About Praphul Kumar

Praphul Kumar works as Sales & Business Solution Specialist at Angel. With Bachelors from IIT Roorkee, India and MBA from UMD College Park, USA, Kumar has more than 10 years of experience in Engineering, Product and Marketing. He has extensive knowledge around Mobility, Social Media and Business Intelligence and has helped many of Angel’s customers solve their business problems around these areas.

Understanding Natural Language Processing

Natural Language Processing

As technology is slowly improving to mimic human-like interaction, many businesses are looking to provide such experiences to their customers—the kind that comes with systems, like Amtrak Julie, that can understand the intent of the caller. Suddenly natural language processing (NLP) has become a buzzword much like “cloud computing.” How do you know if NLP is the right technology for you? That requires a longer discussion.

To understand NLP, it’s important to understand how automatic speech recognition (ASR) works. The way I generally explain it is that it’s very similar to your understanding of foreign languages. When we learn a foreign language, we build a list of words we can understand. These words or phrases in the ASR system are called grammars. If you speak anything outside that list, ASR system doesn’t understand what you are saying. Based on some research done in the IVR industry, the average rate at which callers say things that are not on the list of pre-defined IVR grammars varies from 15–30%. Assuming 95% accuracy in understanding grammar-driven words, our current IVRs can only understand around 70 percent of total caller interaction.

One way to reduce this out-of-list grammar problem is to introduce more comprehensive lists of words and phrases but this process is expensive and time consuming and, in the end, you can do only so much. A true natural language–based solution solves these problems as it works by building a statistical model using machine learning with the goal of understanding the caller’s intent rather than matching a set of words. Let’s take an example: you are interacting with an IVR and you have to enter a four-digit PIN; you say something like, “One, two, five, four—not five, four—three, four.” It would be pretty hard for an IVR to understand but NLP would do a great job. A successful natural language deployment means fewer agent transfers, more containment, and higher customer satisfaction.

So what is stopping businesses from completely switching to NLP technology? Well, it takes a huge amount of time (often years) and resources to train the machine. Businesses find it very hard to justify the ROI, and often results vary widely from one system to another. Although I do not see IVR replaced by NLP technology in the near future, I do believe it has the potential of becoming a force to be reckoned with. What do you think? Let me know in the comments!


What Would Steve Jobs Have Done to an IVR Company?

Like millions of others, I was very upset after hearing the bad news on October 5. We lost a great innovator. I was pondering over everything he has given to this world and suddenly, this thought crossed my mind – what would Jobs have done if he were CEO of an Interactive Voice Response (IVR) company?

I was excited about the idea, but it was a tough question to answer, as Jobs always did the unimaginable. Nevertheless, I decided to give it a shot. Below are three things Jobs strongly believed in, and how I believe he would have applied them to IVR:

1. Awesome User Experience: Jobs would not release a product without ensuring great user experience, and great user experience comes from great design. That means he would have enabled easy to use graphic tools to allow IVR developers to create great voice applications which could then run on highly optimized speech engines. I also strongly believe that he would have allowed the IVR developer community to develop applications and sell them as apps. I can imagine a business downloading an app for a payment IVR, or maybe downloading multiple apps and putting them together to create an entire call flow. It would have just opened the door for innovation and we would have seen some great voice apps.

2. Married Hardware-Software Solutions: Through providing software and hardware together, Jobs focused on providing technology that worked well together, making it easy to use. With this in light, I believe Jobs would have gone with hosted IVR solutions, as this model would have helped him provide highly optimized solutions without creating a huge entry barrier for businesses in terms of cost. He strongly believed in cloud technology, as shown by iCloud, and hosted IVR concepts would have completely resonated with him. Hosted solutions would also have enabled him to capture data from all callers and improve speech engines through combining data from multiple systems. The more caller data you have, the better speech engines can capture names, addresses and natural languages.

3. Mobility: Jobs wouldn’t rest without giving the world some great mobile-based solutions. I think Jobs would have come up with a Siri-like experience for consumers. Who knows? He might have developed some unified solution/app which would allow callers to interact with businesses through preferred channels. Many of those interactions would happen over the web and hence eliminate the need of making a phone call.

Well, it was not easy putting myself into his shoes. I feel overwhelmed and need some caffeine!  While I’m fueling up, comment with your thoughts. How do you think Jobs would have approached the IVR industry?


Driving Next Gen IVRs

Next Gen IVRs

The Changing Face of IVRs

Technology is changing fast and IVRs are no exception. Businesses looking for ways to connect with their customers through multiple channels are gathering as much data as possible and analyzing it to better understand consumer behavior and to better serve them through successful business strategies.

There are four major market drivers that every successful multi-channel business strategy focuses on: mobility, social media, business analytics and cloud. No business can afford to ignore the power of these forces and, while there is no secret formula to do so, they must be integrated with your IVR to obtain optimal results.


With the capacities of smart phones growing so rapidly, these phones definitely provide a great—if not a must-have—mode to communicate with your customers. Taking advantage of real-time data, iPhone/Android-based apps and text messages along with outbound calls to keep customers up to date with releases, outages and case statuses are some of the ways firms can stay connected with their on-the-go customers.

Social Media

I get customers asking all the time how they should leverage the power of social media. A solution that enables decision makers to have access to social media channels right on their handheld devices wouldn’t be a bad start. Social intelligence is also gaining traction—I see a lot of value in allowing agents and supervisors in a call center to have access to Twitter and Facebook (maybe even Google+) to interact with and learn from these channels on a real-time basis.

Click here to read more »