使用定向麦克风进行波束追踪 （Beam Tracking for a Directional Microphone）

可以使用这4个麦克风来模拟定向麦克风产生的效果，这个过程称之为波束追踪(beam tracking)

界面上的细长矩形用来指示某一时刻探测到的说话者的语音方向。矩形有一个旋转变换，在垂直轴上左右摆动，以表示声音的不同来源方向。

<Rectangle Fill="#1BA78B" HorizontalAlignment="Left" Margin="240,41,0,39" Stroke="Black" Width="10" RenderTransformOrigin="0.5,0">    <Rectangle.RenderTransform>        <TransformGroup>            <ScaleTransform/>            <SkewTransform/>            <RotateTransform Angle="{Binding BeamAngle}"/>            <TranslateTransform/>        </TransformGroup>    </Rectangle.RenderTransform></Rectangle>

 

上图是程序的UI界面。后台逻辑代码和之前的例子大部分都是相同的。首先实例化一个KinectAudioSource对象，然后将主窗体的DataContext赋值给本身。将BeamAngleMode设置为Adaptive，使得能够自动追踪说话者的声音。我们需要编写KinectAudioSource对象的BeamChanged事件对应的处理方法。当用户的说话时，位置发生变化时就会触发该事件。我们需要创建一个名为BeamAngle的属性，使得矩形的RotateTransform可以绑定这个属性。

public partial class MainWindow : Window, INotifyPropertyChanged{    public MainWindow()    {        InitializeComponent();        this.DataContext = this;        this.Loaded += delegate { ListenForBeamChanges(); };    }    private KinectAudioSource CreateAudioSource()    {        var source = KinectSensor.KinectSensors[0].AudioSource;        source.NoiseSuppression = true;        source.AutomaticGainControlEnabled = true;        source.BeamAngleMode = BeamAngleMode.Adaptive;        return source;    }    private void ListenForBeamChanges()    {        KinectSensor.KinectSensors[0].Start();        var audioSource = CreateAudioSource();        audioSource.BeamAngleChanged += audioSource_BeamAngleChanged;        audioSource.Start();    }    public event PropertyChangedEventHandler PropertyChanged;    private void OnPropertyChanged(string propName)    {        if (PropertyChanged != null)            PropertyChanged(this, new PropertyChangedEventArgs(propName));    }    private double _beamAngle;    public double BeamAngle    {        get { return _beamAngle; }        set        {            _beamAngle = value;            OnPropertyChanged("BeamAngle");        }    }}

 

以上代码中，还需要对BeamChanged事件编写对应的处理方法。每次当波束的方向发生改变时，就更改BeamAngle的属性。SDK中使用弧度表示角度。所以在事件处理方法中我们需要将弧度换成度。为了能达到说话者移到左边，矩形条也能够向左边移动的效果，我们需要将角度乘以一个 –1

void audioSource_BeamAngleChanged(object sender, BeamAngleChangedEventArgs e){    BeamAngle = -1 * e.Angle;}

语音命令识别

结合KinectAudioSource和SpeechRecognitionEngine来演示语音命令识别的强大功能。为了展示语音命令能够和骨骼追踪高效结合，我们会使用语音命令向窗体上绘制图形，并使用命令移动这些图形到光标的位置

CrossHair用户控件简单的以十字光标形式显示当前用户右手的位置。下面的代码显示了这个自定义控件的XAML文件。注意到对象于容器有一定的偏移使得十字光标的中心能够处于Grid的零点。

自定义控件  CrossHairs

CrossHair用户控件简单的以十字光标形式显示当前用户右手的位置。下面的代码显示了这个自定义控件的XAML文件。注意到对象于容器有一定的偏移使得十字光标的中心能够处于Grid的零点。

<Grid Height="50" Width="50" RenderTransformOrigin="0.5,0.5">    <Grid.RenderTransform>        <TransformGroup>            <ScaleTransform/>            <SkewTransform/>            <RotateTransform/>            <TranslateTransform X="-25" Y="-25"/>        </TransformGroup>    </Grid.RenderTransform>    <Rectangle Fill="#FFF4F4F5" Margin="22,0,20,0" Stroke="#FFF4F4F5"/>    <Rectangle Fill="#FFF4F4F5" Margin="0,22,0,21" Stroke="#FFF4F4F5"/>  </Grid>

在应用程序的主窗体中，将根节点从 grid 对象改为 canvas对象。Canvas对象使得将十字光标使用动画滑动到手的位置比较容易。在主窗体上添加一个CrossHairs自定义控件。在下面的代码中，我们可以看到将Canvas对象嵌套在了一个Viewbox控件中。这是一个比较老的处理不同屏幕分辨率的技巧。ViewBox控件会自动的将内容进行缩放以适应实际屏幕的大小。设置MainWindows的背景色，并将Canvas的颜色设置为黑色。然后在Canvas的底部添加两个标签。一个标签用来显示SpeechRecognitionEngine将要处理的语音指令，另一个标签显示匹配正确的置信度。CrossHair自定义控件绑定了HandTop和HandLeft属性。两个标签分别绑定了HypothesizedText和Confidence属性。

<Window x:Class="KinectPutThatThere.MainWindow"        xmlns="http://schemas.microsoft.com/winfx/2006/xaml/presentation"        xmlns:x="http://schemas.microsoft.com/winfx/2006/xaml"        xmlns:local="clr-namespace:KinectPutThatThere"        Title="Put That There"  Background="Black">    <Viewbox>        <Canvas x:Name="MainStage" Height="1080" Width="1920" Background="Black" VerticalAlignment="Bottom">            <local:CrossHairs Canvas.Top="{Binding HandTop}" Canvas.Left="{Binding HandLeft}" />                <Label  Foreground="White"  Content="{Binding HypothesizedText}" Height="55"   FontSize="32" Width="965"  Canvas.Left="115" Canvas.Top="1025" />            <Label Foreground="Green" Content="{Binding Confidence}" Height="55"  Width="114" FontSize="32" Canvas.Left="0" Canvas.Top="1025"  />        </Canvas>    </Viewbox></Window>

在后台逻辑代码中，让MainWindows对象实现INofityPropertyChanged事件并添加OnPropertyChanged帮助方法。我们将创建4个属性用来为前台UI界面进行绑定。

public partial class MainWindow : Window, INotifyPropertyChanged{    private double _handLeft;    public double HandLeft    {        get { return _handLeft; }        set        {            _handLeft = value;            OnPropertyChanged("HandLeft");        }    }    private double _handTop;    public double HandTop    {        get { return _handTop; }        set        {            _handTop = value;            OnPropertyChanged("HandTop");        }    }    private string _hypothesizedText;    public string HypothesizedText    {        get { return _hypothesizedText; }        set        {            _hypothesizedText = value;            OnPropertyChanged("HypothesizedText");        }    }    private string _confidence;    public string Confidence    {        get { return _confidence; }        set        {            _confidence = value;            OnPropertyChanged("Confidence");        }    }    public event PropertyChangedEventHandler PropertyChanged;    private void OnPropertyChanged(string propertyName)    {        if (PropertyChanged != null)        {            PropertyChanged(this, new PropertyChangedEventArgs(propertyName));        }    }}

 

添加CreateAudioSource方法，在该方法中，将KinectAudioSource对象的AutoGainControlEnabled的属性设置为false。

private KinectAudioSource CreateAudioSource(){    var source = KinectSensor.KinectSensors[0].AudioSource;    source.AutomaticGainControlEnabled = false;    source.EchoCancellationMode = EchoCancellationMode.None;    return source;}

 

接下来实现骨骼追踪部分逻辑来获取右手的坐标，相信看完骨骼追踪那两篇文章后这部分的代码应该会比较熟悉。首先创建一个私有字段_kinectSensor来保存当前的KienctSensor对象，同时创建SpeechRecognitionEngine对象。在窗体的构造函数中，对这几个变量进行初始化。例外注册骨骼追踪系统的Skeleton事件并将主窗体的DataContext对象赋给自己。

KinectSensor _kinectSensor;SpeechRecognitionEngine _sre;KinectAudioSource _source;public MainWindow(){    InitializeComponent();    this.DataContext = this;    this.Unloaded += delegate    {        _kinectSensor.SkeletonStream.Disable();        _sre.RecognizeAsyncCancel();        _sre.RecognizeAsyncStop();        _sre.Dispose();    };    this.Loaded += delegate    {        _kinectSensor = KinectSensor.KinectSensors[0];        _kinectSensor.SkeletonStream.Enable(new TransformSmoothParameters()        {            Correction = 0.5f,            JitterRadius = 0.05f,            MaxDeviationRadius = 0.04f,            Smoothing = 0.5f        });        _kinectSensor.SkeletonFrameReady += nui_SkeletonFrameReady;        _kinectSensor.Start();        StartSpeechRecognition();    };}

 

在上面的代码中，我们添加了一些TransformSmoothParameters参数来使得骨骼追踪更加平滑。nui_SkeletonFrameReady方法如下。方式使用骨骼追踪数据来获取我们感兴趣的右手的关节点位置。这部分代码和之前文章中的类似。大致流程是：遍历当前处在追踪状态下的骨骼信息。然后找到右手关节点的矢量信息，然后使用SkeletonToDepthImage来获取相对于屏幕尺寸的X,Y坐标信息。

void nui_SkeletonFrameReady(object sender, SkeletonFrameReadyEventArgs e){    using (SkeletonFrame skeletonFrame = e.OpenSkeletonFrame())    {        if (skeletonFrame == null)            return;        var skeletons = new Skeleton[skeletonFrame.SkeletonArrayLength];        skeletonFrame.CopySkeletonDataTo(skeletons);        foreach (Skeleton skeletonData in skeletons)        {            if (skeletonData.TrackingState == SkeletonTrackingState.Tracked)            {                Microsoft.Kinect.SkeletonPoint rightHandVec = skeletonData.Joints[JointType.HandRight].Position;                var depthPoint = _kinectSensor.MapSkeletonPointToDepth(rightHandVec                    , DepthImageFormat.Resolution640x480Fps30);                HandTop = depthPoint.Y * this.MainStage.ActualHeight / 480;                HandLeft = depthPoint.X * this.MainStage.ActualWidth / 640;            }        }    }}

 

接下来我们需要实现语音识别部分的逻辑。SpeechRecognitionEngine中的StartSpeechRecognition方法必须找到正确的语音识别库来进行语音识别。下面的代码展示了如何设置语音识别库预计如何将KinectAudioSource传递给语音识别引起。我们还添加了SpeechRecognized，SpeechHypothesized以及SpeechRejected事件对应的方法。SetInputToAudioStream中的参数和前篇文章中的含义一样，这里不多解释了。注意到SpeechRecognitionEngine和KinectAudioSource都是Disposable类型，因此在整个应用程序的周期内，我们要保证这两个对象都处于打开状态。

private void StartSpeechRecognition(){    _source = CreateAudioSource();    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);    };    RecognizerInfo ri = SpeechRecognitionEngine.InstalledRecognizers().Where(matchingFunc).FirstOrDefault();    _sre = new SpeechRecognitionEngine(ri.Id);    CreateGrammars(ri);    _sre.SpeechRecognized += sre_SpeechRecognized;    _sre.SpeechHypothesized += sre_SpeechHypothesized;    _sre.SpeechRecognitionRejected += sre_SpeechRecognitionRejected;    Stream s = _source.Start();    _sre.SetInputToAudioStream(s,                                new SpeechAudioFormatInfo(                                    EncodingFormat.Pcm, 16000, 16, 1,                                    32000, 2, null));    _sre.RecognizeAsync(RecognizeMode.Multiple);}

要完成程序逻辑部分，我们还需要处理语音识别时间以及语音逻辑部分，以使得引擎能够直到如何处理和执行我们的语音命令。SpeechHypothesized以及SpeechRejected事件代码如下，这两个事件的逻辑很简单，就是更新UI界面上的label。SpeechRecognized事件有点复杂，他负责处理传进去的语音指令，并对识别出的指令执行相应的操作。另外，该事件还负责创建一些GUI对象（实际就是命令模式），我们必须使用Dispatcher对象来发挥InterpretCommand到主UI线程中来。

void sre_SpeechRecognitionRejected(object sender, SpeechRecognitionRejectedEventArgs e){    HypothesizedText += " Rejected";    Confidence = Math.Round(e.Result.Confidence, 2).ToString();}void sre_SpeechHypothesized(object sender, SpeechHypothesizedEventArgs e){    HypothesizedText = e.Result.Text;}void sre_SpeechRecognized(object sender, SpeechRecognizedEventArgs e){    Dispatcher.BeginInvoke(new Action<SpeechRecognizedEventArgs>(InterpretCommand), e);}

 

现在到了程序核心的地方。创建语法逻辑并对其进行解析。本例中的程序识别普通的以“put”或者“create”开头的命令。前面是什么我们不关心，紧接着应该是一个颜色，然后是一种形状，最后一个词应该是“there”。下面的代码显示了创建的语法。

private void CreateGrammars(RecognizerInfo ri){    var colors = new Choices();    colors.Add("cyan");    colors.Add("yellow");    colors.Add("magenta");    colors.Add("blue");    colors.Add("green");    colors.Add("red");    var create = new Choices();    create.Add("create");    create.Add("put");    var shapes = new Choices();    shapes.Add("circle");    shapes.Add("triangle");    shapes.Add("square");    shapes.Add("diamond");    var gb = new GrammarBuilder();    gb.Culture = ri.Culture;    gb.Append(create);    gb.AppendWildcard();    gb.Append(colors);    gb.Append(shapes);    gb.Append("there");    var g = new Grammar(gb);    _sre.LoadGrammar(g);    var q = new GrammarBuilder{ Culture = ri.Culture };    q.Append("quit application");    var quit = new Grammar(q);    _sre.LoadGrammar(quit);}

 

上面的代码中，我们首先创建一个Choices对象，这个对象会在命令解析中用到。在程序中我们需要颜色和形状对象。另外，第一个单词是“put”或者“create”，因此我们也创建Choices对象。然后使用GrammarBuilder类将这些对象组合到一起。首先是”put”或者“create”然后是一个占位符，因为我们不关心内容，然后是一个颜色Choices对象，然后是一个形状Choices对象，最后是一个“there”单词。

    我们将这些语法规则加载进语音识别引擎。同时我们也需要有一个命令来停止语音识别引擎。因此我们创建了第二个语法对象，这个对象只有一个”Quit”命令。然后也将这个语法规则加载到引擎中。

    一旦识别引擎确定了要识别的语法，真正的识别工作就开始了。被识别的句子必须被解译，出别出来想要的指令后，我们必须决定如何进行下一步处理。下面的代码展示了如何处理识别出的命令，以及如何根据特定的指令来讲图形元素绘制到UI界面上去。

private void InterpretCommand(SpeechRecognizedEventArgs e){    var result = e.Result;    Confidence = Math.Round(result.Confidence, 2).ToString();    if (result.Confidence < 95 && result.Words[0].Text == "quit" && result.Words[1].Text == "application")    {        this.Close();    }    if (result.Words[0].Text == "put" || result.Words[0].Text == "create")    {        var colorString = result.Words[2].Text;        Color color;        switch (colorString)        {            case "cyan": color = Colors.Cyan;                break;            case "yellow": color = Colors.Yellow;                break;            case "magenta": color = Colors.Magenta;                break;            case "blue": color = Colors.Blue;                break;            case "green": color = Colors.Green;                break;            case "red": color = Colors.Red;                break;            default:                return;        }        var shapeString = result.Words[3].Text;        Shape shape;        switch (shapeString)        {            case "circle":                shape = new Ellipse();                shape.Width = 150;                shape.Height = 150;                break;            case "square":                shape = new Rectangle();                shape.Width = 150;                shape.Height = 150;                break;            case "triangle":                var poly = new Polygon();                poly.Points.Add(new Point(0, 0));                poly.Points.Add(new Point(150, 0));                poly.Points.Add(new Point(75, -150));                shape = poly;                break;            case "diamond":                var poly2 = new Polygon();                poly2.Points.Add(new Point(0, 0));                poly2.Points.Add(new Point(75, 150));                poly2.Points.Add(new Point(150, 0));                poly2.Points.Add(new Point(75, -150));                shape = poly2;                break;            default:                return;        }        shape.SetValue(Canvas.LeftProperty, HandLeft);        shape.SetValue(Canvas.TopProperty, HandTop);        shape.Fill = new SolidColorBrush(color);        MainStage.Children.Add(shape);    }}

 

方法中，我们首先检查语句识别出的单词是否是”Quit”如果是的，紧接着判断第二个单词是不是”application”如果两个条件都满足了，就不进行绘制图形，直接返回。如果有一个条件不满足，就继续执行下一步。

     InterpretCommand方法然后判断第一个单词是否是“create”或者“put”，如果不是这两个单词开头就什么也不执行。如果是的，就判断第三个单词，并根据识别出来的颜色创建对象。如果第三个单词没有正确识别，应用程序也停止处理。否则，程序判断第四个单词，根据接收到的命令创建对应的形状。到这一步，基本的逻辑已经完成，最后第五个单词用来确定整个命令是否正确。命令处理完了之后，将当前受的X,Y坐标赋给创建好的对象的位置。

namespace KinectPutThatThere{    /// <summary>    /// Interaction logic for MainWindow.xaml    /// </summary>    public partial class MainWindow : Window, INotifyPropertyChanged    {        KinectSensor _kinectSensor;        SpeechRecognitionEngine _sre;        KinectAudioSource _source;        public MainWindow()        {            InitializeComponent();            this.DataContext = this;            this.Unloaded += delegate            {                _kinectSensor.SkeletonStream.Disable();                _sre.RecognizeAsyncCancel();                _sre.RecognizeAsyncStop();                //_source.Dispose();                _sre.Dispose();            };            this.Loaded += delegate            {                _kinectSensor = KinectSensor.KinectSensors[0];                _kinectSensor.SkeletonStream.Enable(new TransformSmoothParameters() // 对骨骼数据进行平滑处理                {                    // This struct is used to setup the skeleton smoothing values                    Correction = 0.5f,                    JitterRadius = 0.05f,                    MaxDeviationRadius = 0.04f,                    Smoothing = 0.5f                });                _kinectSensor.SkeletonFrameReady += nui_SkeletonFrameReady;                _kinectSensor.Start();                StartSpeechRecognition();            };        }#region 骨骼数据处理        void nui_SkeletonFrameReady(object sender, SkeletonFrameReadyEventArgs e)        {            using (SkeletonFrame skeletonFrame = e.OpenSkeletonFrame())            {                if (skeletonFrame == null)                    return;                var skeletons = new Skeleton[skeletonFrame.SkeletonArrayLength];    // 不定类型 —— Skeleton                skeletonFrame.CopySkeletonDataTo(skeletons);                foreach (Skeleton skeletonData in skeletons)                {                    if (skeletonData.TrackingState == SkeletonTrackingState.Tracked)                    {                        Microsoft.Kinect.SkeletonPoint rightHandVec = skeletonData.Joints[JointType.HandRight].Position;                        var depthPoint = _kinectSensor.MapSkeletonPointToDepth(rightHandVec                            , DepthImageFormat.Resolution640x480Fps30);                        HandTop = depthPoint.Y * this.MainStage.ActualHeight / 480;                        HandLeft = depthPoint.X * this.MainStage.ActualWidth / 640;                    }                }            }        }#endregion        private KinectAudioSource CreateAudioSource()        {            var source = KinectSensor.KinectSensors[0].AudioSource;            source.AutomaticGainControlEnabled = false;            source.EchoCancellationMode = EchoCancellationMode.None;            return source;        }        private void StartSpeechRecognition()        {            _source = CreateAudioSource();            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);            };                // 识别库                        RecognizerInfo ri = SpeechRecognitionEngine.InstalledRecognizers().Where(matchingFunc).FirstOrDefault();            _sre = new SpeechRecognitionEngine(ri.Id);  // 需要设置识别引擎的ID编号            CreateGrammars(ri);            _sre.SpeechRecognized += sre_SpeechRecognized;            _sre.SpeechHypothesized += sre_SpeechHypothesized;            _sre.SpeechRecognitionRejected += sre_SpeechRecognitionRejected;            Stream s = _source.Start();            _sre.SetInputToAudioStream(s,                                        new SpeechAudioFormatInfo(                                            EncodingFormat.Pcm, 16000, 16, 1,                                            32000, 2, null));            _sre.RecognizeAsync(RecognizeMode.Multiple);        }        private void CreateGrammars(RecognizerInfo ri)        {                // 创建语法            var colors = new Choices(); // 通配符 —— 择类(Choices)是通配符类(Wildcard)的一种，它可以包含多个值。但与通配符不同的是，我们可以指定可接受的值的顺序。            colors.Add("cyan");            colors.Add("yellow");            colors.Add("magenta");            colors.Add("blue");            colors.Add("green");            colors.Add("red");            var create = new Choices();            create.Add("create");            create.Add("put");            var shapes = new Choices();            shapes.Add("circle");            shapes.Add("triangle");            shapes.Add("square");            shapes.Add("diamond");            var gb = new GrammarBuilder();            gb.Culture = ri.Culture;            gb.Append(create);            gb.AppendWildcard();            gb.Append(colors);            gb.Append(shapes);            gb.Append("there");            var g = new Grammar(gb);            _sre.LoadGrammar(g);            var q = new GrammarBuilder { Culture = ri.Culture };            q.Append("quit application");            var quit = new Grammar(q);            _sre.LoadGrammar(quit);        }#region 语音事件处理        void sre_SpeechRecognitionRejected(object sender, SpeechRecognitionRejectedEventArgs e)        {            HypothesizedText += " Rejected";            Confidence = Math.Round(e.Result.Confidence, 2).ToString();        }        void sre_SpeechHypothesized(object sender, SpeechHypothesizedEventArgs e)        {            HypothesizedText = e.Result.Text;        }        void sre_SpeechRecognized(object sender, SpeechRecognizedEventArgs e)        {            Dispatcher.BeginInvoke(new Action<SpeechRecognizedEventArgs>(InterpretCommand), e);        }#endregion        private void InterpretCommand(SpeechRecognizedEventArgs e)        {            var result = e.Result;            Confidence = Math.Round(result.Confidence, 2).ToString();            if (result.Confidence < 95 && result.Words[0].Text == "quit" && result.Words[1].Text == "application")            {                this.Close();            }            if (result.Words[0].Text == "put" || result.Words[0].Text == "create")            {                var colorString = result.Words[2].Text;                Color color;                switch (colorString)                {                    case "cyan": color = Colors.Cyan;                        break;                    case "yellow": color = Colors.Yellow;                        break;                    case "magenta": color = Colors.Magenta;                        break;                    case "blue": color = Colors.Blue;                        break;                    case "green": color = Colors.Green;                        break;                    case "red": color = Colors.Red;                        break;                    default:                        return;                }                var shapeString = result.Words[3].Text;                Shape shape;                switch (shapeString)                {                    case "circle":                        shape = new Ellipse();                        shape.Width = 150;                        shape.Height = 150;                        break;                    case "square":                        shape = new Rectangle();                        shape.Width = 150;                        shape.Height = 150;                        break;                    case "triangle":                        var poly = new Polygon();                        poly.Points.Add(new Point(0, 0));                        poly.Points.Add(new Point(150, 0));                        poly.Points.Add(new Point(75, -150));                        shape = poly;                        break;                    case "diamond":                        var poly2 = new Polygon();                        poly2.Points.Add(new Point(0, 0));                        poly2.Points.Add(new Point(75, 150));                        poly2.Points.Add(new Point(150, 0));                        poly2.Points.Add(new Point(75, -150));                        shape = poly2;                        break;                    default:                        return;                }                shape.SetValue(Canvas.LeftProperty, HandLeft);                shape.SetValue(Canvas.TopProperty, HandTop);                shape.Fill = new SolidColorBrush(color);                MainStage.Children.Add(shape);            }        }#region 前台控件的绑定        private double _handLeft;        public double HandLeft        {            get { return _handLeft; }            set            {                _handLeft = value;                OnPropertyChanged("HandLeft");            }        }        private double _handTop;        public double HandTop        {            get { return _handTop; }            set            {                _handTop = value;                OnPropertyChanged("HandTop");   // 驱动控件            }        }        private string _hypothesizedText;        public string HypothesizedText        {            get { return _hypothesizedText; }            set            {                _hypothesizedText = value;                OnPropertyChanged("HypothesizedText");            }        }        private string _confidence;        public string Confidence        {            get { return _confidence; }            set            {                _confidence = value;                OnPropertyChanged("Confidence");            }        }        public event PropertyChangedEventHandler PropertyChanged;        private void OnPropertyChanged(string propertyName)        {            if (PropertyChanged != null)            {                PropertyChanged(this, new PropertyChangedEventArgs(propertyName));            }        }#endregion    }}