Speech and gesture
The increasing spread of computer systems in daily activities of so many people, it is necessary to “humanize” the use of these systems through modes of interaction “natural”, such as the voice, the look, the gestures. Combining multiple modes of interaction, to get the systems easier and more pleasant to use, is the purpose of interfaces called “multimodal”.
Check your computer without using a keyboard and mouse for many people it can be an interesting diversion, but for others it is a pressing need, either for temporary impediments (situations in which the hands are involved), or to congenital problems.
The technologies which, appropriately combined, allow this type of applications are:
- recognize voice commands: the user “order” to the microphone which action should be performed by the computer;
- voice synthesis (Text To Speech): the computer “answer” to the user, notifying the outcome of a request, or propose one of the possible choices.
The availability of low-cost sensors, such as Leap Motion and Kinect, and the maturity of speech recognition and synthesis technologies now make it possible to integrate gesture recognition and voice in professional applications aimed at different sectors, in which people, during their daily activities, they must interact with a computer but can not touch the mouse or keyboard.
Some examples of application:
- a surgeon can view the diagnostic images on a monitor in the operating room , without touching anything;
- a warehouseman can follow the instructions given by the system (location and goods to be taken) through a mobile device clipped to your belt, and confirm reading the check digit verification;
- an inspector inside a cold room can dictate their own annotations on the state of the products contained;
- an attendant at a production line can control the operations of your computer via gestures, without having to use touch-screen devices;
- a maintenance technician in an industrial plant can query and respond vocally to the computerized system of supervision to follow the ‘checklist’ of operations;
Thanks to its experience in this sector, Voisis is able to achieve multimodal interfaces for different needs.