IVR Deconstructed

Plum’s VoiceXML IVR provides freedom to create, deploy, and easily modify automated telephony applications.  By capitalizing on the standards based nature of VoiceXML, organizations are reaping a number of benefits.  Plum VoiceXML-based IVR solutions can easily integrate with practically any existing business application and database, including any ODBC-compliant databases, ensuring extensive integration capability.  VoiceXML IVR supports standard data access and communication protocols.  By leveraging the capabilities of existing legacy and web systems, organizations can treat IVR like any other enterprise application and deliver integrated solutions.  Like HTML, VoiceXML is an open standard based on XML, and hence development and maintenance of IVR applications with VoiceXML does not require specialized knowledge of proprietary and obscure telephony languages.  Plum systems permit for application modification in real-time.  Meaning, there is no need to shut down the Plum IVR system, and inconvenience callers, to make major or minor changes to applications.  VoiceXML-based IVR allows migration of applications between standards compliant platforms with minimal effort.  At the telephony layer, Plum maximizes flexibility by providing for telephony integration with all major PBX systems and telephony protocols.  Plum enables integration with telephony systems from Avaya, Nortel, NEC, Siemens, and Mitel.  Plum systems offer full telephony interconnection support, and support all major telephony protocols including POTS lines, ISDN digital, channelized T1, and VoIP.

The adoption and standardization of VoiceXML opened the door for revolutionary change in the IVR product category and provides significant benefits to both developers and enterprise buyers.  All IVR implementations require some degree of application customization, usually accomplished via a scripting language or RAD tool.  Voice XML was created and adopted by the primary standards making body (the W3C) to improve and standardize the scripting of IVR applications.  VoiceXML allows for a superset of functionality, incorporating the best features from proprietary IVR systems, while dramatically improving integration techniques and the ease of application modification.

The VoiceXML language has its roots as a research project at AT&T Bell Laboratories.  Based on the Worldwide Web Consortium’s (W3C’s) Extensible Markup Language (XML).  VoiceXML is a tag-based language, that is a very readable, and should be easy to understand for any programmer with good knowledge of HTML and common data scripting languages (such as PHP, ASP, JSP, etc.).  Thanks to active support from America’s leading technology companies, including AT&T, IBM, Lucent, Microsoft, Motorola, and Sun Microsystems, the VoiceXML language entered the public domain in 2000 and has since become the accepted lingua franca for voice applications.  Today, over 600 companies support VoiceXML and use it to develop applications.  It is estimated that over 50,000 developers are now expert in VoiceXML, and the number is still growing rapidly.

Open text transcription over the phone is still a pretty dodgy affair. Take Google Voice: the technology behind it has been applied, by Google, to many of its projects including its map product for mobile devices. And sometimes the results are spectacular; I can pick up my phone, fire up Google Maps, press a button, say the location I want found, and Google will, under ideal circumstances, find the restaurant/bar/retailer/point-of-interest in a few seconds and then send me directions. But just as often, it fails miserably by sending me directions to a site in Connecticut when I’m really just looking for a restaurant 3 blocks where I may have been standing in downtown Boston.

But the one space where this kind of near-but-not-quite real time open transcription is with text messaging. Not that I’d encourage anyone to pick up their phone while driving, but if you’re going to pick up your phone, you really shouldn’t be sending text messages. And, fortunately, many states happen to agree with that sentiment, having banned text messaging while driving. But what if you could send a text messaging by speaking the message that you want sent? Would you be willing to put up with 80% accuracy if you had the ability to send a text message while driving without a) taking your eyes off the road or b) getting fined in those municipalities where texting-while-driving is illegal?

We tried building an IVR application that does just this recently. The app answers the phone, asks you for the destination for your text message, then it asks you to record your message. Two to three minutes later, after it’s been sent via SOAP to be transcribed by an automated transcription service, your intended recipient gets a text message. This is all fine and well…but we still have a few things that would need to be solved:

1.    Since the transcription accuracy is around 80%, it’d be nice to actually see or hear what actually got sent. Unfortunately the transcription is still near real-time. So unless you want to linger on the phone for several minutes while the gears turned at some distant outsourced automated transcription service, there’s no way to do this short of having the IVR call you back or, worse yet, sending you a text message which you really really should not be reading while driving.

2.    Speaking of receiving a text message, usually a text is part of an ongoing conversation. So how would you get the reply message? By text? That would defeat the purpose of this application. By phone? That’s better, but there, again, is a limitation because…

3.    …our SMS provider is outbound only. So your recipient can’t get a message back to you anyway, because if they reply, they’ll end up sending a message back to a shared short code rather than to you.

We might be able to solve item 3 soon. And, if so, we’ll back to report on progress.

The last few decades have witnessed the confluence of telephony and computer technologies, leading to improved Interactive Voice Response (IVR) systems.  Essentially, IVR systems allow for the automation of telephone call processing.  IVR implementations are usually integrated with enterprise data, such that the callers can request real-time information and/or caller input can be stored and processed.  Implementations often enjoy tremendous ROI: the full loaded cost of employing live representatives can reach $4 per call, whereas the cost of automating via IVR is closer to $0.25 per call.  When purchasing an IVR system, there are several important considerations to take into account.  IVR systems are usually integrated with backend databases, telephone lines, and PBX systems.  Plum solutions integrate with practically any database, support all standard telephony protocols, integrate with most PBX systems, and support data exchange standards such as XML.  Plum architects its VoiceXML IVR products with maximum flexibility and modularity.  Callers expect automated phone systems to work without fail.  Many competitive IVR systems are not built to achieve this idea.  Plum enterprise class systems are built for 24×7x365 performance and a zero call failure rate.

Managing an IVR system can entail adding capacity, adding applications, modifying applications, and reviewing logs and reports.  These activities are straightforward with a Plum system; a browser-based control interface allows for convenient administration from any workstation.  Total cost of ownership includes both external and internal costs.  Plum attempts to minimize both of these costs by offering superior products and expert services at reasonable prices.  As with any enterprise solution, services and support are important factors for long-term satisfaction.  The Plum team provides a full range of high quality services, including application assistance, system support, software, upgrade, 24×7 monitoring, and real-time backup support for critical applications.

I was lucky enough to live in Europe for about 8 months, and while I was there, I came to love the BBC, Le Monde, and Der Spiegel.  In terms of news, all three outlets top anything we have stateside by leaps and bounds.  Additionally, I like to read the New York Times and listen to NPR, but it is often times hard to catch news on the go, especially when you aren’t in your car driving.  How can consumers get information from reputable news outlets instantaneously when they are out and about?  An interactive voice response system could go far in giving people accessibility to news on the go.  The system could be used in myriad ways.  First, users could subscribe to this system, configure their preferences based on the newscasts they want to listen to, and then call in on their phones to actually hear the news they chose to consume, from any phone, anywhere.  Instead of having to sit in front of a television or a computer, users could get international news from around the world via a simple phone call.  The system could also be programmed to make outbound IVR calls based on preconfigured alert preferences.  Instead of being a newsreader, with TTS engines reading the news, the IVR could synthesize with news agency, so that users could hear the actual news read by BBC or NPR reporters, as if they were watching or listening to it on their computers.  In this way, people could have access to international news 24/7, and get immediate updates on issues of pressing importance, keeping them always in the loop!