Software

private async Task AssistantSetup()
{
    // Initialize recognizers (speech-to-text) and speaker (text-to-speech)
    Windows.Globalization.Language language = new Windows.Globalization.Language("en-US");
    background_recognizer = new SpeechRecognizer(language);
    task_recognizer = new SpeechRecognizer(language);
    speaker = new SpeechService("Male", "en-US");

    task_recognizer.Timeouts.InitialSilenceTimeout = TimeSpan.FromSeconds(10);
    task_recognizer.Timeouts.EndSilenceTimeout = TimeSpan.FromSeconds(5);

    // Initialize media player
    media_player = BackgroundMediaPlayer.Current;
    await CreateSongsList();

    // Compile recognizer's grammar
    SpeechRecognitionCompilationResult background_compilation_result = await background_recognizer.CompileConstraintsAsync();
    SpeechRecognitionCompilationResult task_compilation_result = await task_recognizer.CompileConstraintsAsync();

    // If compilation has been successful, start continuous recognition session
    if(background_compilation_result.Status == SpeechRecognitionResultStatus.Success)
        await background_recognizer.ContinuousRecognitionSession.StartAsync();

    await GUIOutput("Hi, I'm Alan. How can I help you?", true);

    // Set event handlers
    background_recognizer.ContinuousRecognitionSession.ResultGenerated += ContinuousRecognitionSessionResultGenerated;
    background_recognizer.StateChanged += BackgroundRecognizerStateChanged;
    media_player.MediaEnded += MediaPlayerMediaEnded;
    media_player.CurrentStateChanged += MediaPlayerCurrentStateChanged;
}

In the first four lines we set English as language for recognition and synthesis. Notice that there are two recognition agents ( background_recognizer and task_recognizer) and one synthesis agent (speaker). The difference between background_recognizer and task_recognizer is that the latter is used just to detect single phrases (the commands) whereas background_recognizer runs a continuous session. In particular, task_recognizer required us to set the following timeouts:

• InitialSilenceTimeout sets the time interval during which the recognizer accepts input containing only silence before finalizing recognition.
• EndSilenceTimeout sets the interval of silence that the recognizer will accept at the end of an unambiguous input before finalizing a recognition operation.

private async Task TaskSelection()
{
    if(state == AssistantState.BACKGROUND_DEFAULT)
        state = AssistantState.LISTENING_DEFAULT;
    else if(state == AssistantState.BACKGROUND_MEDIA_PLAYER)
    {
        state = AssistantState.LISTENING_MEDIA_PLAYER;
        media_player_volume = media_player.Volume;
        ChangeMediaPlayerVolume(10.0);
    }
    else if(state == AssistantState.BACKGROUND_STOPWATCH)
        state = AssistantState.LISTENING_STOPWATCH;

    // Stop continuous recognition session and wait for user's command
    await background_recognizer.ContinuousRecognitionSession.StopAsync();
    await GUIOutput("I'm listening.", true);
    SpeechRecognitionResult command = await task_recognizer.RecognizeAsync();

    // The list of possible tasks changes according to the state
    if(state == AssistantState.LISTENING_DEFAULT)
        await StandardTasksList(command.Text);
    else if(state == AssistantState.LISTENING_MEDIA_PLAYER)
        await MediaPlayerTasksList(command.Text);
    else if(state == AssistantState.LISTENING_STOPWATCH)
    {
        if(command.Text == "close")
            CloseStopwatch();
        else
            await GUIOutput("I'm sorry, I couldn't understand.", true);
    }

    // Restart continuous recognition session
    await background_recognizer.ContinuousRecognitionSession.StartAsync();
    return;
}

This piece of code performs state transitions (e.g. from BACKGROUND_DEFAULT to LISTENING_DEFAULT) and selects the proper command set according to the new state (StandardTasksList and MediaPlayerTasksList are functions). Notice that, if the media player is running (i.e. the current state is BACKGROUND_MEDIA_PLAYER), the volume is automatically turned down in order to ease the understanding of the vocal input.

private async Task StandardTasksList(string command)
{
    if(command == "what time is it")
    {
        var now = System.DateTime.Now;
        await GUIOutput("It's " + now.Hour.ToString("D2") + ":" + now.Minute.ToString("D2"), true);
        state = AssistantState.BACKGROUND_DEFAULT;
    }
    else if(command == "what day is today")
    {
        await GUIOutput(System.DateTime.Today.ToString("D"), true);
        state = AssistantState.BACKGROUND_DEFAULT;
    }
    else if(command == "tell me a joke")
        await TellJoke();
    else if(command == "play some music")
        await PlayMusic();
    else if(command == "save a reminder")
        await SaveReminder();
    else if(command == "any plans for today")
        await SearchReminder();
    else if(command == "tell me something interesting")
        await RandomWikiArticle();
    else if(command == "what's the weather like today" || command == "how's the weather today")
        await GetWeatherInfos();
    else if(command == "inspire me")
        await GetInspiringQuote();
    else if(command == "open the stopwatch")
        await OpenStopwatch();
    else if(command == "search a recipe")
        await SearchRecipe();
    else
    {
        await GUIOutput("I'm sorry, I couldn't understand.", true);
        state = AssistantState.BACKGROUND_DEFAULT;
    }

    return;
}

Here we can see the commands that can be given to the assistant when its current state is LISTENING_DEFAULT. Every feature is managed by a function except for time and date requests.