adaptive;
kinect.AudioSource.EchoCancellationMode = EchoCancellationMode.None;
kinect.AudioSource.AutomaticGainControlEnabled = false;
var stream = kinectAudio.Start();
speechRecognitionEngine.SetInputToAudioStream(stream,
new SpeechAudioFormatInfo(EncodingFormat.Pcm, 16000, 16, 1,
32000, 2, null));
speechRecognitionEngine.RecognizeAsync(RecognizeMode.Multiple);
}
catch
{
}
}
void Record()
{
using (KinectAudioSource source = new KinectAudioSource
{
FeatureMode = true,
AutomaticGainControl = false,
SystemMode = SystemMode.OptibeamArrayOnly
})
{
RecognizerInfo recognizerInfo = SpeechRecognitionEngine.InstalledRecognizers().Where(r => r.Id == RecognizerId).FirstOrDefault();
if (recognizerInfo == null)
return;
SpeechRecognitionEngine speechRecognitionEngine = new SpeechRecognitionEngine(recognizerInfo.Id);
var gb = new GrammarBuilder {Culture = recognizerInfo.Culture};
gb.Append(choices);
var grammar = new Grammar(gb);
speechRecognitionEngine.LoadGrammar(grammar);
using (Stream sourceStream = source.Start())
{
speechRecognitionEngine.SetInputToAudioStream(sourceStream, new SpeechAudioFormatInfo(EncodingFormat.Pcm, 16000, 16, 1, 32000, 2, null));
isRunning = true;
while (isRunning)
{
RecognitionResult result = speechRecognitionEngine.Recognize();
if (result != null && OrderDetected != null && result.Confidence > 0.7)
OrderDetected(result.Text);
}
}
}
}
static void Main( string[] args )
{
// 音源を取得するインスタンスを生成する
using ( KinectAudioSource source = new KinectAudioSource() ) {
// SingleChannelAec:シングルチャネルのマイクで、エコーキャンセルを使用する
// OptibeamArrayOnly:マルチチャネルのマイクのみを使用する(エコーキャンセルを使用しない)
// OptibeamArrayAndAec:マルチチャネルのマイクと、エコーキャンセルを使用する)
// SingleChannelNsAgc:シングルチャネルのマイクのみを使用する(エコーキャンセルを使用しない)
source.SystemMode = SystemMode.SingleChannelAec;
using ( Stream audioStream = source.Start() ) {
Console.WriteLine( "Start... Press any key" );
byte[] buffer = new byte[4096];
Win32.StreamingWavePlayer player = new Win32.StreamingWavePlayer( 16000, 16, 1, 100 );
while ( !Console.KeyAvailable ) {
var a = audioStream.Position;
var b = audioStream.Seek( 0, SeekOrigin.Current );
int count = audioStream.Read( buffer, 0, buffer.Length );
player.Output( buffer );
}
}
}
}
protected void MainWindow_Loaded(object sender, RoutedEventArgs e)
{
// Set and start the first connected sensor
this.StartSensor();
if (this.sensor != null)
{
// Set the audio source
this.audioSource = this.sensor.AudioSource;
// Notify status changes
KinectSensor.KinectSensors.StatusChanged += new System.EventHandler<StatusChangedEventArgs>(KinectSensors_StatusChanged);
// Turn on the streams on
this.sensor.ColorStream.Enable();
this.sensor.DepthStream.Enable();
this.sensor.SkeletonStream.Enable();
// Set the informations via the MainWindowViewModel
this.SetKinectInfo();
}
}
public static void WriteWavFile(KinectAudioSource source, FileStream fileStream, Stream audioStream)
{
var size = 0;
//write wav header placeholder
WriteWavHeader(fileStream, size);
//using (var audioStream = source.Start())
{
//chunk audio stream to file
while (audioStream.Read(buffer, 0, buffer.Length) > 0 && _isRecording)
{
fileStream.Write(buffer, 0, buffer.Length);
size += buffer.Length;
}
}
//write real wav header
long prePosition = fileStream.Position;
fileStream.Seek(0, SeekOrigin.Begin);
WriteWavHeader(fileStream, size);
fileStream.Seek(prePosition, SeekOrigin.Begin);
fileStream.Flush();
}
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();
}
private void startAudioListening()
{
audioSource = new KinectAudioSource();
audioSource.FeatureMode = true;
audioSource.AutomaticGainControl = true;
audioSource.SystemMode = SystemMode.OptibeamArrayOnly;
Stream aStream = audioSource.Start();
sre.SetInputToAudioStream(aStream,
new SpeechAudioFormatInfo(
EncodingFormat.Pcm, 16000, 16, 1,
32000, 2, null));
sre.RecognizeAsync(RecognizeMode.Multiple);
}
public static void listen()
{
System.Windows.MessageBox.Show("Listening");
System.Windows.MessageBox.Show(Thread.CurrentThread.GetApartmentState().ToString());
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
//onMessage("Constructor is doing good");
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);
//onMessage("Could not find speech recognizer: {0}. Please refer to the sample requirements." + RecognizerId);
System.Windows.MessageBox.Show("RI is null");
return;
}
//onMessage("Using: {0}" + ri.Name);
using (var sre = new SpeechRecognitionEngine(ri.Id))
{
sre_speech = sre;
var choices = new Choices();
choices.Add("microsoft");
choices.Add("google");
choices.Add("facebook");
choices.Add("bellevue");
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(choices);
// 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();
}
}
}
}
/// \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>
/// Starts speech recognition using audio stream from specified KinectAudioSource.
/// </summary>
/// <param name="audioSource">
/// Audio source to use as input to speech recognizer.
/// </param>
public System.IO.Stream Start(KinectAudioSource audioSource)
{
if (null == audioSource)
{
return null;
}
this.kinectAudioSource = audioSource;
this.kinectAudioSource.AutomaticGainControlEnabled = false;
this.kinectAudioSource.NoiseSuppression = true;
this.kinectAudioSource.BeamAngleMode = BeamAngleMode.Adaptive;
this.kinectAudioSource.SoundSourceAngleChanged += this.SoundSourceChanged;
this.speechEngine.SpeechRecognized += this.SreSpeechRecognized;
this.speechEngine.SpeechRecognitionRejected += this.SreSpeechRecognitionRejected;
var kinectStream = this.kinectAudioSource.Start();
this.speechEngine.SetInputToAudioStream(
kinectStream, new SpeechAudioFormatInfo(AudioFormat, AudioSamplesPerSecond, AudioBitsPerSample, AudioChannels, AudioAverageBytesPerSecond, AudioBlockAlign, null));
this.speechEngine.RecognizeAsync(RecognizeMode.Multiple);
return kinectStream;
}
void InitializeSpeech()
{
try
{
kinectAudioSource = new KinectAudioSource();
kinectAudioSource.SystemMode = SystemMode.OptibeamArrayOnly;
kinectAudioSource.FeatureMode = true;
kinectAudioSource.AutomaticGainControl = false;
kinectAudioSource.NoiseSuppression = true;
kinectAudioSource.MicArrayMode = MicArrayMode.MicArrayAdaptiveBeam;
var kinectStream = kinectAudioSource.Start();
speechRecognitionEngine.SetInputToAudioStream(kinectStream, new SpeechAudioFormatInfo(
EncodingFormat.Pcm, 16000, 16, 1,
32000, 2, null));
speechRecognitionEngine.RecognizeAsync(RecognizeMode.Multiple);
}
catch (InvalidOperationException)
{
// kinect unplugged or something. s'okay
}
}
public void Cleanup()
{
if (speechRecognitionEngine != null)
{
speechRecognitionEngine.UnloadAllGrammars();
speechRecognitionEngine.Dispose();
speechRecognitionEngine = null;
}
if (kinectAudioSource != null)
{
kinectAudioSource.Stop();
kinectAudioSource.Dispose();
kinectAudioSource = null;
}
}
static void Main(string[] args)
{
try {
// Kinectが接続されているかどうかを確認する
if (KinectSensor.KinectSensors.Count == 0)
{
throw new Exception("Kinectを接続してください");
}
// 認識器の一覧を表示し、使用する認識器を取得する
ShowRecognizer();
//RecognizerInfo info = GetRecognizer( "en-US" );
RecognizerInfo info = GetRecognizer("ja-JP");
Console.WriteLine("Using: {0}", info.Name);
// 認識させる単語を登録する
Choices colors = new Choices();
colors.Add("red");
colors.Add("green");
colors.Add("blue");
colors.Add("赤");
colors.Add("ミドリ");
colors.Add("あお");
// 文法の設定を行う
GrammarBuilder builder = new GrammarBuilder();
builder.Culture = info.Culture;
builder.Append(colors);
Grammar grammar = new Grammar(builder);
// 認識エンジンの設定と、単語が認識されたときの通知先の登録を行う
SpeechRecognitionEngine engine = new SpeechRecognitionEngine(info.Id);
engine.LoadGrammar(grammar);
engine.SpeechRecognized +=
new EventHandler <SpeechRecognizedEventArgs>(engine_SpeechRecognized);
// Kinectの動作を開始する
KinectSensor kinect = KinectSensor.KinectSensors[0];
kinect.Start();
// 音声のインタフェースを取得し、動作を開始する
KinectAudioSource audio = kinect.AudioSource;
using (Stream s = audio.Start()) {
// 認識エンジンに音声ストリームを設定する
engine.SetInputToAudioStream(s, new SpeechAudioFormatInfo(
EncodingFormat.Pcm, 16000, 16, 1,
32000, 2, null));
Console.WriteLine("Recognizing. Press ENTER to stop");
// 非同期で、音声認識を開始する
engine.RecognizeAsync(RecognizeMode.Multiple);
Console.ReadLine();
Console.WriteLine("Stopping recognizer ...");
// 音声認識を停止する
engine.RecognizeAsyncStop();
}
}
catch (Exception ex) {
Console.WriteLine(ex.Message);
}
}
