The Simon main window is split into four logical sections. On the top left, you can see the scenario section, to its right you find the training section, on the bottom left is the acoustic model and finally, on the right of that, the recognition section.
The Simon main window can be hidden at any time by clicking on the Simon logo in the system tray (usually next to the system clock in the task bar) which will minimize Simon to the tray. Click it again to show the main window again.
A list of scenarios shows the currently loaded scenarios. You can manage this selection by clicking which will open the scenario management dialog.
To modify a scenario, select it from the list and open it by pressing .
This section shows all training texts from all currently active scenarios.
Selecting a training text will highlight the parent scenario in the scenario section.
You can start to train the recognition by selecting a text and clicking on . Please note that, depending on your selected model type, training may or may not improve your recognition accuracy. The acoustic model section (see below) in the Simon main menu tells you if training will have an effect for your specific configuration. For more information, please refer to the base model section for background information on this subject.
The gathered training corpus can be managed by selecting which will open the sample management dialog.
Here, Simon shows information about the currently used base- and active model.
Select to configure the base model.
This section shows information about the recognition status.
If Simon is connected to the server, you can activate and deactivate the recognition by toggling the button. If this control element is not available, make sure you are connected by selecting → from Simons menu.
An integrated volume calibration widget monitors the configured recognition devices. The sound setup can be modified by selecting to bring up the sound configuration.