Voice Recognition News

Testing voice-recognition software: A small business owner puts three packages to the test

Many business owners regularly talk to inanimate objects. Don't believe me? I'm guessing that in the last week alone you've begged your PC not to lose valuable data or implored your notebook to recover lost documents. While we all have one-sided conversations with our tech toys, we generally don't expect them to answer, much less complete tasks simply because we say so. But today's voice-activated software promises to do just that, claiming faster speeds and an impressive 99% accuracy level.

Several years ago I fell and permanently injured the nerves in my right hand, so too much keyboard time can literally cramp my style. Hoping to ease the strain, I recently tested the latest versions of three popular voice-recognition software packages: Dragon NaturallySpeaking Professional 9 ($899), IBM ViaVoice Pro USB Edition, version 10 ($189.99), and the speech-recognition software included in the Ultimate version of Microsoft's new Vista operating system ($399). I tried all three systems on notebooks and desktops running various versions of Windows XP's small-business edition. I used them for everything from dictating e-mail to composing formal marketing pitches. Each system started easily at the click of an icon. But before they would follow my orders, I had to teach them my speech patterns by reading several scripts that appeared onscreen.

]]>
While I was generally impressed with their ease of use, I had to be vigilant about the results. Programs would sometimes slow down or speed up, resulting in repetitions as well as missed words. Punctuation was tricky; you need to say "period" at the end of a sentence. And I'm still wondering about the accuracy of those accuracy claims, because each system on occasion offered inventive substitutions for my actual words. ("Melody" became "nullity," and "man" transmogrified to "math," "Matt," and more.) Full disclosure: I admit to deriving a certain childish pleasure from testing - okay, tormenting - my would-be assistants by singing or using off-color language. Confronted with my favorite four-letter expletive, all three applications responded with prim substitutions such as "Oh, flock."

Dragon NaturallySpeaking Professional 9 (nuance.com/naturallyspeaking), which ships with an Andrea noise-canceling headset, is the latest incarnation of the Nuance desktop speech-recognition software formerly known as ScanSoft. The new version features an appealing interface (who doesn't love dragon icons?) and includes a cheat sheet with the most common commands. Dragon allowed me to choose between two narrator voices (I nicknamed them Computer Lady and Earnest Guy), which provided clear instructions. I was told to speak slowly and carefully, like a TV anchor reading the nightly news.

IBM's ViaVoice application (nuance.com/viavoice) came with a simple setup disc, plus British and American English options. ViaVoice ships with the same headset as Dragon, along with a USB connector. Despite initial compatibility issues, I set up the software in less than an hour, and the cheat sheet helped with basic commands. But ViaVoice was slower to establish voice patterns than either of its competitors. It also featured the most irritating icon of all the applications that I tested. Woodrow, the talking pencil? I mean, really. After ten seconds of Woodrow's virtual company, I was tempted to snap the little flock.

Vista's speech-recognition software was the easiest application to set up, although it provided no tips or tricks. Vista picked up most of my slang and intentional mispronunciations. But it seemed to work better with an external headset microphone than with the internal one in my Vaio notebook. Worse, I have so far been unable to banish the software from my desktop (microsoft.com/enable/products/windowsvista/speech.aspx).

Bottom line: If forced to choose a favorite, I'd probably pick ViaVoice (Woodrow notwithstanding) for its excellent dummy-proofing. Still, I think any of the applications could be a gift to entrepreneurs with repetitive-stress disorders, arthritis, or impaired vision, as well as users who are strapped for time or who type more slowly than they speak.

Rachel C. Weingarten is president of GTK Marketing Group and author of Career and Corporate Cool (Wiley, July 2007).

AT A GLANCE

Dragon NaturallySpeaking Professional 9 - $899

UPSIDE: This software has been around the longest, so most of the kinks have been worked out.

DOWNSIDE: Offered a relatively limited set of commands.

IBM ViaVoice Pro USB Edition, version 10 - $189.99

UPSIDE: Awesome cheat sheet lists just about any command you can think of, and then some.

DOWNSIDE: Woodrow, the talking pencil - need I say more?

Voice-recognition feature in Microsoft Windows Vista (Ultimate Version) - $399

UPSIDE: Included in the operating system, so you don't have to shell out extra money for voice-activated software.

DOWNSIDE: Fewer add-ons, difficult to remove from the desktop.

Cisco: voice-recognition next on acquisition menu?

Cisco may be on the acquisition trail again this time hunting for voice recognition technology. The network giant has made 122 acquisitions since 1993.

Barry O'Sullivan, head of Cisco's Voice Technology Group, told Reuters the company wants to add more sophisticated voice-recognition technology to its products aimed at helping office workers communicate more flexibly. He was not sure if the network equipment maker would develop such technology internally or through partnerships or acquisitions. In the past however Cisco hasn't been one to wait too long to jump on a technology it considers hot.

And from the sounds of it, voice recognition is showing up a lot more on Cisco's radar: "We'd like to be able to do things like search for stored conference calls, and intelligent tagging of voice," O'Sullivan told Reuters. "There's a $30 billion market opportunity out there. We're all circling around it with different strengths and we all want a piece of the pie."

]]> Not to mention the fact that Opus Research said the market for server-based voice-recognition technology in call centers was valued at $600 million in 2006 and is expected to double by 2009.

In its recent 10-K filing Cisco says it is in the process of identifying additional advanced technologies for focus and investment in the future, and our investments in some presently identified advanced technologies may be curtailed or eliminated depending on market developments. "We have also continued to focus on developing a new wave of technologies, which we refer to as emerging technologies, including such products as digital media, TelePresence, and physical security, among others."

Cisco currently lists the following as its advanced technologies: application networking services, home networking, hosted small-business systems, security, storage area networking, unified communications, video systems and wireless technology.

Certainly Cisco is not alone in pushing for voice recognition technology. Microsoft is embedding voice in Office Communication Server collaboration software and IBM doing the same thing with its Lotus/Sametime collaboration software.

Windows Vista Speech Recognition Demo Gone Awry

Dutch bank ABN Amro offers banking by voice recognition

A large Dutch bank has begun offering its customers access to their accounts with a telephone system that operates entirely by voice recognition.

IBM talks up voice-based biometric user identification

IBM is developing software that could enable IT directors to deploy biometric user authenticated systems based on voice recognition technology.

Wii Rumour: Headsets. Voice Recognition

According to a strengthening rumour gaining momentum right now, the Nintendo Wii will feature wireless headsets for communication as standard across all online play, with a voice-to-text conversion enabling users to censor the content to which they are subjected to by other users.

Stemming from a well-established board in the more right-wing areas of the online gaming world, a user who nailed the Wii-Mote speaker news months before the E3 announcement claims Nintendo will make the voice-to-text technology an absolute standard in all elements of Wii online, reflective of it's security-conscious stance towards gaming and communication over the Internet.

Don't Ask, Don't Tell...Your Computer

After over 20 years in No Man's Land, it seems like speech recognition is finally finding its groove: telephone-based customer service.

It's certainly true that speech recognition has a devoted user base, especially among differently abled workers. The technology has long helped those who aren't able to see their computer screens well or at all, and so rely on speech recognition to read a Web site for them, or help input a word processing document. It has also proven useful for people with repetitive stress injuries and other people unable to use a keyboard and mouse.

A little byte to eat: Restaurants are logging in to technology

...several companies are vying for the upper hand in "point-of-sale hand-helds" - minicomputers for waiters - for this reason. With orders instantly transmitted to the kitchen, waiters manage more tables, while remaining on the floor and available to patrons. Furthermore, the tableside payment-processing feature calms fears of identity theft because credit cards are never out of sight.

And in the future, POS hand-helds will be even more efficient. Ameranth Wireless Inc. was recently awarded patents for its handwriting and voice-recognition devices. While both will decrease time spent navigating through screens, Keith McNally, CEO, believes voice recognition holds the most promise. "When you speak, you don't lose eye contact. It's a more natural experience."

MobileVoiceControl Launches Speech Recognition System for BlackBerry

MobileVoiceControl Inc., a developer of voice recognition systems for the mobile marketplace, today launched VoiceControl_bb, a high accuracy speech recognition system that combines out-of-the-box functionality, single keystroke operation, and a natural speech command set. Designed for specific BlackBerry devices from Research In Motion, this powerful system was developed to increase productivity and safety.

Voice recognition in Windows Vista

Check out this great video of the voice recognition system built into Windows Vista... not enough time to get a good idea of its accuracy and its not as fast as I'd hoped, but being able to use any computer running Windows Vista would be a great boon to die-hard voice recognition users.

The Silent Speaker

In space, no one can hear you scream. Use a cell phone on a crowded commuter train and everyone can.

Charles Jorgensen is working to solve both problems, using an uncanny technology called subvocal speech recognition. Jorgensen demonstrates it at his offices at NASA's Ames Research Laboratory in Mountain View, Calif. He attaches a set of electrodes to the skin of his throat and, without his opening his mouth or uttering a sound, his words are recognized and begin appearing on a computer screen. The Ames lab has already used subvocal commands to drive a car around a virtual city in a computer simulation and to Google the Web using nothing but unuttered search terms and commands.

Woman's disability is no distraction

The East Tennessee Technology Access Center modified Wilson's workspace to fit her needs. They replaced the computer mouse with a trackball and provided a headset for her dictation program. She uses voice recognition software for typing and laughs because it has a penchant for mistaking words for profanity.

Raging against the machines

That is just a taste of the secret shortcuts we could all use - maybe double during the holidays. Don't thank me. Thank Paul English. He's the Bostonian co-founder of Kayak.com, an Internet travel site. But he has recently become a minor celebrity because of his personal Web site, paulenglish.com. and its "IVR Cheat Sheet" - which lists dozens of ways to circumvent those automated voice recognition systems.

Down syndrome barriers falling: College opportunities expand for disabled

In the past, the educational road for students like Brown came to an abrupt halt after high school. But in recent years, young adults with developmental disabilities are finding a burst of opportunities--from Maine to Elmhurst--that once would have been unthinkable.

...Each program is different. Though the courses are demanding, they are taught differently. Less "chalk and talk," more hands-on experiences and technology, such as voice-activated computers.

"This isn't some watered-down curriculum," Johnson said. "We push our students somewhere between frustrating and challenging ... that's where true learning happens."

W3C looks to improve speech recognition technology for web transactions

W3C, the standards-setting body for the Internet (World Wide Web Consortium), has completed a draft for the important VoiceXML 3.0 - technology enabling voice identification verification. While normally associated with voice commands, it has the potential to greatly speed and improve the accuracy and positive proof of online transactions.