Efrat Barak @CodingChick

private async void Button_Click_1(object sender, RoutedEventArgs e)

{

    //SpeechRecognizerUI class, engine + ui.

    var recognizerWithUI = new SpeechRecognizerUI();

    // Activate recognition (with the dictation grammar by default). Get result

    SpeechRecognitionUIResult recognizerResult = await recognizerWithUI.RecognizeWithUIAsync();

    // Display the result in a TextBox.

    MessageBox.Show(string.Format(“I heard {0}.”, recognizerResult.RecognitionResult.Text));

}

SpeechRecognizer reco = new SpeechRecognizer();

// Add a dictation grammar to the grammars collection in the recognizer.

reco.Grammars.AddGrammarFromPredefinedType(“typeName”,

                    SpeechPredefinedGrammar.Dictation);

SpeechRecognizer reco = new SpeechRecognizer();

// Add a WebSearch grammar.

reco.Grammars.AddGrammarFromPredefinedType(“typeName”,

                    SpeechPredefinedGrammar.WebSearch);

• SRGS grammar- which is an XML based file, written in the standard Speech Recognition Grammar Specifications format. These XMLs are meant for more complex sentences and syntax and have a lot of ways to change and create. How to write an SRGS XML is out of the scope of this blog post, I have provided links to resources  about SRGS and how to write them at the end of this post. In order to add an GRGS file to our application we use the method AddGrammarFromURI, which accepts only absolute URIs.

    SpeechRecognizerUI recoWithUI = new SpeechRecognizerUI();

    // Initialize URI with my path to the SRGS XML file.

    Uri babylon5Grammer = new Uri(“ms-appx:///Babylon5Characters.grxml”, UriKind.Absolute);

    // Add the SRGS grammar to the grammars collection.

    recoWithUI.Recognizer.Grammars.AddGrammarFromUri(“b5″, babylon5Grammer);

<?xml version=“1.0“ encoding=“utf-8“ ?>

<grammar version=“1.0“ xml:lang=“en-US“ root=“characters“ tag-format=“semantics/1.0“

          xmlns=“http://www.w3.org/2001/06/grammar“          xmlns:sapi=“http://schemas.microsoft.com/Speech/2002/06/SRGSExtensions“>

  <rule id=“characters“scope=“public“>

    <one-of>

      <item> John Sheriden </item>

      <item> Jeffry Sinclair </item>

      <item> Londo Molari </item>

      <item> Delenn </item>

      <item> Susan Ivanova </item>

    </one-of>

  </rule>

</grammar>

    Uri babylon5Grammer = new Uri(“ms-appx:///Babylon5Characters.grxml”, UriKind.Absolute);

    // Add SRGS grammar from file to Grammars

    recoWithUI.Recognizer.Grammars.AddGrammarFromUri(“b5″, babylon5Grammer);

    List<string> farscapeCharacters = new List<string> { “John Crichton”, “Aeryn Sun”, “Ka Dargo”, “Chiana”, “Rygel” };

    // Add list of strings to grammar as well

    recoWithUI.Recognizer.Grammars.AddGrammarFromList(“myFarscapeCharactersList”, farscapeCharacters);

    recoWithUI = new SpeechRecognizerUI();

    recoWithUI.Recognizer.SetRecognizer(InstalledSpeechRecognizers.All.First());

The default recognition language set by the OS is accessible in the InstalledSpeechRecognizers.Default property.

Automatically (I changed the OS language to German):

• Grammar settings- which were already discussed earlier, we can either use the property Grammars to get existing grammars as an object called SpeechGrammar set (that is a wrapper around a list with some extra), or add grammars to the list using the given Add methods (AddGrammarFromList, AddGrammarFromPredefinedType and AddGrammarFromURI)
• Async options- we can use the SpeechRecognizer’s PreloadGrammarAsync method to load grammars ahead of time, and therefor avoid waiting time when starting to use the recognizer. The method RecognizeAsync which starts the recognizing action in SpeechRecognizer or RecognizeWithUIAsync method for SpeechRecognizerUI both have only async calls.
• Audio events – these are two events that are already handled automatically by the SpeechRecognizerUI object, but if we want to create our own logic, we can subscribe to them. AudioCaptureStateChanged event occurs when the capturing sound mode has changed, AudioProblemOccurred occurs occurs when there is some problem with the audio. The code for handing these events will be:

private SpeechRecognizer _recognizer;

public MainPage()

{

    InitializeComponent();

    _recognizer = new SpeechRecognizer();

    // Subscribe to the AudioCaptureStateChanged event.

    _recognizer.AudioCaptureStateChanged += Recognizer_AudioCaptureStateChanged;

    // Subscribe to the AudioProblemOccurred event.           

    _recognizer.AudioProblemOccurred += Recognizer_AudioProblemOccurred;

}

void Recognizer_AudioProblemOccurred(SpeechRecognizer sender, SpeechAudioProblemOccurredEventArgs args)

{

    // Get the value of the enum SpeechRecognitionAudioProblem from event args, to determine nature of problem

    SpeechRecognitionAudioProblem speechRecognitionAudioProblem = args.Problem;

    //Handle problem accordingly

    if (speechRecognitionAudioProblem == SpeechRecognitionAudioProblem.TooSlow)

    {

        //Do something…

    }

    else if (speechRecognitionAudioProblem == SpeechRecognitionAudioProblem.NoSignal)

    {

        //Do something else

    }

    //…Continue with more problem options

}

void Recognizer_AudioCaptureStateChanged(SpeechRecognizer sender, SpeechRecognizerAudioCaptureStateChangedEventArgs args)

{

    //Get the state of the audio that has changed to figure out what happened from event args

    SpeechRecognizerAudioCaptureState speechRecognizerAudioCaptureState = args.State;

    //Handle changed audio state

    if(speechRecognizerAudioCaptureState == SpeechRecognizerAudioCaptureState.Capturing)

    {

        //Do something…

    }

    else if (speechRecognizerAudioCaptureState == SpeechRecognizerAudioCaptureState.Inactive)

    {

        //Do something else

    }

}

var recoWithUI = new SpeechRecognizerUI();

string[] babylon5Characters = { “John Sheriden”, “Jeffry Sinclair”, “Susan Ivanova”, “Delenn”, “Londo Molari”, “G’Kar” };

recoWithUI.Recognizer.Grammars.AddGrammarFromList(“myB5CharactersList”, babylon5Characters);

//Display to the user what we are expecting as an answer

recoWithUI.Settings.ExampleText = “Londo Molari”;

//Ask the user a question

recoWithUI.Settings.ListenText = “Who is your favorite Babylon 5 character?”;

// Read the result out loud or not

recoWithUI.Settings.ReadoutEnabled = false;

//Show the confirmation page after a successful recognition.

recoWithUI.Settings.ShowConfirmation = false;

SpeechRecognitionUIResult recoResult = await recoWithUI.RecognizeWithUIAsync();

var recoWithUI = new SpeechRecognizerUI();

string[] confusingBabylon5Characters = { “Delenn”, “Gelenn”, “Mellen”, “Bellen” };

recoWithUI.Recognizer.Grammars.AddGrammarFromList(“myB5CharactersList”, confusingBabylon5Characters);

SpeechRecognitionUIResult recoResult = await recoWithUI.RecognizeWithUIAsync();

StringBuilder builder = new StringBuilder();

//Get alternate results from recognition, (provided 10 as the maximum number of alternate results I want to retrieve)

IReadOnlyList<SpeechRecognitionResult> speechRecognitionResults = recoResult.RecognitionResult.GetAlternates(10);

foreach (SpeechRecognitionResult speechRecognitionResult in speechRecognitionResults)

{

    builder.AppendLine(speechRecognitionResult.Text);

}

MessageBox.Show(builder.ToString());

<?xml version=“1.0“ encoding=“utf-8“ ?>

<grammar xmlns=“http://www.w3.org/2001/06/grammar“ xml:lang=“en“

          xmlns:xsi=“http://www.w3.org/2001/XMLSchema-instance“

          xsi:schemaLocation=“http://www.w3.org/2001/06/grammar

                             http://www.w3.org/TR/speech-grammar/grammar.xsd“

          version=“1.0“ mode=“voice“ tag-format=“semantics/1.0“ root=“main“>

  <rule id=“main“ scope=“public“>

    <item repeat=“0-1“>character</item>

    <ruleref uri=“#babylon5Characters“/>

    <tag>out.MyB5Character=rules.babylon5Characters;</tag>

  <item repeat=“0-1“>and</item>

    <ruleref uri=“#farscapeCharacters“/>

  <tag>out.MyFarscapeCharacter=rules.farscapeCharacters;</tag>

  </rule>

  <rule id=“babylon5Characters“>

    <one-of>

      <item> John Sheriden <tag>out=”JS”;</tag></item>

      <item> Jeffry Sinclair <tag>out=”SJ”;</tag></item>

      <item> Londo Molari <tag>out=”LM”;</tag></item>

      <item> Delenn <tag>out=”D”;</tag></item>

      <item> Susan Ivanova <tag>out=”SI”;</tag></item>

    </one-of>

  </rule>

  <rule id=“farscapeCharacters“>

    <one-of>

      <item> John Crichton <tag>out=”JC”;</tag></item>

      <item> Aeryn Sun <tag>out=”AS”;</tag></item>

      <item> Ka Dargo <tag>out=”KD”;</tag></item>

      <item> Chianna <tag>out=”C”;</tag></item>

      <item> Rygel <tag>out=”R”;</tag></item>

    </one-of>

  </rule>

</grammar>

var recoWithUI = new SpeechRecognizerUI();

Uri babylon5Grammer = new Uri(“ms-appx:///Babylon5Characters.grxml”, UriKind.Absolute);

recoWithUI.Recognizer.Grammars.AddGrammarFromUri(“b5″, babylon5Grammer);

SpeechRecognitionUIResult result = await recoWithUI.RecognizeWithUIAsync();

//I use StringBuilder and add the entire semantics dictionary to a list of strings.

StringBuilder builder = new StringBuilder();

foreach (KeyValuePair<string, SemanticProperty> keyValuePair in result.RecognitionResult.Semantics)

{

    //For each semantic on the list I want to add the key (name of the out param from xml), how many values it has, and what is the first available value)

    builder.AppendLine(keyValuePair.Key);

    builder.AppendLine(keyValuePair.Value.GetAllValues().Count().ToString());

    builder.AppendLine(keyValuePair.Value.GetAllValues().First().ToString());

}

MessageBox.Show(builder.ToString());

SpeechRecognitionUIResult result = await recoWithUI.RecognizeWithUIAsync();

SpeechRecognitionUIStatus speechRecognitionUiStatus = result.ResultStatus;

if (speechRecognitionUiStatus == SpeechRecognitionUIStatus.Succeeded)

{

    //Do one thing

}

else if (speechRecognitionUiStatus == SpeechRecognitionUIStatus.Cancelled)

{

    //Do something else

}

//Add more enum values to handle…