Introduction: Remote Trainer for XSEC-2.1 can work across a network provided a server machine runs the XSEC training Server. The requirements for a Machine for running XSEC remote Trainer are:

A good quality Microphone.
A camera with resolution 320 X 240.

The Training Serial: A trainee undertaking training using the Remote Trainer module is expected to have a training serial assigned by the Administrator. Each trainee is assigned a unique serial no. The serial proves the validity of the user who is willing to train the system.

How to get trained?

Step I: Once the Remote Trainer Module is executed, the form shown below will be evoked. User must have a training serial number assigned by the Administrator. He is then expected to supply the required information in the form. If the XSEC Server is running on a local computer, then Server IP will be 127.0.0.1 else user will have to provide the valid IP so as to get connected to the XSEC Server. Once the data is supplied user is expected to click on the "Post To XSEC Server" to connect to the Server. Status label will show the current status of the trainer.


 

Step II: After the verification the panel shown below will be opened. This shows the training panel where user will have to supply his face and voice samples. We will discuss the training session in two separate phases Face and Voice namely.

Face Training Phase: This phase intends to take 8 pictures of the user and train the system properly for the user. Please follow the following steps to complete this session successfully.

1. First check if the lighting conditions are appropriate.
2. There are two orthogonal lines in the camera panel. User is supposed to fix up his face as shown in the picture above.
Horizontal line must match the line connecting both eyes of the user.
Vertical line must match the nose line of the user.
3. Allow small movements in the face and click on the "Take Snap Shot" button to take a picture.
4. If unsatisfied, click on the "Cancel Last Snap Shot" button to cancel the last picture taken.
5. Once, 8 pictures are taken user may move to Voice Training Phase.

Voice Training Phase: This phase intends to take speech samples of the user. In the text area, a sentences will be flashed whose words will be separated by "-". User will be required to supply 5 successful recordings of the sentence. Please follow the steps below.

1. Click on the "Start Recording Utterance" button and keep pause for about 3 seconds.
2. Now start uttering the sentence word by word keeping a small pause of about 1 seconds.
3. After finishing all the words, again keep a small pause of about 3 seconds.
4. Now click on the button "Stop Recording Utterance" to stop recording.
5. Continue above steps for 5 successful times.

Now click on the "Submit" button to send all user specific features to the XSEC Server through a secured encrypted protocol. After submission a message box will be flashed telling if the submission was successful.