使用 Microsoft.Speech 或 System.Speech 命名空间的语音识别

Question

我正在尝试在 C# 桌面应用程序中使用语音识别，如果用户说“按 3”或“按 4”，那么该数字应该写在图表上（比如标签）。我能够识别出用户说出的单词“press”，但除此之外。请帮忙。以下是我的示例代码：

    string txtSpoken = "";
    string[] words = new string[10];

    public Form1()
    {
        InitializeComponent();

        SpeechRecognitionEngine _recognizer = new SpeechRecognitionEngine();
        _recognizer.LoadGrammar(new Grammar(new GrammarBuilder("press")) { Name = "pressGrammar" }); // load a grammar
        _recognizer.SpeechRecognized += _recognizer_SpeechRecognized;
        _recognizer.SetInputToDefaultAudioDevice(); // set the input of the speech recognizer to the default audio device
        _recognizer.RecognizeAsync(RecognizeMode.Multiple); // recognize speech asynchronous
        // _recognizer.Recognize();
    }

    void _recognizer_SpeechRecognized(object sender, SpeechRecognizedEventArgs e)
    {
        string txt = e.Result.Text;
        this.Invoke(new MethodInvoker(() =>
        {
            listBox1.Items.Add("I heard you say: "
                + txt);
        })); // WinForm specific

        if (e.Result.Text == "press") // e.Result.Text contains the recognized text
        {
            textBox1.Text = "3";
            label1.Text += " 3 ";
            //   MessageBox.Show("The test was successful!");
        }

        txtSpoken += e.Result.Text;
        MessageBox.Show(txtSpoken);


        if (txt.IndexOf("press") >= 0)
        {
            words = txt.Split(' ');
        }
    }

Answer 1

问题是，您的语法仅包含单词 press。为了使用户语音和语法之间发生匹配，用户必须准确说出您的语法中的元素之一。 我建议你创建Choices，例如这样：

Choices inputs = new Choices();
inputs.Add(new string[] {"press 3", "press 4"});

GrammarBuilder gb = new GrammarBuilder();
gb.Append(inputs);
Grammar g = new Grammar(gb);
_recognizer.LoadGrammar(g);

更多信息请关注this tutorial。