≡ Menu

Top 3 reasons not to use ASR in IVR Systems in India

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!

Next post:

Previous post:

{ 13 comments… add one }
  • Ankit November 10, 2010, 12:11 pm

    I very much agree with you. I have been working with various renowned speech engines. They work excellent for lab conditions but fails tremendously on field. One of the best open end recognition engine I have experienced is with Google(Google mobile voice search). But that also had very poor score when tried with real people due to varied accent.

    But I have a strong faith that ASR for Indian scenario is just 3-5 years away from now.

  • Nicole November 10, 2010, 8:53 pm

    Very good points Uttam, using ASR (automatic speech recognition) is not appropriate for every IVR application. There is also the option of having a hybrid IVR, that allows users to use ASR and switch over from ASR to DTMF mode if necessary.

  • KO November 10, 2010, 8:57 pm

    First consideration is whether ASR is the right technology for the task given the circumstances. Another thing is that speech recognition is also quite expensive even though the price is coming down. So with this extra expense, you really have to think about whether speech rec would provide that much added value over DTMF.

  • Uttam Pegu November 11, 2010, 2:25 pm

    @Ankit,
    Thank you Ankit. I have similar experience with few ASR engines!

    @Nicole, thank you for the feedback.

    @KO, I agree on the part that ASR may not be right consideration specially where data accuracy is very important like phone banking, etc.

  • Naag December 22, 2010, 2:15 pm

    Well said Mr.Uttam Pegu,

    These three reason are the best for “not to use ASR in INDIA”. But things may change. ASR engines would be developed, even for indian conditions too.

    Let’s hope for the best.

  • Amelia Maddox December 24, 2010, 12:32 pm

    First consideration is whether ASR is the right technology for the task given the circumstances. Another thing is that speech recognition is also quite expensive even though the price is coming down. So with this extra expense, you really have to think about whether speech rec would provide that much added value over DTMF.

  • GSK Chaitanya February 2, 2011, 4:51 pm

    With the current ASR engines, I agree that it is highly inappropriate to use VOICE over KEYS, but the basic concept of research is to break the conventionality and aim the unimaginable.
    Coming to the problem on noise, with proper tuning of the ASR systems, this can be handled. Also, the mobile signal can be improved in the coming years. The successful ASR systems of English etc also faces the problem with accents, but with the proper research going on, we can expect a good ASR system in the coming 3-4 years.

  • Tim April 4, 2011, 3:14 pm

    Interesting post Uttam. As you know things are changing fast. Today many call centers are using third-party solutions to improve the accuracy of their ASR engines – even existing ASR engines. Take a look, for example at the PBXMate from SoliCall. These new third-party solutions have evolved thanks to the standardization that exists in the telecommunication market.

  • madhav December 10, 2012, 11:28 am

    i am thinkin you suggest ng to lunch IVR system Nepal. it’s a new for nepal. can you suggest me whether this business suitable for Nepal or not.

    madhav

Cancel reply

Leave a Comment