In its most generic sense a voice portal can be defined as “speech enabled access to Web based information”. In other words, a voice portal provides telephone users with a natural language interface to access and retrieve Web content. An Internet browser can provide Web access from a computer but not from a telephone. A voice portal is a way to do that.The voice portal market is exploding with enormous opportunities for service providers to grow business and revenues. Voice based internet access uses rapidly advancing speech recognition technology to give users any time, anywhere communication and access-the Human
Voice- over an office, wireless, or home phone. Here we would describe the various technology factors that are making voice portal the next big opportunity on the web, as well as the various approaches service providers and developers of voice portal solutions can follow to maximize this exciting new market opportunity.
For a voice portal to function, one of the most important technology we have to include is a good VUI (Voice User Interface).There has been a great deal of development in the field of interaction between human voice and the system. And there are many other fields they have started to get implemented. Like insurance has turned to interactive voice response (IVR) systems to provide telephonic customer self-service, reduce the load on call-center staff, and cut overall service costs. The promise is certainly there, but how well these systems perform-and, ultimately, whether customers leave the system satisfied or frustrated-depends in large part on the user interface. Many IVR applications use Touch-Tone interfaces-known as DTMF (dual-tone multi-frequency)-in which customers are limited to making selections from a menu. As transactions become more complex, the effectiveness of DTMF systems decreases. In fact, IVR and speech recognition consultancy Enterprise Integration Group (EIG) reports that customer utilization rates of available DTMF systems in financial services, where transactions are primarily numeric, are as high as 90 percent; in contrast, customers' use of insurers' DTMF systems is less than 40 percent. Enter some more acronyms. Automated speech recognition (ASR) is the engine that drives today's voice user interface (VUI) systems. These let customers break the 'menu barrier' and perform more complex transactions over the phone. "In many cases the increase in self-service when moving from DTMF to speech can be dramatic," said EIG president Rex Stringham.
The best VUI systems are "speaker independent"-they understand naturally spoken dialog regardless of the speaker. And that means not only local accents, but regional dialects, local phrases such as "pop" versus "soda," people who talk fast (you know who you are), and all the
various nuances of speech. Those nuances are good for human beings; they allow us to recognize each other by voice. For computers, however, they make the process much more difficult. That's why a handheld or pocket computer still needs a stylus, and why the 'voice dialing' offered by some cell-phone companies still seems high-tech.Voice recognition is tough. And sophisticated packages not only can recognize a wide variety of speakers, they also allow experienced users to interrupt menu prompts ("barge-in") and can capture compound
instructions such as "I'd like to transfer a thousand dollars from checking to savings" in one command rather than several.
These features are designed to not only overcome limitations of DTMF but to increase customer use and acceptance of IVR systems. The hope is that customers will eventually be comfortable telling a machine "I want to add a driver to my Camry's policy." Besides taking some of the load off customer service representatives, VUI vendors promise an attractive ROI to help get these systems into insurers' IT budgets. ASR systems can be enabled with voice authentication, eliminating the need for PINs and passwords. Call centers themselves will likely transform into units designed to support customers regardless of whether contact comes from a telephone, the Web, e-mail, or a wireless device. At the same time, the 'voice Web' is evolving, where browsers or Wireless Application Protocol (WAP)-enabled devices display information based on what the user vocally asks for. "We're definitely headed toward multi-modal applications," Ehrlich predicts. ASR vendors are working to make sure that VUI evolves to free staff from dealing with voice-related channels; it's better to have them supporting the various modes of service that are just now beginning to emerge.
Voice- over an office, wireless, or home phone. Here we would describe the various technology factors that are making voice portal the next big opportunity on the web, as well as the various approaches service providers and developers of voice portal solutions can follow to maximize this exciting new market opportunity.
For a voice portal to function, one of the most important technology we have to include is a good VUI (Voice User Interface).There has been a great deal of development in the field of interaction between human voice and the system. And there are many other fields they have started to get implemented. Like insurance has turned to interactive voice response (IVR) systems to provide telephonic customer self-service, reduce the load on call-center staff, and cut overall service costs. The promise is certainly there, but how well these systems perform-and, ultimately, whether customers leave the system satisfied or frustrated-depends in large part on the user interface. Many IVR applications use Touch-Tone interfaces-known as DTMF (dual-tone multi-frequency)-in which customers are limited to making selections from a menu. As transactions become more complex, the effectiveness of DTMF systems decreases. In fact, IVR and speech recognition consultancy Enterprise Integration Group (EIG) reports that customer utilization rates of available DTMF systems in financial services, where transactions are primarily numeric, are as high as 90 percent; in contrast, customers' use of insurers' DTMF systems is less than 40 percent. Enter some more acronyms. Automated speech recognition (ASR) is the engine that drives today's voice user interface (VUI) systems. These let customers break the 'menu barrier' and perform more complex transactions over the phone. "In many cases the increase in self-service when moving from DTMF to speech can be dramatic," said EIG president Rex Stringham.
The best VUI systems are "speaker independent"-they understand naturally spoken dialog regardless of the speaker. And that means not only local accents, but regional dialects, local phrases such as "pop" versus "soda," people who talk fast (you know who you are), and all the
various nuances of speech. Those nuances are good for human beings; they allow us to recognize each other by voice. For computers, however, they make the process much more difficult. That's why a handheld or pocket computer still needs a stylus, and why the 'voice dialing' offered by some cell-phone companies still seems high-tech.Voice recognition is tough. And sophisticated packages not only can recognize a wide variety of speakers, they also allow experienced users to interrupt menu prompts ("barge-in") and can capture compound
instructions such as "I'd like to transfer a thousand dollars from checking to savings" in one command rather than several.
These features are designed to not only overcome limitations of DTMF but to increase customer use and acceptance of IVR systems. The hope is that customers will eventually be comfortable telling a machine "I want to add a driver to my Camry's policy." Besides taking some of the load off customer service representatives, VUI vendors promise an attractive ROI to help get these systems into insurers' IT budgets. ASR systems can be enabled with voice authentication, eliminating the need for PINs and passwords. Call centers themselves will likely transform into units designed to support customers regardless of whether contact comes from a telephone, the Web, e-mail, or a wireless device. At the same time, the 'voice Web' is evolving, where browsers or Wireless Application Protocol (WAP)-enabled devices display information based on what the user vocally asks for. "We're definitely headed toward multi-modal applications," Ehrlich predicts. ASR vendors are working to make sure that VUI evolves to free staff from dealing with voice-related channels; it's better to have them supporting the various modes of service that are just now beginning to emerge.
No comments:
Post a Comment