Skip to main content

IVR Speech Recognition- KooKoo can now hear you

When we acquired Yantrasoft, the goal was to integrate their speech capabilities into the core KooKoo platform so that KooKoo developers can start building speech applications.

We took a first step towards that goal today with the release of a new KooKoo tag, <recognize>. The tag is free for all users of KooKoo and all developers can immediately start using it.

Our vision is to solve the customer communication problem for businesses. This is another big leap in that direction. This will help your user communicate a lot more easily. 

Entering touch tones is inconvenient, where user has to move the phone from ear and back to press digits or has to put it in front on speaker phone. Imagine the same to be done when using handsfree in car. Our first release of digit pack solves this problem. Now user can just say the digits, confirm saying yes or no and navigate the IVR hassle free.

This would sound miniscule as compared to google and siri that recognize the natural dialogue. While we can talk about the tech that enables such recognition, I would just say that we are solving diffrent problem which has its set of challenges, that limits similiar recognition. Just to make a point, here is demo of how google works when on a phone call  https://www.youtube.com/watch?v=cN0q8SvlQAk. India with many dilalects makes it even harder.

Our approach allows speech to be helpful, but not blocking i.e we enable press or say. It may happen that speech may not work for someone, that doesnt stop him from using IVR, its his choice to say or press the button like regular IVR. Both will work seamlessly.

Our approach to speech is to make it easily available to our user, without they having to know about how speech recognition works, similar to what we did for telecom when we launched KooKoo. 

Ozonetel will be rolling out multiple domain specific word packs for e.g. cities/state, grocery, banking, insurance etc. These would be already trained and tested for accuracy, and our team would continuously monitor and improve it for better accuracy. Kookoo users just have to use the tag to add speech recognition to their application. 

The recognize tag allows you to include speech recognition capabilities into your IVR application. To start with we are just supporting a couple of grammars.

1. "digit" grammar: This will allow you to recognize digits spoken on the phone. You can use this to recognize pin numbers, OTP, phone numbers, IVR choices.
2. "yesno" grammar: This will allow you to recognize "yes/no". A little surprise, this grammar also accepts hindi. So it recognizes even "haan/naa".  Very useful to ask questions and get a yes or no answer from your callers.

Documentation

You can check out a small demo by calling 040-30247041. It will ask you to say a number from 1 to 9. Say a number from 1 to 9 and wait. The IVR will repeat the number spoken by you.

We are moving from "Please press 1 for sales or 2 for support" to "Please say 1 for sales or 2 for support". It will not be long before you can say "Please say sales or support" :)

Yeah Baby!

Signup for KooKoo

Popular posts from this blog

Integrating Arborjs with Angular to create a live calls dashboard

Arborjs  is a cool graph visualization library. Angular  is one of the best JavaScript frameworks and we have been using Angular in a lot of our front end development. When you handle millions of calls, proper visualization becomes very important. Without proper visualization, you can get lost in the mountains of data. So we spend a lot of time to come up with good visualizations to represent the data. Since we loved the cool way in which Arbor represented graph data, we could not wait to hook it up with Angular. Because of Angular's two way data binding, when you hook up Angularjs with Arbor.js you can get a dynamically updated visualization of graph data with cool animations. To give back to the community, we have put up the code online at Github . Basically we have created an Angularjs directive for Arborjs. Please feel free to fork the code and add extensions and use it for your own visualizations. The code is self explanatory with comments inline. Best way to ...

First Post

In this blog, I will be talking about my experiences in trying to build a cloud telephony platform , KooKoo . Along the way I will also be talking about different design choices I made, good programming practices and the IVR domain in general. For technoratti: NNFJW8EW86C3

Cloud Telephony-History and state of the art

Well, its been 11 years since Twilio launched their voice API in November 2008. I would say that was a major turning point in the cloud telephony industry. Before that, for people to build telephony applications, you either had to depend on proprietary platforms like Avaya dialog designer or build on arcane technologies like VXML which again was supported at varying degrees by the incumbents. Enter Twilio with their voice API and the industry changed for the better. Since it's been almost 11 years now I thought now might be a good time to do a comprehensive review of the cloud telephony industry as a whole in general and in India in particular. The Beginning Twilio was undoubtedly the startup which ushered in the era of cloud telephony. They started in November 2008. At that time in India, we at Ozonetel had launched a hosted VXML platform. There were no takers. After all who coded in VXML :) So when Twilio launched and we saw them take off, we immediately realized tha...