Question

请查看以下代码

using System;
using System.Collections.Generic;
using System.Linq;
using System.Text;
using System.Speech.Recognition;
using System.Speech.Synthesis;
using System.Windows.Forms;
using System.IO;

namespace US_Speech_Recognizer
{
    public class RecognizeSpeech
    {
        private SpeechRecognitionEngine sEngine; //Speech recognition engine
        private SpeechSynthesizer sSpeak; //Speech synthesizer
        string text3 = "";

        public RecognizeSpeech()
        {
            //Make the recognizer ready
            sEngine = new SpeechRecognitionEngine(new System.Globalization.CultureInfo("en-US"));


            //Load grammar
            Choices sentences = new Choices();
            sentences.Add(new string[] { "I am hungry" });

            GrammarBuilder gBuilder = new GrammarBuilder(sentences);

            Grammar g = new Grammar(gBuilder);

            sEngine.LoadGrammar(g);

            //Add a handler
            sEngine.SpeechRecognized +=new EventHandler<SpeechRecognizedEventArgs>(sEngine_SpeechRecognized);


            sSpeak = new SpeechSynthesizer();
            sSpeak.Rate = -2;



            //Computer speaks the words to get the phones
            Stream stream = new MemoryStream();
            sSpeak.SetOutputToWaveStream(stream);


            sSpeak.Speak("I was hungry");
            stream.Position = 0;
            sSpeak.SetOutputToNull();


            //Configure the recognizer to stream
            sEngine.SetInputToWaveStream(stream);

            sEngine.RecognizeAsync(RecognizeMode.Single);


        }


        //Start the speech recognition task
        private void sEngine_SpeechRecognized(object sender, SpeechRecognizedEventArgs e)
        {
            string text = "";

            if (e.Result.Text == "I am hungry")
            {
                foreach (RecognizedWordUnit wordUnit in e.Result.Words)
                {
                    text = text + wordUnit.Pronunciation + "\n";
                }

                MessageBox.Show(e.Result.Text + "\n" + text);
            }


        }
    }
}

在这里，语法为I am hungry，但要求计算机说I was hungry。但情况是，识别事件被触发并说文本完全等于I am hungry !!在输出框中，您也可以查看音素！

避免这种情况的唯一方法是加载DictationGrammar

我认为提供自定义语法是限制应用程序监听不需要的所有内容的最佳方法，但似乎自定义语法失败了！

我的问题是，有没有办法避免这种情况？为什么会这样？

非常感谢您的帮助。感谢。

Answer 1

我找到了答案。 Custom Grammar将通过向引擎施加大量压力来过滤用户的发音，以使用提供的LIMITED语法识别用户的语音。

Dictation grammar不是那样的，它只会尝试匹配WHAT COMPUTER UNDERSTOOD而不是用户所说的内容。

这可以通过训练语音引擎来最小化。

听写语法VS自定义语法

1 个答案: