C# SpeechRecognitionEngine.SetInputToWaveFile方法代码示例

        public void InitializeSpeechRecognitionEngine(String filePath)
        {
            MySpeechRecognitionEngine = new SpeechRecognitionEngine();
            //MySpeechRecognitionEngine.SetInputToDefaultAudioDevice();

            MySpeechRecognitionEngine.UnloadAllGrammars();

            try
            {

                MySpeechRecognitionEngine.SetInputToWaveFile(filePath);

                Process.Start("C:\\Program Files\\Windows Media Player\\wmplayer.exe", ("\"" + filePath + "\""));

                MySpeechRecognitionEngine.LoadGrammar(new DictationGrammar());

                MySpeechRecognitionEngine.RecognizeAsync(RecognizeMode.Single);

                MySpeechRecognitionEngine.AudioLevelUpdated += MySpeechRecognitionEngine_AudioLevelUpdated;

                MySpeechRecognitionEngine.SpeechRecognized += MySpeechRecognitionEnginee_SpeechRecognized;

                MySpeechRecognitionEngine.AudioStateChanged += MySpeechRecognitionEnginee_AudioStateChanged;

                MySpeechRecognitionEngine.RecognizeCompleted += MySpeechRecognitionEngine_RecognizeCompleted;

            }

            catch (Exception ex)
            {

                Console.Write(ex.Message.ToString());

            }
        }

        public void Transcribe(MediaSegment segment)
        {
            using (var engine = new SpeechRecognitionEngine())
            {
                engine.LoadGrammar(new DictationGrammar());
                engine.SetInputToWaveFile(segment.File.FullName);

                var result = engine.Recognize();

                var metaDatum = new Metadata();
                metaDatum.Start = result.Audio.AudioPosition.TotalMilliseconds + segment.OffsetMs;
                metaDatum.End = metaDatum.Start + segment.DurationMs;
                metaDatum.EngineMetadata = new SpeechResults
                {
                    Text = result.Text,
                    Confidence = result.Confidence
                };

                _concurrentDictionary.AddOrUpdate(segment.FileId, new List<Metadata> {metaDatum}, (x, y) =>
                {
                    y.Add(metaDatum);
                    return y;
                });
            }
        }

 public SpeechRecognizer(List<string> phrases, string wavFilePath)
 {
     _phrases = phrases;
     _speechRecognitionEngine = CreateSpeechRecognizer();
     if (string.IsNullOrEmpty(wavFilePath))
         _speechRecognitionEngine.SetInputToDefaultAudioDevice();
     else
         _speechRecognitionEngine.SetInputToWaveFile(wavFilePath);
     _speechRecognitionEngine.RecognizeAsync(RecognizeMode.Multiple);
 }

 /// <summary>
 /// Recognize method has not handle exception if audio is not in video file and it goes in while loop. to overcome this join main thread if it not returns in specific time
 /// </summary>
 /// <param name="audioFilePath"></param>
 /// <param name="noOfAudioFiles"></param>
 /// <param name="recognizer"></param>
 private void codeBlock(string audioFilePath, int noOfAudioFiles, SpeechRecognitionEngine recognizer)
 {
     try
     {
         recognizer.SetInputToWaveFile(audioFilePath);
         RecognitionResult result = recognizer.Recognize(timeSpan);
         audioContentMessage += "\r\n" + result.Text;
     }
     catch (Exception)
     {
     }
 }

        // Initialize an in-process speech recognition engine.
        static void Main(string[] args)
        {
            using (SpeechRecognitionEngine recognizer =
             new SpeechRecognitionEngine())
              {

            // Create and load a grammar.
              string[] myWords = new string[] { "Me", "Kiss", "Fluff", "Yell", "Kind", "Crack", "Hope", "Check", "Lake", "Steep", "Shell", "Bark", "Tooth", "Mouse", "Force", "Fringe", "Flight", "Haunt", "Asked", "Going", "Table", "Giant", "Bully", "Treated", "Spying", "Wiggle", "Shredded", "Picnic", "Decoy", "Slaying", "Scheming", "Happier", "Joyous", "Riotous", "Chow", "Cookie", "Feud", "Eighty", "Host", "Weather", "Crawl", "Stew" }; //Sets the words that it will be listening for
            Choices commands = new Choices(); //Usually the system is sets up the words expected to be commands. Our "commands" will be the 42 words given.
            commands.Add(myWords); //This adds my 42 words to the commands to be recognized (commands being a list of words).
            GrammarBuilder gBuilder = new GrammarBuilder(); //This is setting up the system that will understand the words
            gBuilder.Append(commands);
            Grammar grammar = new Grammar(gBuilder);

            recognizer.LoadGrammarAsync(grammar);
            recognizer.SetInputToDefaultAudioDevice();

              //Grammar dictation = new DictationGrammar();
            //dictation.Name = "Dictation Grammar";

               // recognizer.LoadGrammar(dictation);

            StreamReader sr = new StreamReader(@"c:\Users\Taylor\Desktop\AllVoiceSamples\Input.txt");
            // Read the input file to a string
            String line = sr.ReadToEnd();

            // Configure the input to the recognizer.
            recognizer.SetInputToWaveFile(@"c:\Users\Taylor\Desktop\AllVoiceSamples\" + line);

            // Attach event handlers for the results of recognition.
            recognizer.SpeechRecognized +=
              new EventHandler<SpeechRecognizedEventArgs>(recognizer_SpeechRecognized);
            recognizer.RecognizeCompleted +=
              new EventHandler<RecognizeCompletedEventArgs>(recognizer_RecognizeCompleted);

            // Perform recognition on the entire file.
            Console.WriteLine("Starting asynchronous recognition...");
            completed = false;
            recognizer.RecognizeAsync();

            // Keep the console window open.
            while (!completed)
            {
              Console.ReadLine();
            }
            Console.WriteLine("Done.");
              }

              Console.WriteLine();
              Console.WriteLine("Press any key to exit...");
              Console.ReadKey();
        }

        protected void decode()
        {
            try
            {
                SpeechRecognitionEngine SpeechRecognitionEngine = new SpeechRecognitionEngine();
                DictationGrammar DictationGrammer = new DictationGrammar();
                SpeechRecognitionEngine.LoadGrammar(DictationGrammer);

                SpeechRecognitionEngine.SetInputToWaveFile(Input);
                RecognitionResult Result = SpeechRecognitionEngine.Recognize();
                mOutput = Result.Text;
            }
            catch (Exception E)
            {
                MessageBox.Show(E.Message);
            }
        }

//.........这里部分代码省略.........
                                                        gc.LogGrammar("<item><token sapi:pron=\"" + pronunciations[data.listOfWords[randomWordType]][i] + "\">" + data.listOfWords[randomWordType] + "_" + i + "</token></item>");
                                                    }
                                                    wordCount++;
                                                }
                                                else
                                                {
                                                    for (int k = 1; k <= MWordTypes; k++)
                                                    {
                                                        randomWordType = k;
                                                        // we don't add the "correct" word
                                                        if (randomWordType != iWordType)
                                                        {
                                                            wordTypesChosen.Add(randomWordType);
                                                            for (int i = 0; i < pronunciations[data.listOfWords[randomWordType]].Count; i++)
                                                            {
                                                                for (int j = 0; j < MSample; j++)
                                                                {

                                                                    ConfusionMatrix[NTrainingSpeakers - 1, iTestSpeaker, MSample * (iWordType - 1) + j, numberOfAlternates * (randomWordType - 1) + i].den++;
                                                                }
                                                                gc.LogGrammar("<item><token sapi:pron=\"" + pronunciations[data.listOfWords[randomWordType]][i] + "\">" + data.listOfWords[randomWordType] + "_" + i + "</token></item>");
                                                            }
                                                            //System.Diagnostics.Debug.WriteLine("word chosen: " + randomWordType);

                                                        }

                                                    }

                                                    break;
                                                }
                                                //ConfusionMatrix[NTrainingSpeakers - 1, iTestSpeaker, iWordType - 1, randomWordType - 1].den+=MSample;

                                                /*foreach (string pronun in pronunciations[data.listOfWords[randomWordType]])
                                                {
                                                    gc.LogGrammar("<item><token sapi:pron=\"" + pronun + "\">" + data.listOfWords[randomWordType] + "</token></item>");
                                                }*/

                                                //wordCount++;
                                            }
                                            gc.boundrule(false, "");
                                            gc.boundgr(false);

                                            // setup recognizer
                                            SpeechRecognitionEngine rec = new SpeechRecognitionEngine();
                                            rec.LoadGrammar(gc.getGrammar());

                                            // recognizing
                                            for (int iSample = 1; iSample <= MSample; iSample++)
                                            {
                                                rec.SetInputToWaveFile(data.getAudioName(iTestSpeaker, iWordType, iSample));
                                                RecognitionResult result;
                                                try
                                                {
                                                    result = rec.Recognize();
                                                }
                                                catch (Exception e)
                                                {
                                                    System.Diagnostics.Debug.WriteLine(e.Message);
                                                    System.Diagnostics.Debug.WriteLine(data.getAudioName(iTestSpeaker, iWordType, iSample));
                                                    continue;
                                                }
                                                //System.Diagnostics.Debug.WriteLine("recognising");
                                                if (result == null)
                                                {
                                                    ConfusionMatrix[NTrainingSpeakers - 1, iTestSpeaker, MSample * (iWordType - 1) + iSample - 1, numberOfAlternates * MWordTypes].num++;
                                                }
                                                else
                                                {
                                                    string[] word = result.Alternates[0].Words[0].Text.Split('_');
                                                    word = wordTypeResult(2, result);
                                                    //if (result.Alternates.Count > 2)
                                                     //   System.Diagnostics.Debug.WriteLine("No. of results found for wordType " + iWordType + "sample " + iSample + " = " + result.Alternates[2].Confidence);
                                                    ConfusionMatrix[NTrainingSpeakers - 1, iTestSpeaker, MSample * (iWordType - 1) + iSample - 1, numberOfAlternates * (Array.IndexOf(data.listOfWords.ToArray(), word[0]) - 1) + int.Parse(word[1])].num++;

                                                    if (word[0].Equals(data.listOfWords[iWordType]))
                                                        SampleAccuracy[NTrainingSpeakers - 1, NTrainingSamplesPerSpeaker - 1, Array.IndexOf(V, vocabSize), iTestSpeaker, iWordType - 1, iSample - 1].num++;

                                                }
                                                /*
                                                if (result != null && result.Alternates[0].Words[0].Text.Split('_')[0].Equals(data.listOfWords[iWordType]))
                                                {
                                                    SampleAccuracy[NTrainingSpeakers - 1, NTrainingSamplesPerSpeaker - 1, Array.IndexOf(V, vocabSize), iTestSpeaker, iWordType - 1, iSample - 1].num++;
                                                    //System.Diagnostics.Debug.WriteLine(NTrainingSpeakers + "_" + NTrainingSamplesPerSpeaker + "_" + Array.IndexOf(V, vocabSize) + "_" + iTestSpeaker + "_" + iWordType + "_" + iSample);
                                                }*/
                                                SampleAccuracy[NTrainingSpeakers - 1, NTrainingSamplesPerSpeaker - 1, Array.IndexOf(V, vocabSize), iTestSpeaker, iWordType - 1, iSample - 1].den++;

                                            }

                                            gc.Destroy();
                                        }
                                    }
                                }
                            }

                            // end testing
                        }
                    }
                }
            }
        }

        private string Recognize()
        {
            using (SpeechRecognitionEngine sre = new SpeechRecognitionEngine(new CultureInfo("zh-CN")))
            {
                Choices colors = new Choices(new string[] { "宝塔镇河妖" });
                GrammarBuilder gb = new GrammarBuilder();
                gb.Append(colors);

                // Create the Grammar instance.
                Grammar g = new Grammar(gb);
                sre.LoadGrammar(g);
                // Configure the input to the recognizer.
                sre.SetInputToWaveFile("d:\\output.mp3");
                RecognitionResult result = sre.Recognize();

                return result == null ? string.Empty : result.Text;
            }
        }

        private void button3_Click(object sender, EventArgs e)
        {
            SpeechRecognitionEngine recognizer = new SpeechRecognitionEngine();
            Grammar dictationGrammar = new DictationGrammar();
            recognizer.LoadGrammar(dictationGrammar);
            try
            {
                button3.Text = "Recognizing";
                recognizer.SetInputToWaveFile("c:\\InMind\\temp\\fromClient3.wav");

                RecognitionResult result = recognizer.Recognize();
                button3.Text = result.Text;
            }
            catch (InvalidOperationException exception)
            {
                button3.Text = String.Format("Could not recognize input from default aduio device. Is a microphone or sound card available?\r\n{0} - {1}.", exception.Source, exception.Message);
            }
            finally
            {
                recognizer.UnloadAllGrammars();
            }
        }