Touchtone, also known as DTMF or dual tone multi-frequency, has been the standard of interactive voice response (IVR) for years. Traditional touchtone IVR has its limitations, however. On 
average, 80% to 85% of callers prefer live representatives. DTMF is capable of delivering average self-service rates of 15% to 20%. For complex customer interactions, DTMF isn’t even an option.
Changing patterns of phone usage, along with the exploding use of cell phones and other mobile devices are playing a role in keeping DTMF acceptance rates low. Listening to instructions on a cell phone while pressing buttons and maneuvering it back to your ear in time to listen to the next instruction gets old in a hurry, not to mention it’s darned dangerous! Fortunately, just as DTMF’s age is showing, speech recognition has really grown up.
Finally, Technology That Listens to You!
Speech recognition IVR has become increasingly effective. Accuracy rates have improved drastically and the processing power needed to support the servers has increased. Once impossible complex applications are now not only possible, your customers expect them. User acceptance is strong, automated voices are natural, more “human, making speech recognition the accepted standard of quality customer care.
Average self-service rates for speech recognition programs hover around 50% and above, quite impressive compared to DTMF’s standard of 15%.. The main reason for the difference is that speech recognition can be written in a much more conversational manner. In fact, most speech recognition applications, written today, use what is known as “directed dialogue”, or normal conversation with a specific goal. Questions are asked conversationally, predictable answers are programmed into the system and the IVR leads the caller through the process like a live agent would. Yet instead of having to force fit responses into one of the “Press 1″ boxes, a well-designed speech application anticipates all expected responses to a prompt and then gathers and presents the data the way the customer understands it.
For recurring interactions, phrasing can be randomized to make each interaction seem more personal. A unique” persona”, one specific to your company or center can even be created, or auditory added, helping make the voice on the phone “real” without adding time to the call. In fact, speech recognition can seem so real, many customers actually say “goodbye” before hanging up!
So, is speech recognition right for your application?
Four types of calls lend themselves well to speech recognition applications:
- Informational calls. These repeat inquiries include: store locator calls, flight times and delays, retail order status calls and bank customers checking balances.
- Transactional calls. No matter how complex your transactions are, they can be adapted for speech recognition. Think about booking flights or hotel rooms, renewing prepaid accounts, or paying a bill with a credit card. Since speech recognition can upsell and cross-sell for you, you may even want to test it for your direct campaigns, especially to handle volume spikes.
- Calls that don’t play well in a simple menu. Speech recognition makes a whole range of offerings and services possible that couldn’t be automated with DTMF. Imagine a caller who wants to know if a particular test or treatment is covered by their health plan. With a speech recognition program capable of understanding words and phrases and alpha-numeric information, no longer are your customers restricted to a 12-button interface.
- Calls with an alphanumeric input. Despite the widespread use of text messaging, for many people it’s just not easy to input letters using a phone pad. Examples include non-numeric passwords, college course designations, part numbers, reservation confirmation codes and many others. A simple speech recognition application quickly solves this problem and leaves you with happier, less frustrated callers.
What about designing your speech recognition application?
To provide a quality experience for your callers, your speech recognition application should be designed and built from the ground up. Simply using an existing DTMF application with the response mechanism converted from touch-tone to speech recognition will not provide the experience your customers want! Bad experiences make clients leave, not what we’re after. Begin by tuning into your representatives interacting with your customers. Because they deal with your callers every day, their input will not only be invaluable, it represents the cornerstone of your successful speech application. Your reps know what your customers want and need! Be sure to include them on the design of your speech recognition solution.
Armed with this information, you can then layout the flow of your speech recognition program. Before actually writing it, usability testing must be conducted to simulate the application’s interaction with your callers. From there, the application flow can be tested (enlisting the support of actual customers), to uncover any glitches and solve application challenges before moving forward into programming and development. Working with a seasoned partner specializing in IVR and other contact center specific solutions can make this process more seamless.
Once the application is developed, building a test plan is essential. Include testing all of the expected and unexpected responses, possible misinterpretations by the system, unrecognizable responses, background noise interference, etc. An experienced speech recognition development partner will work with you to build an appropriate plan to ensure the new application works well, not only in a controlled environment but with the ultimate test group, live customers. In addition ask co-workers to call into your IVR as if they were a customer. What did they like, dislike? Gather this feedback and tweak accordingly. Don’t set it and forget it, tweak your IVR regularly to ensure maximum effectiveness.
DTMF is cheaper!
It’s true that speech recognition is more expensive to deploy than DTMF, there’s no getting around that. In terms of both development costs and IT infrastructure, there are discernable differences. Yet it’ remember that speech recognition is a call-shifting technology. Calls that would otherwise be handled by your agents are shifted to automated technology. What makes the ROI of speech recognition so sweet is the reduction in the number of callers who insist on talking with an agent. A well-designed, thoughtful application will lead to a greater percentage of callers self-serving than a traditional DTMF application which generates substantial overall cost savings in the long run. In fact, the payback from a larger up-front investment can quite often be recovered in a matter of months!
Quite frankly, the projected savings generated by speech recognition may leave you speechless. You owe it to your customers and to your bottom line to look at deploying speech recognition. Enough said (sorry, couldn’t resist)!