Technology is evolving rapidly. The major focus of this evolution is to make things easier for the users and make their life more comfortable.

Who could forget this?

I remember the day when my dad brought home our first television set. It was a black and white TV with no remote (remote wasn’t even a thing back then). We had these knobs on the device using which you could increase/decrease the volume, switch the channels, and modify brightness/contrast. It was an amusing act for me initially to see things change while I play around but as time passed by, it became boring.



Then came the color television. This beautiful lady came with a remote, which was an extraterrestrial device to us at that time. Things got easier and obviously the one in the family who possessed the remote in their hand imagined themselves as a King/Queen while the others passed through requests about what they want to watch.

Xbox Kinect responding to voice commands

Today: Well, things have changed. Today, my TV acts on my voice. Now that I’ve connected my Satellite Box to my Xbox One (with Kinect), its’s totally voice controlled. I flip the channels by just saying the name of the channel to my device standing anywhere in the room.

Chitchat with Google’s digital assistant Allo

The same goes with my phone/laptop. Not to mention Apple’s Siri, Google Assistant, and Microsoft Cortana have been trying to assist the users by performing tasks according to their voice commands and they have been successful.

Now what’s happening with e-learning? The interactivity levels in e-learning have increased, but the way they do it hasn’t. I remember the courses we developed 8 years ago where the learner’s only chance to interact with the course was while clicking the Next/Previous buttons for every 3 minutes or so. This act of staying idle for so long did bore them as it’s a machine that they see before their eyes and not a person training which would’ve at least brought the aspect of liveliness.

Things have changed. We now develop highly interactive courses that require user inputs throughout. We have simulations that stay on par with games as to interactivity levels are concerned. However, the interaction methods have not changed.

Now that every technology is trying to be voice-activated starting from our phones to our cars, and even household appliances, why not use this concept in e-learning?

Where does it apply in e-learning?

We’re not talking about using the learner’s voice just to navigate through the course. Obviously, we do not want to invest so much time and effort to make them say “Previous/Next”. If at all we could integrate speech recognition systems into a e-learning program, we would want it to be justified and purposeful. Role-plays have become common in today’s learning programs.

A screenshot from the game SimCity

Especially, when you design simulation based programs where a lot of scenarios are involved, we write a lot of conversations. However, these conversations are limited to the dialogues we write from which, the user must select the appropriate ones. I somehow feel this method lacks something. If this was a classroom, the faculty would ask the learners to come up with their own dialogues and evaluate them. Isn’t that what we’re trying to recreate in an e-learning?

This is where speech recognition could do magic. Since the learner is participating in a digital role-play, we could as well use his/her voice to interact with the elements in the program. To begin with, the conversations. Of course, this would involve great amount of effort in terms of technology but VR isn’t cheap either. And remember, this takes learner involvement to another level and places them deep into the course where we want them to be. This could add a lot of value to the realism in our scenarios.

Another screenshot from the game SimCity where you play the role of a salesman

Imagine a sales rep scenario, where the learner takes on the role of a sales rep trying to sell the product to a customer. Imagine what all we could do by taking the learner’s voice as an input. We could help them do better by evaluating what they say, how they say it (tone), and when they say it (timing). Of course, this would require a lot of programming effort in the back-end.

Now that’s just one idea on how speech recognition could help create an engaging learning experience with TRUE involvement of learners. What are the other areas in e-learning you can think of where we can use this technology? Please share your views in the comments section below.