Plum IVR Support

I am getting a lot of information out of these forums and was wondering if someone could help me out here. I am in charge of configuring IVR system for 2 distinct caller group and am dealing with a lot of complaints about the usability.

The first group are callers, mostly immigrants, which are not necessarily well versed in the English language calling from a noisy (car) environment.

The second group is comprised of mostly elderly or physically impaired users, which – to say the least – are not necessarily fond of technology.

The complaints I am getting are around the “robotic” voice (which we will address with human recorded voice prompts once they are signed off on), sensitivity (a background noise, cough, etc. taken as input and stopping the prompt, confusing both caller and system), timely input, etc.

I was wondering if the forum has any suggestions on how to optimize the settings of sensitivity, length of pauses, waits for input, and so on. Every time I get complaints the system is compared to “Well, how does United Airlines do it?” or “Why can’t it work like ___?” (insert UPS, FedEx, any big company) and while they do compare apples to oranges I am challenged to get as much as I can out of the Plumvoice system.

Thanks!

-hp-

Hi hp,

Some good IVR practices to follow when designing VoiceXML applications for callers who are in noisy environments:

1) Set specific local properties for when you are prompting the user for an input.

So, if you had a <field> where you are prompting the user to say their name, you may want to set specific values for properties that work with speech recognition such as: sensitivity, incompletetimeout, and confidencelevel

2) Set a low sensitivity value if you believe background noise (i.e. coughing) will be a factor in your application.

Setting a low sensitivity will help capture inputs when the caller is in a noisy environment. Typically, a value of 0.3 or 0.4 should suffice in this situation.
3) Increasing the incompletetimeout value within your <field>.

Setting a higher incompletetimeout value will give your caller more time to input a response before the speech recognizer recognizes the response. This particularly helps when the caller is saying a long string of digits and pauses in between saying digits.
4) Setting prompt bargein="false"

By setting prompt bargein="false" within your application, you can prevent the caller from accidentally barging in with an incorrect input by coughing or with a loud background noise.
Hope these tips help you out.

Regards,
Plum Support

Great response, thanks! I will give your suggestions a try.

-hp-

support wrote: 2) Set a low sensitivity value if you believe background noise (i.e. coughing) will be a factor in your application.

Setting a low sensitivity will help see phenq here capture inputs when the caller is in a noisy environment. Typically, a value of 0.3 or 0.4 should suffice in this situation.

4) Setting prompt bargein="false"

By setting prompt bargein="false" within your application, you can prevent the caller from accidentally barging in with an incorrect input by coughing or with a loud background noise.

Thanks for the tips. By setting a low sensitivity value and prompt bargein="false", my problem has been solved. Glad, I searched for the answers before creating a new post.