As voice recognition technology makes advances in ease of use and accuracy, Conversational Computing Corp. is pushing for the day when it can replace the mouse and keyboard for surfing the Internet.
To bring that day closer, Conversay, as the company is known, next month will introduce Conversay Voice Surfer, a plug-in to Microsoft Corp.s Internet Explorer that lets users navigate the Web with their voice from within the Web browser.
Voice Surfer, due in beta by the end of the month, is an upgrade to Conversay Web 3.2, a desktop application that sits on top of IE. A key enhancement is a tool bar that contains a voice meter, a horizontal strip that measures the volume and quality of ones voice by color. Voice Surfer features a status box with text that shows what state the application is in (for instance, “Im listening,” “Sleeping” and “Wake up”).
A status response box provides text from the users voice that includes such phrases as “Go back,” “Page down” and “Refresh the page.”
With Voice Surfer, users can verbalize almost any link on a Web page—such as check boxes, drop-down boxes, images, logos and radio buttons—because Conversay tags links with numbers that are voice-activated icons called Saycons, said officials of the Redmond, Wash., company. Users can also enter URL addresses and text by verbally spelling with a pop-up military alphabet list (that is, “Alpha,” “Bravo,” “Charlie,” “David” and so on).
A “Read me the links” feature uses Conversays proprietary text-to-speech technology so that users can listen to the links instead of reading them from the screen, officials said. Because any speaker can use Voice Surfer, no training is necessary to learn the product, they said.
Conversay Voice Surfer can be downloaded for free and will cost $29.95 for the full-featured version.
In May, Conversay will release an upgraded voice browser development tool kit that increases the functionality of voice recording from WAV files. Conversay plans to bring Voice Surfer to wireless devices later this year.
“With the advent of Web-enabled wireless devices, I think it would definitely be a godsend to be able to use your voice to navigate vs. having to utilize a stylus or keypad to find the information youre looking for,” said Roseann Sanji, regional alliance manager for Youcentric Inc., a maker of Web-based relationship management software in Charlotte, N.C. “[Voice Surfer] would be the ultimate tool to find information easily while on the road. … You would save time and get information faster.”
Other users of voice recognition products said they believe that Voice Surfer would be useful to those with disabilities or with little computer experience. However, they agree that voice will become more pervasive in the workplace.
“If [Voice Surfer] enabled me to mine information faster and easier, it would be a great benefit,” said Jim Alland, CEO of ArialPhone Corp., of Vernon Hills, Ill. ArialPhone makes a voice-based wireless earset communications device that enables users in small offices to surf the Web and control home automation devices. “Its part of the natural evolution of computing and the Internet to be able to improve the user interface to evolve into more natural ways to interact with the computer in a powerful way,” Alland said.
Gary Gunnerson, IT architect at newspaper giant Gannett Co. Inc. and an eWeek Corporate Partner, is excited by the possibilities that software such as Voice Surfer raise. Voice recognition is “a technology thats a little new, but youre going to see it become an everyday technology in your lifetime,” said Gunnerson in Arlington, Va. “Interacting by voice is a natural for human beings.”
In a related effort, Conversay, earlier this month, announced an upgrade to its Conversation Server, a platform that provides a voice interface to networked content through a telephone connection. Version 1.6 adds support for Short Message Service notification to a Personal Communications Service phone, support for speech recognition and text-to-speech in German, more developer control of speech recognition accuracy and text-to-speech playback, and advanced audio play controls, officials said.