in the mid to late 90’s, telephony was advanced enough for the visitor to interact with the IVR through both voice and telephone keypads. At this time, the rumors fueled by industry experts on new voice response technology and promise for more complex applications were fiercely distributed. Yet watching the speech IVRs today, it is painfully clear that very little real progress has in fact occurred. models today are soon limited in scope, and often performed properly. We’ll talk more about that topic in a moment, but now I would like to highlight the important characteristics of the new technology.
There are basically three tiers popular speech IVR technology, provided by one well-known technology supplier. Tiers, consisting of a keyword, key phrase, and natural recognition are each designed with a certain degree of sophistication to accommodate as many business settings as possible.
The least sophisticated tier keyword recognition, works by having IVR guide or direct the caller requests. For example, IVR might say something like “tell or press 1”. If the caller said something that did not fit the script for the IVR, the caller may be sent to the beginning of the menu – or even disconnected from the call in its entirety.
The next step up from that key phrase recognition, works in a similar way as the search engines. Basically, the IVR provides answers based on a predetermined set of conditions provided by the caller. The caller might say something like “please give me the number to the bank branch near Disney”, and IVR would provide information on the key phrases “bank” and “Disney”. Obviously, because the caller does not know what key phrases are pre, communication is prone to breakdown.
Finally, the most sophisticated technology is significantly different from the two previous examples given. With natural recognition, IVR is designed (hypothetically) to fully understand the real rings or natural language. In this case, the caller can say something like: “I have already tried fixing my computer by rebooting, turn off the power, touch, now what do I do?”. In order for this type of technology to work successfully, three different things must first happen
- The IVR must be programmed with an extensive list of vocabulary and in addition will also calculate how often these words appear items.
- The IVR needs to be able to understand complete sentences, and grammar must also be programmed.
- The IVR need to be able to reduce the actual intent of the caller, and not just rely on keywords or phrases.
It should be fairly clear to the reader that normal recognition is selected how speech technology. However, now these IVRs are limited to basic call routing applications. The reason more complex applications are not used because of the cost required for IVRs capable of extracting intent is astronomical! Rather than choose the lesser of three evils, it is yet another IVR technology on the market – IVRs powered by artificial intelligence (AI).
Newer IVRs are actually still stuck in the 90s and do not deliver on the promises made at the beginning of them. Modern IVRs to embrace technology from the current era have carried out promises of a better IVR, and to do what their predecessors only dreamed of.