Conversational AI 101

A little bit of history

Before we begin our journey through the world of voice, we must first understand how human-computer interfaces have evolved. This will give us some perspective on why voice is being hailed as the next great disruption in the history of computing.

In the old days, before Windows or Mac were around, people interacted with computers through text-based commands. For example, there wasn’t a clock in the taskbar that you could use to check the time. You actually had to type in a command like “time” into a shell and the computer would show you the time.

Sometime in the 1980s, a company called Xerox came up with the concept of Graphical User Interfaces (GUIs). The theory was there, but the idea failed to take off until Steve Jobs and Apple realized the potential of GUIs. Then, Apple’s Mac took the world by storm. Soon after, Bill Gates and Microsoft, not to be left behind, joined the bandwagon with their Windows machines. The world of computers would never be the same.

“A picture is worth a thousand words.” This age-old adage now had new meaning as GUIs made interfaces more intuitive with visual elements. Anyone could start clicking around to get things done instead of having to memorize a dozen different commands. GUIs have remained relevant to this day, with the advent of smartphones only accelerating the ways in which we interact with technology. As the world moves towards being more mobile-oriented, GUIs will likely continue to be relevant in the coming decades.

Advent of Conversational AI and Voice User Interfaces

But, where does voice control come in? As they say, history repeats itself. We are at the cusp of another revolution in human-computer interaction (HCI); a new form of HCI technology is now taking the world by storm!

Conversational AI, powered by Voice User Interfaces (VUI), is making its way to homes worldwide, just as PCs found their way onto peoples’ desks during the 2000s and mobile phones have made their way into people’s pockets for the last decade.

But what exactly is Conversational AI?

Conversational AI is an umbrella term for a set of AI technologies that enable users to interact with computers more naturally through a Conversational User Interface. This is either done through speech (voice-based) or messaging (text-based).

Voice-based interfaces are those where users directly speak with the assistant, Like talking to Alexa or Siri. Speech-based interfaces are called Voice User Interfaces (VUI).

The alternative to VUI is a text-based interface. These include the customer service bots often found in e-commerce stores.

In this course, we’ll be looking at Voice User Interfaces and how they can enhance your apps.

Why Voice User Interface?

Verbal communication is as old as humanity itself. It only makes sense that the most intuitive form of communication with technology would be to speak with it! With advancements in artificial intelligence, Natural Language Processing (NLP)/Natural Language Understanding (NLU), and cloud technologies, talking to computers is no longer confined to the realm of science fiction.

Ever since Siri came out in 2011, millions of people have asked her questions ranging from “What time is it?” to “What is the diameter of the earth?” Got a question? All you need to do is ask! Voice User Interfaces have further exploded in popularity with the advent of AI assistants like Alexa, Google Assistant, Bixby, and Cortana.

These assistants are being integrated everywhere these days. Aside from dedicated devices like Amazon’s Echo, they are also available on our smartphones. Millions of people around the world use these assistants to get their jobs done just by asking.

Voice User Interfaces(VUI): Advantages

There are many advantages of using a voice interface. For example, it is much easier to ask Alexa to set an alarm for 6 am than to hunt for your phone on the sofa, open up the Alarm app, and set the alarm manually. Those steps just become one sentence; “Alexa set the alarm for 6 am.”

Here’s a list of other advantages for users:

• Convenient: All you need to do as a user is shout out a command! Fast: It usually takes less time for users to say what they want than do it manually in the software.
• Natural: Voice is a more intuitive way of interacting with technology. There is no need to learn how to use an interface. Frictionless and ubiquitous: Voice is frictionless, and Voice UIs are best suited to communicate with IoT devices. This makes them ideal for homes and cars and helps to make computing ubiquitous.
• Accessible and low cost: The IoT devices that run assistants are generally accessible and available at a low price.
• Accurate and reliable: Due to the latest developments in natural language understanding and increased accuracy in speech recognition, voice technology is becoming easier to use and more reliable by the day.
• Easy development: Developing voice applications as a third-party developer is surprisingly easy and fun), as we’ll see in this course.
• New experiences: Voice allows for new experiences in almost every domain, be it healthcare, the hospitality industry, restaurants, finance, or really any other sector.

Why should you care as a developer?

Millions of people worldwide now have access to some form of voice interface, either through smart devices like the Echo or on phones. Now is a perfect time for developers and brands to be thinking about how to solve problems for customers more naturally with voice control.

Some of the world’s biggest companies have been placing their bets on the voice ecosystem by making it easier for third-party developers to build the next generation of apps powered by voice. In this course, we will explore one such ecosystem - Amazon Alexa.

This course will give you all the tools to be the next pioneer of the voice revolution.