Siri, the new IPhone 4S feature has created quite a buzz around the globe among smart phone users! Actually, this new feature can be thought as a natural progress in mobile phone industry, from keyboard input, touch input, audio or video file stored from a host, and now a voice input to get things done by the phone! For example, using Siri, one can get few things done like :-

How Siri in IPhone will Help IVR

1. Call 911 ( or 100 in India) for police emergency!
2. Send text message by speaking.
and many more including searching restaurant nearby for you when you are hungry!

So, how does it affect IVR industry ?

I am very happy with this development of introduction of “Siri type application” in Apple SmartPhone! Recently, SmartPhones have been doing things which were also done by IVR with a phone call ( retrieve information quickly).

How Siri will help IVR ?

I hope, Siri will introduce concept of “Audio Menu” in masses and people will be receptive to the idea of listening to audio menus to learn things and perform task. Having to listen to audio menu has been one of the most hated thing about IVR. Siri type application help people realise its importance and usefulness in getting things done!

Many people have complained ( ridiculed) about having to speak to machines! Siri application in iconic Apple IPhone does the same, it gets a person to speak to his phone, except that the phone is not connected! So, with wide acceptance of Siri, people will stop ridiculing about having to speak to machine using IVR. I hope this will help in speaker recognition, IVR Payment gateway etc.

Finally, more people would be now involved in developing and training voice recognition engines and hope it will become more accurate in noisy environments. Also speaker recognition in IVR would be more used in verifying identities of callers.

So, I am hoping with introduction of Siri in Apple IPhone, Android Based Phones will also have some really smart Applications for accepting voice input!

IVR system is not just a clubbing together of state of the art CTI boards, high end servers, very easy to drag and drop tool design IVR call flow for flexibility. One of the saddest part about IVR development is, the users may not appreciate about these technological break-through like SS7, ISUP, CPA ( Call Progress Analysis), accuracy and speed of speech recognition or the or intricacies involved in detecting disconnect tone, engage tone.

They simply care about what menus they hear and if the options they press or speak works! They are least bothered about the hard work some one may have put in to detect her key presses, or recognise heavily accented English numerals, but only if the IVR retrieves the information it promised in its menu. The appreciate only when they can understand the information read out to her listening first time without having to press a key to listen again!

It may not be possible to satisfy all the users of an IVR system, but by using well scripted menus in simple language and intelligently constructed sentences may surely help majority of the people to use IVR system without having to learn the IVR before using it.

The answer to all these problems faced by IVR users and making IVR more useful and user friendly is ‘scripting of the IVR menus’! Script writing for IVR means, writing the IVR menu options in simplest language, well formed sentence so that the listener understands the message accurately without having to concentrate.

IVR scripting can be used in three areas to improve IVR usability:-

1. Scripting the menus
2. Dividing complex menus to simple sub menus
3. Scripting the phrases used for providing information

1. Scripting the Menus

This is quite straight forward. The menu options where IVR gives some options to the IVR user to either press telephone keys, or speak some word or phrase, should be properly scripted. Accuracy of the options is of course a must and forgone conclusion. For example, if the menu says, “To transfer your call to a customer care executive, please press 9″, then on pressing 9 by the caller, the IVR should transfer the call to customer care executive, not to the main menu!

2. Dividing complex menus

Script writers will divide complex options or large options will divide into some groups, and make it two level menus, in place of one. This will not only help first time callers, but also make it more user friendly faster with using ‘cut through’ key pressing!

3. Scripting phrases

Now a days, IVR has to retrieve many information from various locations through either database look up or by using API. Also, it may have retrieve information in bits and pieces from different servers, then knit them together, and then finally produce a sentence which would present a complete required message/information to the IVR user! Now that may not be easy for an IVR engineer! So, one must use a professional script writer for writing these phrases either to be recorded or used with TTS.

Without proper scripts used in IVR menus and in information, IVR will not be usable at all, even by expert IVR users! It will be very frustrating for users and all the great technologies used to design and develop IVR system will completely go waste!

Dialogic D/300 JCT-E1 is the entry level board for anyone who needs digital network interface with PSTN network as well as voice resources in the single board. I feel, D/300 board is most used entry

Dialogic D/300 JCT-E1 board

Features of Dialogic D/300 JCT-E1 board

1. Digital Network Interface

It has both E1(2.048MBPS) and T1(1.544 Mbps) support. It supports digital interface network protocols like ISDN PRI, R2MF. ISDN PRI is widely used protocol for connecting CTI board with PBX systems. With D/300 board, it is quite easy to configure it to work with many ISDN variants as per PBX from one country to another or manufacturer.

2. FAX support

Dialogic D/300 board supports both FAX and host based speech recognition. In certain cases, FAX and speech recognition may not work together. It also supports CSP ( Continuous Speech Processing) which offers IVR developers a powerful feature to develop many interesting IVR applications and features depending on the call progress. Speech recognition feature provides IVR developers to develop Speech-Enabled menu for any IVR application.

3. Scalability

Dialogic D/300 supports H.100 connector and it allows it to connect to other Dialogic boards. Inexpensive normal PC can be used to install this board and one PC may install upto 16 boards per machine if PCI slots are available.
With its support for GSM and G.726 bit exact voice coders ( standard for Voice Profile for Internet Messaging (VPIM) , one may develop unified messaging solutions based on D/300 board.

4. Programming

Dialogic D/300 board is supported by many RAD Tools for IVR development. It also supports widely popular GC ( Global Call Protocol) for making many high end, mission critical IVR applications.

Applications

D/300 board can be used to develop any kind of IVR applications. It offers many call related information available with digital network interface protocols. Call bridging available in ISDN PRI is one of the feature which is used to make Click To Call application can be developed.

D/300 board is also ideal choice for starting a voice portal service to start with 30 lines and then increase the lines.

DIalogic has some other models with higher capacity with same features. D/600 and DMV1200 have 60 voice and 120 resources respectively. One may move from D/300 to DMV/1200 without having to make any changes in the application.

Other CTI vendors like Donjin, Synway, Digium too have D/300 equivalent boards. For example, Digium TE122P/TE122B, Synway TEJ Series and Donjin DN300 are Dialogic D/300 equivalent boards with similar features.

What is Speaker Verification
Speaker verification, also known as speaker recognition, can be defined as process of authenticating ones claimed identity by comparing their voice and previously recorded or computed speech characteristics (voiceprint, which is as unique as finger print ). While speech recognition is widely used in IVR, speaker verification or recognition is different than speech recognition and is relatively recent addition to numerous usage of IVR systems.

Speaker verification is one of the recent and advanced IVR feature which is increasingly being used some IVR applications where personal identification is very important, for example, Banking, attendance registration etc.

How it can be used in IVR ?

As the name suggests, speaker verification is essentially used for authentication a IVR caller to manage his account. Since now, IVR systems have been authenticating its caller with ‘password’ or PIN ( Personal Identification Number) by pressing telephone keys or DTMF or even speech recognition.

Normally, while using speaker recognition for user authentication, IVR caller is asked to speak a random phrase which is compared with caller’s existing voice print. This is a quicker process for user authentication.

Advantages of Speaker Verification

The age-old IVR user authentication method of asking caller to enter a 4 digit ( or 5 digit) PIN is slow as well as it needs to changed periodically. But with usage of speaker recognition, authentication process is faster and IVR may ask a caller to speak any phrase randomly without user having to remember PIN or keep changing it periodically.

Another method of caller verification was using ANI (Automatic Number Identification) or Caller ID. But though detection of caller ID is fool proof, but this kind of user authentication may not be fool proof as anybody could dial from user’s phone number. But speaker recognition with voice print does not suffer from these drawbacks. Speaker recognition along with speech recognition may provide almost fool prof user authentication.

How it helps usability of IVR

With speaker recognition, customer details could be retrieved quickly from CRM ( Customer Resource Management) and many routine questions to a caller could be avoided. Caller would be happier not having to repeat his information each time he calls to the IVR.

Since it authenticates a caller much faster, it can provider any service quicker to the caller and usability of the IVR increases.

Many people may feel frustrated having to enter PIN or change it periodically for security reasons. But with speaker recognition, a caller just has to speak a given phrase and can authenticate herself. Many people. specially the one, who use call center or IVR rarely, may forget PIN. With speaker recognition, user does not need to remember any PIN or change the PIN periodically.

I have posted one article how IVR can be used to generate revenue, mainly from caller paying to use the IVR services through a voice portal in collaboration with a telecom operator. No doubt, it is a lucrative Voice VAS(Value Added Service) for many M-VAS companies as well as telecom operators, but there are other ways too where one can use IVR to generate revenue, even without any collaboration with any telecom operator.

Also, one of the negative side of collaborating with telecom operator is, they take away majority of the revenue generated while IVR service provider does all the investment as well as majority of the promotions for the IVR services.

There comes in IVR E-Com portal! One may actually generate revenue by establishing an IVR e-com portal! IVR e-com portal can be thought of as corresponding voice portal for an e-com ( e-commerce) web portal. While an e-com portal is accessed using a web browser on a PC/Laptop or mobile phone, IVR e-com portal is accessible by any phone or mobile phone. A successful IVR e-com portal can be even hosted on a toll free number where caller will not be charged anything!

An IVR e-com portal would be capable of selling products like music album after listening to music trailers, can buy movie tickets after hearing some famous dialogues of the movie etc.

Credit card can be charged securely on IVR e-com portal for making payment. Delivery of products would be just like e-com portal, by using courier or postal service.

There are few advantages of IVR e-com portal. For example :-

1. Easy browsing
User will be focused on browsing category wise and will not be distracted by many colorful links as in a e-com web portal. Browsing of products are quick and to the point.

2. Selling Adult products
Many people, specially in India, are unable to buy many products like condom from a chemist shop. There have been many advertisements by governments and other NGOs encouraging people to buy condoms from chemist shops boldly. Using IVR e-com portal, everybody would be able to buy condom or other adult products without any inhibition.
3. Listen trailer
For products like musical album, children CD, etc. could be heard on IVR e-com portal by browsing through them. They can also listen user feedback in original voice form by celebrity users or common users. It will increase authenticity of testimonial of the products.

4. Good option for certain disabilities
IVR e-com portal is a solution for people with visual disabilities. Presently, I am not aware if there is any shop or e-com portal for people with visual disabilities. IVR e-com portal can serve them better with many options.

Challenges in running IVR e-com portal
There are some disadvantages of IVR e-com portal. Many products would be difficult to sell on IVR e-com portal. For example, shirts, pants etc.
Also, not many people may want to dial an IVR and pay for the outgoing call. Also many people may not like the idea of pressing keys on phone many times while browsing through products. Clicking on keys are easier than pressing buttons on phones.

Apart from few ticketing IVR service for airlines, IVR e-com portal has not really picked up or even started. Most probably, not many people are thinking in this direction. If you are thinking now to start IVR e-com portal abd make Ebay in IVR, remember me too that I also had this idea. . Jokes apart, in my next articles I would try to list the services which could be sold or how IVR e-com portal could be monetized.

What is IVR customisation ?
Normally, an IVR application is designed and developed as per requirement of the customer by IVR companies. But they have ready-made modules tested and readily available for quick development. Normally, the modules like, telephone interface, ring detection, caller ID detection, database connectivity etc. are always readily available. Also many people use RAD tools for IVR customization where they simply implement call flow required by the customer. So IVR customising can be described as implementing call flow of the IVR application as desired by customer using existing IVR related software modules.

In fact, after RAD (Rapid Application Development) tools have been introduced, IVR development have become just IVR customisation. Many IVR functionality, modules are available in RAD tools ready-to-be-used. It is not easy to develop an IVR application from scratch, as it involves auxiliary knowledge and experience about telecommunication switches, telecommunication standards and protocols, speech recognition, TTS.

While RAD tools are easy and quickest way to developed customised IVR application, but it may not suitable for IVR customisation which needs to interact with existing business processes or existing software which generate various data to be provided by the IVR. For example weather update, complaint ticket generation, complaint status update etc. Apart from these kind of complex and very sophisticated IVR systems, RAD tools are excellent development or customisation tools for IVR solutions.

One important aspect which many people overlook is writing script of voice prompts and recording of voice prompts professionally. IVR systems are to be deployed to be used by normal people for availing services, solutions from it. IVR system interacts with its user ( caller to the IVR) through voice prompts. Any mistake in voice prompts may render the IVR useless. For example, if the voice prompts announces, “to know your complaint status, press 1, or press any key to end the call.” Now imagine if IVR is coded to recognize 1 for disconnecting the call and any other key for asking further information to retrieve complaint status!

So, while customising IVR application, one must write script for voice prompts and record them with professional voice artists. Without this, IVR system may have the best of the hardware and most well coded software, still IVR system will not be useful to its intended users.

While customising an IVR application, one should think about future enhancements. Many times, one finds out that existing codes can not be used for enhanced services, features and everything needs to be done from scratch. This not only delays the process of upgrading IVR systems, also it become costlier.

While integrating with third party application or software, direct interaction with their database should be avoided. If you do so, any changes made by them would require you to make changes in your code too. So I think HTTP URL is a very good approach where you send few parameters for exchanging data from third party application. This will ensure that your IVR code need not be changed even if third party database is changed.

What is TTS ( Text to Speech) ?
TTS or Text To Speech is a process where text is converted to WAV file and played back. So it is a system or often called “engine” that converts text to voice. If some one types a sentence in a note pad, a TTS software would convert it to voice ad play it through speaker attached to computer or laptop.

What does IVR System do ?
IVR System plays recorded voice on a telephone when a caller calls in. So, it is obvious that instead of playing recorded voice, IVR can play text file using TTS engine.

TTS software or engine:-
There are many TTS engines available. Many TTS engines are built in computer operating system. Microsoft SAPI5.1 is such TTS engine which is available for Windows Operating System. Voiceover is built-in TTS engine for MAC OS Leopard. There are various companies which make TTS engines. For example : AT&T, Nuance, SVOX etc.

Using TTS with IVR System
TTS is very useful when there are lot of dynamic content to be provided to caller in a voice portal. The use of TTS in IVR system is quite easy! Every TTS engine comes with SDK (Software Development Kit) which can be used to integrate with IVR application developed in various tools. Almost all RAD Tools for developing IVR applications, support TTS as well as speech recognition.

TTS produces voices which can be recognised easily that it is generated by a computer, not by human. So, people who are used to listening to human voice, may not be able to understand TTS easily. It is specially true for people whose first language is not English. Most of the world’s TTS engines support English. Recently many companies are developing TTS for other languages as well.

It may take some time, but it is expected that quality of TTS voice will increase where everyone will be able to understand TTS Engine generated voice easily. That will help voice portals immensely.

VUI ( Voice User Interface) is the call flow of IVR system. Usability of IVR is dependent on the VUI. So it is desirable that considerable amount of time be devoted in designing, testing and documenting VUI of IVR system before actually developing IVR system.

Here are few simple VUI design guidelines of tips I have thought of :

1. Identify specific purpose of IVR system
First step towards designing VUI should be the question, why would a caller call the IVR system and how quickly efficiently IVR should reply to his “why”. If the purpose of an IVR system is to record customer complaint, allow customer to lodge their complaint in the first menu itself. IVR should not try to act very smart or human by asking intelligent questions and get the caller answer before it actually is able to lodge the complaint. The other way is to allow the caller lodge the complaint, provide him complaint ticket and then ask few polite questions about details of the his complaint an which is completely optional. IVR system should stick to its specific purpose in its operation.

2. Maximum 3 Levels of menu
Stick to maximum 3 levels of menus before caller gets his desired information after calling a IVR system. A caller should not be “interviewed” or put through “set of question answer session” till he gets the desired information. In many IVR system, it is observed that, trying to be smart, caller is put through set of questions, many irrelevant options before actually providing the information required by the caller. So, golden rule should be, provide maximum 3 levels of menu, before a caller is answered or provided the final information.

3. Provide Shortcuts as per usage
IVR system should have in-built MIS (Management Information System) to enable finding out the most used menus and information. Depending on the usage, shortcut should be provided to access the widely used menus quickly. Many repeat caller will not like to go through the same menu and having to choose same options before his desired menu options. Even a first time caller may like to use the shortcut once the shortcut is explained.

4. Top Level Menu options
By top Level Menu options, I mean the menu options provided to caller as soon as his call is answered. This is the menu which is to be designed very carefully and success of IVR system may depend on this menu to a large extent. This menu should not be long list of options, but few main specific purposes of the IVR system. And this menu should be changed as per usage statistics. For example, if the 4th option here has less usage than 3rd option of the second level option of 1st top level option, than most probably, it is time to bring the second level option to top level menu. If the IVR system is a call center and human agent is available, then I strongly suggest that option should be given to caller in Top Level menu to speak to a human agent.

5. Voice prompts
Voice scripts should be simple English or the language the IVR is using. The language should be really simple and easy to understand, without any grammatical errors. It should be spoken as if you are speaking in daily conversation with regular pauses. A good menu design may look totally ridiculous if proper scripting and voice prompts are not used.

There are five VUI design tips I have been using in all my IVR works. VUI is a must for IVR usability.

There are few basic difference between outbound and inbound IVR Application. Normal IVR Application deals with inbound calls and call transferring. But an outbound IVR performs the few more tasks than an Inbound IVRS! And this is purely call handling point of View.

Though inbound application may have to do more computation as it has wider applications. But outbound calls have greater challenges in development. Here are few points to ponder about developing an outbound IVR Software:

1. Outbound calls may encounter various called parties! For example, the number dialed may turn out to be FAX number, so as soon as your call gets connected, IVR will get a FAX tone! So IVR has to detect FAX tone and and take appropriate action! It is specially important where outbound calls are payable as well as the usage time needs proper recording! It may face not only FAX, but also voice mail, answering machine, call forwarding etc.

2. Starting the message ( playback audio file ) after connection is very crucial! For example, if you detect FAX tone, you need to disconnect, not play the message! Same for Voice Mail, Answering Machine.

3. Deciding the type of card is also important. According to me, digital cards are better suited that analog cards. Here by digital cards, I am meaning digital interface like ISDN, R2MF, SS7! CTI cards are of course digital! Digital CTI boards can perform better in detecting FAX tone, Voice Mail, Answering Machine! Also, they give quick disconnection which important for call accounting.

4. Call synchronization is important. As outbound IVR Application will dial out multiple number simultaneously and some calls will be unsuccessful, which need to be retried! These kind of mechanism should be important and properly taken care of.

Few Features which are useful in an outbound IVR Application:

1. Outbound IVR application should have call transfer facility as an option just like inbound IVR application.

2. It should also have called party interaction through DTMF or Speech recognition.

3. The messages should be short and quick.

Speech recognition in IVRS has become more of a necessity after mobile phones have arrived. POTS ( Plain Old Telephone ) System have telephone instrument with proper keypad along with head-set. Procedure of calling is suitable for pressing DTMF based interaction with IVR System!

You normally lift the headset with left hand, dial pressing keys on telephone instrument using your right hand. So, when IVR is connected and you are listening to the voices by IVR System as well as pressing keys! While in a mobile phone, the tiny instrument itself is head-set, so when you are listening to IVR instructions, it is almost impossible to press keys without removing from your ear and looking at keys! The one solution is to use ear-phone or blue-tooth powered wireless headset!

Most probably, this has given prompted IVR developers as well as CTI vendors to come out with speech recognition for IVR Input. Though, speech recognition has evolved a lot, still speech recognition can not claim to perform 100%. This happens mainly because of pronunciation, accents of language from one region to another.

There are many speech recognition engines available. Nuance, Loquendo, Microsoft, Spinvox etc. are few companies which provide speech recognition engines on various technologies.

IVR with speech recognition capabilities are supposed to more advanced and suitable for mobile user, but it is actually very difficult to predict if the IVR application and speech engine will be able to recognise speech command properly. But IVR with Speech Recognition has been on the rise and every IVR Company now a days provide speech recognition. CTI vendors too support speech recognition in their hardware.

But still many people like me, will prefer to use DTMF for giving command to IVR as it sounds more technical. Most probably some people will take time get used to the idea of commanding some invisible machines by speaking!