Most probably, the debate on merits and demerits of using ASR ( Automatic Speech Recognition) would continue for some time to come, but in case of India, there are three compelling reason avoid using ASR where simple, old, robust and universally understood ‘keypress’ can do. While ASR can surely speed up and increase interactivity of an IVR system, in Indian scenario, it can be a big nuisance, specially for IVR vendors providing IVR to be used nationwide.

Here are my reasons:-

1. Poor Recognition due to background noise

With due respect to all ASR engines, India is a loud country with lot of noises all around! So, with lot of background noise, it is not possible to recognise words or phrases with high degree of accuracy. Indian cities are noisy with lot of noise pollution all around. Even Indian houses are not well ventilated. Indian villages are crowed with various domestic animal who create lot of sounds.

Because of this background noises, good ASR engines also fail to perform properly and end up with poor accuracy. But users will never appreciate the ‘genuine’ technical problems behind this, but the blame will fall squarely on IVR developer or IVR Vendor.

2. Languages and Accent

India is home to 1652 languages. Out of these, 29 languages are spoken by more than more than 1 million people and another 122 are spoken by more than 10,000. It has officially recognised 22 languages. English is widely spoken and understood all around the country but India also has more than 250 million illiterate people.
So with this statistics, one can easily figure out the changes in accents for speaking even English numerals, forget about English words or Phrases!

This lack of common accent for speaking out any word or phrase prevent any ASR engine detecting them accurately. But, everyone who has dialed into an IVR system, already know how to press a key from the telephone instrument or the mobile. So, in order to wider use of IVR as well as accuracy, ASR should be avoided.

3. Poor Mobile Signal

Most of the recent telephone users in India are mobile phone users. Apart from big cities, large areas as well as large pockets of cities too, have poor network signal and keeps fluctuating rapidly. Due to which, two human may be able to somehow communicate, but in case of IVR, there chances that it would miss some voices, part of voice which are vital for recognising a word or phrase by ASR.

So, even the best ASR would fail to detect words accurately resulting in caller dissatisfaction, call abandonment which will defeat the very reason for using an IVR system.

While there would be remedies, tricks and techniques to address these problems, but these are top reasons if some one wants to avoid using ASR in India!

Like any other computer software, IVR too work inputs of responses provided by the user. Though, a computer application software has widely used input devices like keyboard, mouse, voice, even hand movement, IVR applications have limited, only two types of inputs or responses. One is telephone keypad which has 12 keys and automatic speech recognition!

Another specific difference between a normal computer application software and a IVR software is, IVR can provide the options sequentially in voice while computer application software can software options in various menus, buttons, drop down menu, quick links using related graphics etc. So IVR provides its options or tasks it can perform to a caller in series of voice announcement along with key option to press or word, phrase to speak for choosing the tasks. This is known as IVR menu.

With advent of hosted IVR services, IVR application has become designing of this menu system only, while the integration of CTI hardware with various PBX systems have become standard modules provided by hosted IVR service provider.

Irrespective of direction of call of the IVR ( inbound IVR or outbound IVR), menu starts as soon as the call is picked up. Normally, IVR starts with a “welcome prompt” typically welcoming the caller with greetings and quick short brief about the service, organisation behind the IVR.

IVR menus can be divided into two types depending on how user give commands to IVR application or how user responds to its menu options, DTMF(DualTone Multiple Frequency) or Telephone driven and ASR (Automatic Speech Recognition) driven. Both have advantage and disadvantages and are widely used. ( Click here for more about DTMF driven menu or ASR driven menu)

Apart from above two types of IVR menus, it can also be divided another two types depending on how menu options are generated.

1. Menu options can be recorded using a voice artist in studio and played back.
2. Menu options can be generated using TTS (Text to Speech) converters.

Again, choices in a menu, may be static or dynamic. When the choices in a menu are fixed for the IVR system, than the menu can be called as static menu while if the menu options changes dynamically depending on caller id, time of the day etc., than the menu can be called dynamic. For example:-

In a call center IVR, if a registered customer dials, he may be given different options while an unregistered customer would be presented a different options in the IVR menu.

Many people do not like TTS generated menus as one can make out the difference between human voice and TTS generated voice, specially in India, it has mainly to do with accent of the voice. TTS can be very useful in dynamic menu as well as presenting data retrieved from database where playing recorded voice may not be possible all the time.

Usability of an IVR depends mainly on the design of IVR menu. For more about usability one may check this : Usability of IVR systems.

An IVR user is interacts with IVR through it menu only. So it is very important to design IVR menu which is easily understandable to first time callers. Previously people used Visio like tools to design IVR menu. But now a days, almost all IVR development tools come with powerful, feature rich visual IVR menu designer giving DYI(Do It Yourself) feature for IVR customers.

What is speech recognition or automatic speech recognition ?
Automatic speech recognition can be defined as a process by which spoken words are converted to text. Many people may confuse with voice recognition as speech recognition. Voice recognition is recognising the speaker of the voice, while automatic speech recognition recognise the words spoken. While speech recognition is mainly used for menu selection, voice recognition is used for checking authorised user.

How automatic speech recognition can be used in voice portal ?
Voice portal is a large IVR application which provides many value added services to the voice portal user. Normally, voice portals are operated by telecom operators to provide information of their services, activating deactivating services, utility services like matrimonial, job search, listening to music and download, jokes etc. Since voice portals have large information to be provided to a caller, it needs to give out a long list of options. But the DTMF digits or touch tones on a mobile phone or telephone instrument is limited. So automatic speech recognition is used as an alternative to touch tone or DTMF input for selecting a menu option in the voice portal or IVR.

Advantages of Automatic Speech Recognition over DTMF in Voice Portal:
1. Caller can choose a menu option quickly without having to listen to boring long list of menus. IVR can become truly interactive with its caller using same human voice.
2. Using an IVR was always a problem as one he has to remove it from his ear to look at the keypad and press a key. This can be again quite irritating for a voice portal user. Implementation of ASR completely remove this problem.
3. Change of menu or introduction of new options a menu, or shuffling of options in a menu becomes easier as menu options are the words most commonly used by everybody for a particular option. Using a touchtone or DTMF menu, any option was assigned to a DTMF key or a number. With ASR, it is assigned to the word itself.
4. Not many people are aware of # and * keys as they are hardly used in normal operation while IVR seems to use them for some options for very long menus. ASR does not face this kind of problem.

So, one may find it very useful in a developer point of view to use ASR in voice portal as it gives more flexibility for designing menu and presentation of data. But as user point of view it may not that user friendly as touch tone. This mainly due to lack of 100% accuracy in recognising the word spoken by the caller. Wrong detection of words by ASR may result in very awkward menu options and information fetching. One way of tackling this problem is to confirm a user of his chosen option in the menu with a YES or NO for every menu option. But it would be too irritating for a user! A voice portal is normally a premium service where irritating caller is the biggest crime one can commit!

Problems of Speech recognition
1. Accuracy of recognition
Accuracy of recognition can be thought as converting words spoken by a user accurately to ts corresponding text.
As per information available ( by Googling and visiting ASR engine provider websites), almost all ASR engine has high accuracy for detecting two words, YES and NO. Apart from them, other words like numbers, date of births etc. has lower accuracy in recognising. For example, accuracy of recognition of numbers 1,2,3 etc vary from 87 to 91% depending on ASR engine. Accuracy of recognising other natural English language is fare much worse! As per report, recognising departments in company is maximum 85%!
Though accuracy can be improved by training of ASR, but it is not practical at all and does not serve a voice portal.

2. Different accent
Using ASR in a big country where people speak different languages or same language with different accents,speech recognition accuracy is bound to fare worse.

3. Confirming YES/NO again and again is irritating
People may design IVR very intelligently to confirm for any doubtful word recognition by YES or NO, but it is still irritating for many people and it slows down the time for fetching an information. In a voice portal where caller pays by minute of usage, it may not work in the interest of voice portal users.

Still, automatic speech recognition (ASR) is used widely in voice portal now a days and here are the few services in voice portal where ASR may work well :-

1. Contests
2. Classifieds
3. City wise weather information