Interactive Question and Answer Learning Through Voice Recognition
Interactive Question and Answer Learning Through Voice Recognition
Abstract
E-learning nowadays needs to adapt to the different technological advances in our society. The
so-called Technology-based training has becoming more and more popular. Technology-based
training (TBT) uses computer-based tools to enhance the training process, typically by
involving trainees actively rather than passively (Lavrakas, 2008). With the development of the
voice recognition software, a new opportunity to e-learning awaits us. People of different ages
embrace smartphones as a necessity (Miakotko, 2017). Incorporating speech recognition
together with smartphones can make e-learning more fun, productive and efficient. Thus, the
aim of this study is to create an application for smartphone users that interactively provide
questions thru speech and the learner will provide answer through speech also and the
application will identify if it is correct or wrong. The application can provide explanation
through speech also if the learner’s wants to.
Introduction
E learning can change the way of educational system in our society. Adapting to different
technological advances can change the way e-learning evolves. Schools already using different
tools of e-learning but the fast pace of technology changes is on the run. Telecommunication
tools like the television and the internet are already in used but its capability is limited (Lin,
2006). The so-called Technology-based training (TBT) has becoming more and more popular.
Technology-based training uses computer-based tools to enhance the training process, typically
by involving trainees actively rather than passively (Lavrakas, 2008). With the development of
the voice recognition software, a new opportunity to e-learning awaits us. People of different
ages embrace smartphones as a necessity (McNutt, 2017). This is all because Smartphones
already have capabilities beyond our expectations. Capabilities like internet communication,
information retrieval, video, e-commerce and other features make smartphones the preferred
gadget by anyone.
The use of smartphones significantly outstripped personal computers. Similarly, computing and
mobile devices have become ubiquitous on today’s college campuses. According to Harris
Interactive College Explorer Study today’s college students are connected via digital
communication devices throughout the day spending on average eleven hours with their devices
and roughly 1.3 million students have smart phones with which they communicate daily. The
massive infusion of computing devices and rapidly improving Internet capabilities are altering
the learning and teaching pedagogies in higher education. A 2000 Campus Computing Survey
revealed that the majority of college professors use email to communicate with their students,
and approximately one-third of college courses use Web resources or have a class Web page
(National Survey of Information Technology in US Higher Education). Similarly, Jones reports
that a great majority of college students using digital media 80 percent believing that Internet
use has enhanced their learning experience. (Motiwalla, 2009). Incorporating speech recognition
together with smartphones can make e-learning more fun, productive and efficient.
In other studies, the use of avatar, en image that represents a user in a multi-user virtual reality
space, is already developed and used in different institutions. An avatar functions as a
communications interface linking a user with the information the user needs. An avatar is not a
video demonstration and neither is it a cartoon sample. An avatar has a built in element of
interactivity. It responds to the users’ requests and needs, it provides a clear, insightful, rapid
link to an information database, and it does so in a manner that is easy to understand. Certainly,
avatars are not the only communications interface in e-Learning, and they are not the interface
of choice in every e-Learning application. But as the technology that makes them possible
continues to advance and become more accessible to developers, avatars are becoming more
important where interactivity, learner engagement, and cultural factors are important design
considerations (Sheth, 2003).
Speech recognition has long been existed in our society. From personal computers and now
existed already as integrated capability of smartphones. For the two types of speech recognition,
the Trained Speech Recognition (TSR) which involves a specified user training the software to
recognize his/her own voice and the independent speech recognition (ISR) software which uses
different types of algorithms to recognize speech from any user (Pritchard, 2008), the ISR is the
more appropriate one to be used in this study considering the time and the type of users
nowadays that have little patience in every sense of work.
Methodology