The speech recognition engine can be controlled using the Speech applet in the control panel. The settings that can be configured on the Speech Recognition tab include the following:

  • Speech Recognition Engine settings
  • Speech Recognition profile settings
  • Speech recognition accuracy
  • Microphone settings

Speech Recognition Engine Settings
From the Speech Recognition tab, you can select the SRE to use. If multiple engines are installed, you can use the drop down arrow under the Language section to select which one to use. Some engines will also support special features. You can click the Settings button beside the SRE to configure such features. If the Settings button is not available, it simply means that the engine selected does not support any custom features.

Speech Recognition profile settings
Windows XP stores recognition profiles. The information stored within a profile is used to recognize your voice. You can create different profiles for different users or for different noise environments. To change speech recognition profile setting options, use the steps listed below:

  1. Click Start and click Control Panel.
  2. Double click the Speech applet.
  3. Click the Speech Recognition tab.
  4. Under Recognition Profiles, highlight the profile you want to configure.
  5. Click the Settings button.
  6. Use the sliders to configure the following two options:
    • Pronunciation Sensitivity – This setting allows you to control the confidence level. Moving the slider to tells Windows XP that you want the computer to reject any command when it is not confident of what you said. When you use this setting, the computer makes fewer recognition errors but more frequently rejects your commands. Therefore, you may have to enunciate more slowly and clearly. By moving the slider to Low sensitivity, Windows XP will respond to your command when it has almost no confidence that it has correctly recognized what you said. When you use this setting, the computer recognizes fewer commands but rarely rejects a command. This option affects only command and control programs.
    • Accuracy vs. Recognition Response Time – This setting allows you to configure the accuracy/response time. When you move the slider to the Low/Fast setting, the computer performs limited processing. The recognized text appears on the screen quickly but with low accuracy. Conversely, by using the High/Slow setting, the computer processes more for higher accuracy but produces the dictated text more slowly. This option affects command-and-control programs and dictation programs.
  7. Click OK once you have made your configuration changes to return to the Speech Recognition tab.

Training Your Profile
Under the Recognition Profiles section, you will also see an addition button called Train Profile. This allows you to train your profile to improve speech recognition accuracy. The more the speech engine knows about your particular style of speaking and the sounds in your environment, the more accurate it will be. When you click the Train Profile button, the Voice Training Wizard will appear. The wizard will collect voice samples from you so that it can adjust to your particular speaking style.

Microphone settings
Finally, at the bottom of the Speech Recognition tab, you can configure microphone settings. Keep in mind that speech recognition performance is dependent on the type of microphone you are using and different microphones will have specific requirements.

The Microphone Wizard will appear once you click the Configure Microphone button. The wizard will walk you through the process of configuring and testing your microphone for use with speech recognition.

In the final installment of this series, you will learn how to use Windows XP’s Speech Recognition.

[tags]Speech Recognition Engine, SRE, speech recognition, XP[/tags]