An audible Bangla text-entry method in Mobile phones with intelligent keypad

Abstract

Communication through mobile device is the most effective and fastest way that becomes a part of our daily life nowadays. Particularly, Short Message Service (SMS), is one of the most popular and relatively cheaper application of cell phone. In Bangladesh, there has been an enormous growth of mobile users and in this context, it is quite reasonable that people like to send SMS with their own language. Taking these challenges, a few initiatives were taken to introduce Bangla text in Mobile phones, more specifically, in messaging. But unfortunately, Bangla SMS is not popular yet in our country due to the presence of large number of characters and complex script. In fact, it is very much difficult to map Bangla characters efficiently on a mobile with 12 keys only. That's why, it motivated us to design an intelligent mobile keypad layout, which significantly reduces the number of keystrokes than existing methods, and remove difficulties of entering text. We eliminate traditional multi-tapping on a single button and introduce two key press technique, by arranging characters in two-dimensional matrix. Using this keypad the system becomes faster, reliable and flexible. Predictive text input method is also added in the system for further speeding up messaging. Moreover, our text-entry system ensures accessibility to visual impaired people by avoiding disambiguation caused by multi-tapping and introducing audio feedback for inserting each Bangla characters, which is not supported by existing systems. Finally, after analyzing the result on different sample SMS data, we showed that, our proposed keypad with the predictive input system reduces the number of key presses than the common Bangla keypad by 60.34%.