Publishers of technology books, eBooks, and videos for creative people

Home > Articles

  • Print
  • + Share This
This chapter is from the book

Using Speech Recognition

Control Panel's Speech utility controls Windows' speech-recognition and text-to-speech (speech synthesizer) features.

Speech recognition lets you speak into a microphone to control your computer; you can give commands that the computer will carry out or dictate text that will self-type on your screen. You can create a voice profile that trains your computer to understand you better. You can use speech recognition to dictate documents and email messages, use your voice to control programs and browse the web, and avoid repetitive-strain injuries by reducing the use of your mouse and keyboard.

Currently, speech recognition works for:

  • Nearly all applications that come with Windows
  • Microsoft Word and Outlook (but not Excel and PowerPoint)

Windows' text-to-speech (TTS) utility reads aloud onscreen text, buttons, menus, filenames, keystrokes, and other items by using a speech synthesizer. The only built-in program that reads to you is Narrator, which has its own voice controls (see "Accommodating Disabled Users" earlier in this chapter). You can find other TTS programs at www.microsoft.com/enable.

To set up speech recognition for first use:

  1. Choose Start > All Programs > Accessories > Ease of Access > Speech Recognition.

    or

    Choose Start, type speech recognition in the Search box, and then press Enter.

    Click Start Speech Recognition to open the Set Up Speech Recognition wizard. Figure 4.57 shows the wizard's first two pages.

    Figure 4.57

    Figure 4.57 This wizard helps you set up your microphone, learn how to talk to your computer, and train your computer to understand your speech.

  2. Follow the onscreen instructions.

To set speech options:

  1. Choose Start > Control Panel > Ease of Access > Speech Recognition > Advanced Speech Options (on the left) > Speech Recognition tab (Figure 4.59).
    Figure 4.59

    Figure 4.59 You must train a speech recognizer to adapt to the sound of your voice, word pronunciation, accent, and speaking manner.

  2. In the Language section, choose a speech-recognition engine from the drop-down list or click Settings (if available) to show additional engine properties.
  3. In the Recognition Profiles section, click New to create a new recognition profile for your voice; then follow the onscreen instructions when the wizard opens.
  4. In the Microphone section, set and configure your audio input device.
  5. Click OK (or Apply).

To use speech recognition:

  1. Choose Start > Control Panel > Ease of Access > Speech Recognition (refer to Figure 4.58).
  2. Click Open the Speech Reference Card to use a quick reference while you give commands and dictate text.
  3. Switch back to Speech Recognition and click Start Speech Recognition.

    If you haven't yet set up speech recognition, the Set Up Speech Recognition wizard opens; see "To set up speech recognition for first use" earlier in this section.

    See the sidebar for an example session.

To set TTS options:

  1. Choose Start > Control Panel > Ease of Access > Speech Recognition > Advanced Speech Options (on the left) > Text to Speech tab (Figure 4.60).
    Figure 4.60

    Figure 4.60 For U.S. English, the robotic voice of Windows is named Microsoft Anna.

  2. In the Voice Selection section, choose one of the available TTS voices from the drop-down list or click Settings (if available) to display additional voice properties.

    The selected voice speaks the text in the "preview voice" box.

  3. In the Voice Speed section, drag the slider to adjust the voice's rate of speech.
  4. Click Audio Output to set the preferred device for voice playback.
  5. Click OK (or Apply).
  • + Share This
  • 🔖 Save To Your Account