IVR Development

This section of our technical library presents information and documentation relating to IVR Development and custom IVR software and products. Business phone systems and toll free answering systems (generally 800 numbers and their equivalent) are very popular for service and sales organizations, allowing customers and prospects to call your organization anywhere in the country. The PACER and WIZARD IVR System is just one of many DSC call center phone system features..

What Is IVR?. An Interactive Voice Response (IVR) processes inbound phone calls, plays recorded messages including information extracted from databases and the internet, and potentially routes calls to either inhouse service agents or transfers the caller to an outside extension.

Contact DSC today. to learn more about our IVR services and IVR application development software.

By Art Rosenberg and Paul Anderson


Are voice portals something new? Or are they merely a better way to implement IVR apps?

The dramatic changes being brought on by unified communications, wireless accessibility, and web information access/delivery are enabling new opportunities for customer support through automated self-service applications. While much has been written and debated about the impact of all of the above on the next-generation of multimedia contact centers, a lot of the emphasis has been about the staffing, training, and management of increasingly scarce CSR resources. These are important operational concerns for enterprise contact center management and are certainly a critical facet of CRM. But, from the customer's perspective, there are other interfaces besides the live contacts via telephone, email, and instant text messaging ("chat") that will be playing an increasingly prominent role in the "customer experience."

By now, the designs of customer-oriented web-sites have reached a high degree of strategic sophistication for web visitors and shoppers. There are long litanies of "dos" and "don'ts" about web page screen interfaces in order to make them easy to navigate and satisfying for the web visitor. The objectives are to maximize the availability of automated web-based interactions for visitor self-services. While the web site GUI has been the primary target for PC users, there is a lot of hype being generated about the potential for speech-based applications that will be supported by "voice portals." So, are these "voice portals" something new or are they merely a new and better way to implement traditional IVR applications?

Improved Speech Technologies

The combination of improved speech recognition and text-to-speech technologies, along with the growing consumer use wireless phones, is indeed opening up a new dimension for customer self-service that has not been particularly acceptable in the past. While we have had telephone-based IVR applications for decades, these relied upon the combination of touch-tone input, rather than speech recognition. Similarly, speech output was primarily pre-recorded information, because text-to-speech technology produced the "drunken Scandinavian" sound. Now, both technologies can better support the Telephone User Interfaces (TUIs) via speech input and output.

One direction for the improved speaker-independent speech recognition technology is for enterprise organizations to incorporate speech recognition input into traditional IVR applications as a replacement for touch-tone input. This offers particular benefits in simplifying the navigation of complex or long voice menus by allowing the caller to speak the desired input, rather than listen to a long selection of options. Name recognition would be an especially practical use of speech recognition technology, because, coupled with directory services, it can eliminate or minimize awkward, time-consuming, and error-prone keypad entry of addresses for voice messaging and telephone dialing.

The question, however, is how will such improvements in speech technologies be exploited differently in the multimedia environment of the Web and eCommerce?

"Where's the Beef?"

Most of the hype that we have seen regarding "voice portals" has been about basic sources of cost savings for the enterprise:

• 1. The familiar reduction of labor costs because of telephone-based (voice) self-service customer interactions, which has been around since the birth of IVR and CTI technologies;
  
  
• 2. The ease of implementation and maintenance of consolidated and consistent self-service information access, whether via a web site GUI or a voice telephone;
  
  
• 3. With better speech recognition, there are incremental benefits because the call flow can be simplified and the connect time for wading through menus reduced;
  
  
• 4. And finally, it is claimed, the implementation of voice-based applications with new programming tools like VoiceXML will enable callers to do more things application-wise on their own than the traditional IVR/CTI development tools allowed.

Speech at the Customer Touchpoints

We know that a major driver for a voice interface is when users are mobile and carrying a wireless phone. That's when they will not have the benefits of a PC screen and may need to be "eyes-free, hands-free," (e.g., driving a car). However, that doesn't mean that customers will want to listen to large doses of information that can be more efficiently scanned with a GUI. So, the notion that the same presentation layer used designed for desktop surfing can also be used, as is, for telephone users is clearly inappropriate. So-called "voice portals" will have to do what IVR applications have always done in the past, provide a telephone interface to selectively access databases for information retrieval and data entry transactions, except this time the data, the servers, and the means of access are all based on Internet standards.

While it will be indeed easier to "integrate" telephone access with open, standards-based IP servers, the implementation of voice applications through touch-tone or speech input is still a non-trivial user interface design task, and can't be simply copied from existing web page GUIs. Using evolving standards such as VoiceXML will make the transition from Web server text to voice easier, but not the interface design. We still need good design tools for that purpose.

It Won't Be Just a "Voice" Portal: Multi-modal Telephones

The IVR model of the past lends itself well to traditional telephone application interfaces, wired and unwired, but it doesn't give us much help with the multi-modality of the next generation of telephones that are already appearing on the market. Now we will have a choice of small screens, miniature QWERTY keyboards, a PDA stylus, and voice input and output that can be strategically exploited together for on-line interactivity. So, it is no longer going to be a choice between all voice or all text interfaces for customer access to enterprise information, but several practical combinations that applications must support in the future.

The new wireless phones will enable users to dynamically choose the modality that is most suitable for the circumstances. So, for example, in a noisy environment or where silent communication is required, the screen/keyboard combination will be selected. While driving a car, the speech recognition/text-to-speech interface will be used. So, it won't even be a matter of choice of device, but rather the user's choice of modality based upon wireless circumstances.

So what industry marketers are promoting as voice portals is really all about IP-based customer self-service a la IVR applications. We know that will probably be servicing POTS phone callers forever, so moving to IP-based servers is a practical move. However, with the coming explosion of wireless multi-modal phones, we probably should look for even more convergence between voice and screen interfaces.

What do you think will be the impact of new wireless screen-phones on enterprise self-service applications?