VoiceXML and Speech Recognition
VoiceXML and Speech Recognition
By: Don Read
Mar. 15, 2001 04:59 PM
With all the hype surrounding the wireless Internet and its promises of anytime, anywhere information availability, the introduction of a new computing technology may make companies skeptical to yet another new Internet medium. However, extending corporate IT systems to a VoiceXML device will help to reshape the way you do business...again.
So far, the customer has been pushing the wave in IVR systems (interactive voice response), telephone information services, and DTMF (dial tone multifunction). However, it may be to your advantage to examine a new technology: VoiceXML and how it could impact your way of doing business. Is this the future? This article will endeavor to examine the current and future state of VoiceXML.
What Can VoiceXML Offer?
VoiceXML infrastructure can empower your sales professionals with instant verbal access to customer resource management (CRM) from the field. VoiceXML can offer value-added services to your telephone service for your customers and partners. Access to voicemail from a phone is obvious, but voice-activated access to e-mail, messaging, portals, and ERP systems affords time-saving efficiency to anyone on your staff who is "on the road."
How Do You Make Your Calls Now?
Very frustrating...and nearly impossible if you are driving. Now if you could speak the letters and have the system on the other end recognize your voice input, it would be a lot easier. Recent improvements to speech recognition software and Voice- XML ensure that you now can.
Why not do it this way instead? Dial the network access number and start the procedure to submit your PIN. Simply say your personal code, the system will respond by reading back the numbers and letters you used and ask you to confirm, yes or no. If yes, the system will ask you to speak your PIN. If it's correct, the system will allow you to access your system and confirm. Using your voice, you can select from a list of options to access your system.
Using the current IVR application, customers would have five rounds of button pushing before beginning to do what they want. DTMF is tedious. No wonder that 60% of customers using these systems hang up before completing their call. Some tasks that would take less than a minute can be time-consuming as customers are subjected to several minutes of multiple choice options.
With a speech-enabled system, a customer could have duplicated the above procedure, after dialing into the network, by simply stating, "My PIN number is 123456." Instead of choosing from a menu, which may not list their needs, consumers just say what they want. It is much less awkward to use speech when calling on a cell phone, or even a cordless handset at home, since the keypad is in the same handset you need to hold to your ear to hear the prompts.
The simplicity of this application is obvious.
The next step will be the convergence of the Internet and computer powered telephony to enable the creation of voice portals and voice commerce based upon your existing Web site. The new interactive IVR is a proven technology. Large companies who require extensive voice interacting with their customers have adapted this technology. Speech Technology Magazine reports that companies such as Sears, Hewlett Packard, FedEx, and United Airlines have employed this technology.
New Voice Recognition Software Apps
VoiceXML Review, another industry publication, says that the speech recognition application development is greatly simplified using familiar Web structures including authoring programs and Web servers. The comparison goes like this: VoiceXML is used to create voice-enabled applications in which HTML is used to create Web pages. Your VoiceXML application will work a lot like a Web page; organized prerecorded responses are prepared to answer all questions. If your customer goes to your Web pages, types in an order, and purchases the product using a credit card, the system works the same except the customer speaks all the necessary inputs. Your VoiceXML application will order and authorize the purchase, and confirm it by reading it back to the customer. No live operator involved and the exchange is done in a friendly tone.
How It Works - An Overview
Four Approaches to Using VoiceXML
Obviously, the first advantage of deploying VoiceXML lies in the ease of operation for the caller. The use of an interactive speech interface is easier ergonomically than keypunching (DTMF) on your phone. For the mobile professional the use of a speech user interface with some of the applications already available is hands-free and thus solves a safety issue for employees on the road.
Speech Technology Magazine reports that the cost of a live operator-assisted call is $1.47 whereas the cost of an IVR call using VoiceXML is 9 cents. Moreover, no one is put "on hold" and the system operates 24x7.
In VoiceXML Review, Jeff Kunins states, "For VoiceXML, the benefits of standardization are particularly strong. Because it is a thin layer that sits on top of the entire existing Web technology stack, it inherits complete and immediate interoperability with all existing infrastructure, software, and other standards that have been built to make enterprise Web deployments practical and efficient."
The Future of VoiceXML
E-commerce is the biggest trend on the Internet today and voice portals are a potentially dynamic way to attract new customers and enhance your existing e-commerce applications. VoiceXML is poised to fundamentally change the way you interact with your customers.
Reader Feedback: Page 1 of 1
Latest Cloud Developer Stories
Subscribe to the World's Most Powerful Newsletters
Subscribe to Our Rss Feeds & Get Your SYS-CON News Live!
SYS-CON Featured Whitepapers
Most Read This Week