How to use spinprocrecocontext and trigger events with C#

See more:

C#

Speech-SDK

speech

recognition

, +

I'm very close to completing a personal project for modifying the Windows speech dictionary via C# (SAPI 5.4). The last bit I'm working on is how to get the SAPI phone set for a given word. I've found a way to do this via a C# form and spoken recognition obtained through SpSharedRecoContext. However I'm trying to get the recognition to work with a voice file (*.wav) as the input. I understand that this needs to be done via an SpInprocRecoContext.

Nearly every example from Microsoft I've found regarding SAPI 5.4 recognition (like this one for VB) is for SpSharedRecoContext and not SpInprocRecoContext (and I believe I've seen comments that some of these examples are missing details). Additionally, I've found multiple topics on Stack Overflow (mostly answered by Eric Brown, see topic 1, topic 2, topic 3) that mention using a SpInprocRecoContext requires more setup than SpSharedRecoContext, but I have yet to find a definitive answer for how to capture voice recognition events when using SpInprocRecoContext in C#.

How can I proceed on this? Any help would be extremely appreciated!!

What I have tried:

Here is my code so far:

using SpeechLib;
using System;

namespace SpeechTest
{
    class Program
    {       
        static void Main(string[] args)
        {
            string MyText = "dolphins"; // Text string of interest
            string WaveFile = @"C:\Reco\MYWAVE.wav"; // Path to wav file used for voice recognition

            // Declare important recognition objects
            SpInprocRecognizer Recognizer;
            SpInProcRecoContext RecoContext;
            ISpeechRecoGrammar grammar;
            ISpeechFileStream MyFileStream;
            ISpeechVoice MyVoice;

            // Create recognizer and recognition context
            RecoContext = new SpInProcRecoContext();
            Recognizer = (SpInprocRecognizer)RecoContext.Recognizer;            

            // Set up recognition event handling            
            RecoContext.Recognition += new _ISpeechRecoContextEvents_RecognitionEventHandler(RecoContext_Recognition);

            // Set up the grammar
            grammar = RecoContext.CreateGrammar(); // Initialize the grammar
            grammar.DictationLoad("", SpeechLoadOption.SLOStatic); // Set up dictation grammar
            grammar.DictationSetState(SpeechRuleState.SGDSActive); // Activate the grammar

            // Set up audio input for SpInProcRecoContext
            SpObjectTokenCategory Category = new SpObjectTokenCategory();
            Category.SetId(SpeechStringConstants.SpeechCategoryAudioIn);
            SpObjectToken AudioToken = new SpObjectToken();
            AudioToken.SetId(Category.Default);
            Recognizer.AudioInput = AudioToken;

            //Category.SetId(SpeechStringConstants.SpeechCategoryRecognizers); // <== generates a runtime error!!!
            //SpObjectToken EngineToken = new SpObjectToken();
            //EngineToken.SetId(Category.Default);
            //Recognizer.Recognizer = EngineToken;

            //Category.SetId(SpeechStringConstants.SpeechCategoryRecoProfiles); // <== generates a runtime error!!!
            //SpObjectToken ProfileToken = new SpObjectToken();
            //ProfileToken.SetId(Category.Default);
            //Recognizer.Profile = ProfileToken;

            // Create an audio file stream from MyText
            MyFileStream = new SpFileStream(); // Create new SpFileStream instance
            TextToWave(MyText, WaveFile); // Call function to create a wav file that voices MyText
            MyFileStream.Open(WaveFile, SpeechStreamFileMode.SSFMOpenForRead, true);

            // Activate the recognizer and input the audio file stream into the recognizer
            RecoContext.State = SpeechRecoContextState.SRCS_Enabled;
            Recognizer.State = SpeechRecognizerState.SRSActive;
            Recognizer.AudioInputStream = MyFileStream; // <== generates a runtime error!!!

            // Output info and cleanup
            Console.WriteLine(MyText + " = " + SAPIPhonemes);
            MyFileStream.Close();
            Console.ReadLine();
        }

        static void TextToWave(string text, string file)
        {
            SpFileStream fileStream = new SpFileStream();
            SpVoice voice = new SpVoice();

            fileStream.Open(file, SpeechStreamFileMode.SSFMCreateForWrite, true);
            voice.AudioOutputStream = fileStream;
            voice.Speak(text);

            fileStream.Close();
        }

        public static string SAPIPhonemes = null;

        public static void RecoContext_Recognition(int StreamNumber, object StreamPosition, SpeechRecognitionType RecognitionType, ISpeechRecoResult Result)
        {
            // This event is recognized and all the below code works fine when using SpSharedRecoContext

            Console.WriteLine(Result.ToString());
            string SAPIPhonemes = null;
            SpPhoneConverter MyPhoneConverter = new SpPhoneConverter();
            MyPhoneConverter.LanguageId = 1033;

            foreach (ISpeechPhraseElement MyPhrase in Result.PhraseInfo.Elements)
            {
                SAPIPhonemes += " " + MyPhoneConverter.IdToPhone(MyPhrase.Pronunciation);
            }
        }
    }
}

For reference here is the form-based SpSharedRecoContext code that works:

using SpeechLib;
using System;
using System.Windows.Forms;

namespace RecoForm
{
    public partial class Form1 : Form
    {
        // Speech Recognition Object
        SpSharedRecoContext listener;

        // Grammar object
        ISpeechRecoGrammar grammar;

        public Form1()
        {
            InitializeComponent();
        }

        private void Form1_Load(object sender, EventArgs e)
        {
            // nothing
        }

        public string ps;
        private void button1_Click(object sender, EventArgs e)
        {
            if (btnListen.Text == "Start Listening")
            {
               // textBox1.Clear();
                try
                {

                    listener = new SpSharedRecoContext();
                    listener.Recognition += new _ISpeechRecoContextEvents_RecognitionEventHandler(listener_Reco);
                    grammar = listener.CreateGrammar(0);
                    grammar.DictationLoad("", SpeechLoadOption.SLOStatic);
                    grammar.DictationSetState(SpeechRuleState.SGDSActive);
                    btnListen.Text = "Stop Listening";
                    if (ps == "1")
                    {
                        listener.Resume();
                        ps = "0";
                    }
                }
                catch (Exception ex)
                {
                    MessageBox.Show(ex.Message);
                }
            }
            else if (btnListen.Text == "Stop Listening")
            {
                listener.Pause();
                btnListen.Text = "Start Listening";
                if (ps == "0")
                {
                    ps = "1";
                }
            }
        }        

        public void listener_Reco(int StreamNumber, object StreamPosition, SpeechRecognitionType RecognitionType, ISpeechRecoResult Result)
        {
            string heard = Result.PhraseInfo.GetText(0, -1, true);
            textBox1.Text += " " + heard;

            SpPhoneConverter MyPhoneConverter = new SpPhoneConverter();
            MyPhoneConverter.LanguageId = 1033;

            foreach (ISpeechPhraseElement MyPhrase in Result.PhraseInfo.Elements)
                textBox2.Text += " " + MyPhoneConverter.IdToPhone(MyPhrase.Pronunciation);
        }
    }
}

// https://stackoverflow.com/questions/11935533/c-sharp-sapi-5-4-languages

Here is another example (in VB) that combines the Microsoft examples (here and here) which STILL doesn't work (see the comments in Command1_Click to find the location where I encounter a runtime error):

Imports SpeechLib

Public Class Form1
    Const WaveFile = "C:\Reco\MYWAVE.wav"

    Dim WithEvents RC As SpInProcRecoContext
    Dim Recognizer As SpInprocRecognizer
    Dim myGrammar As ISpeechRecoGrammar
    Dim MyFileStream As SpeechLib.SpFileStream
    Dim MyVoice As SpeechLib.SpVoice
    Dim MyText As String

    Private Sub Form1_Load(sender As Object, e As EventArgs) Handles MyBase.Load
        On Error GoTo EH

        RC = New SpInProcRecoContext
        Recognizer = RC.Recognizer

        myGrammar = RC.CreateGrammar
        myGrammar.DictationSetState(SpeechRuleState.SGDSActive)
        MyVoice = New SpVoice
        MyVoice.Voice = MyVoice.GetVoices("gender=male").Item(0)

        Dim Category As SpObjectTokenCategory
        Category = New SpObjectTokenCategory
        Category.SetId(SpeechStringConstants.SpeechCategoryAudioIn)

        Dim Token As SpObjectToken
        Token = New SpObjectToken
        Token.SetId(Category.Default)
        Recognizer.AudioInput = Token

        TextBox1.Text = "play the eight of clubs"

EH:
        If Err.Number Then ShowErrMsg()
    End Sub

    Private Sub Command1_Click(sender As Object, e As EventArgs) Handles Command1.Click
        MyFileStream = MakeWAVFileFromText(TextBox1.Text, WaveFile)
        MyFileStream.Open(WaveFile)
        Recognizer.AudioInputStream = MyFileStream ' ==> produces a runtime error!!!
    End Sub

    Private Sub RC_Recognition(ByVal StreamNumber As Long, ByVal StreamPosition As Object, ByVal RecognitionType As SpeechLib.SpeechRecognitionType, ByVal Result As SpeechLib.ISpeechRecoResult)
        On Error GoTo EH

        TextBox2.Text = Result.PhraseInfo.GetText

EH:
        If Err.Number Then ShowErrMsg()
    End Sub

    Private Sub ShowErrMsg()

        ' Declare identifiers:
        Const NL = vbNewLine
        Dim T As String

        T = "Desc: " & Err.Description & NL
        T = T & "Err #: " & Err.Number
        MsgBox(T, vbExclamation, "Run-Time Error")
        End

    End Sub

    Private Function MakeWAVFileFromText(ByVal strText As String, ByVal strFName As String) As SpFileStream

        On Error GoTo EH

        ' Declare identifiers:
        Dim FileStream As SpFileStream
        Dim Voice As SpVoice

        ' Instantiate Voice and FileStream objects:
        Voice = New SpVoice
        FileStream = New SpFileStream

        ' Open specified .wav file, set voice output
        ' to file, and speak synchronously:
        FileStream.Open(strFName, SpeechStreamFileMode.SSFMCreateForWrite, True)
        Voice.AudioOutputStream = FileStream
        Voice.Speak(strText, SpeechVoiceSpeakFlags.SVSFIsXML)

        ' Close file and return reference to FileStream object:
        FileStream.Close()
        MakeWAVFileFromText = FileStream

EH:
        If Err.Number Then ShowErrMsg()
    End Function
End Class

' https://msdn.microsoft.com/en-us/library/ee125184%28v=vs.85%29.aspx
' https://msdn.microsoft.com/en-us/library/ee125344(v=vs.85).aspx