World Business

Demand for the technology is expected to rise dramatically over the next not many years, and IBM’s oral communication research group is focusing on forming partnerships to take it to market

by Steve Hamm

Watch original video:

There aren’t likewise many good-news stories to come exhausted of Iraq, but here’s one. The U.S. military is bridging the communications gap betwixt its soldiers and Iraqis by tapping some innovative speech recognition technology from IBM Research (IBM). Using a laptop computer or PDA, soldiers speak into a microphone and the software translates what they say in English into Arabic. Iraqi soldiers or civilians observe and perceive by the ear the words in Arabic, and their answers are immediately translated into English. About 10,000 of these systems are in appliance in the battle surface bounded by parallel circles.

But what’s a boon for the U.S. military highlights a conundrum for IBM Research, which provides the technology gratis. When the military selected speech recognition technology for a new healing records network, it chose an offering from market leader, Burlington (Mass.)-based Nuance Communications (NUAN). For all of IBM’s expertise and resources, the 3,000 or so scientists in its basic investigation facilities worldwide assurance a major challenge to swain their innovations from the lab into the marketplace.

David Nahamoo, the chief technology officer for IBM Research’s speech and translation division, is out to change that. On Aug. 18, Nahamoo announced a unaccustomed strategy at SpeechTEK 2008, a gathering of the leaders in the speech recognition industry in New York City. Rather than distressing to push its technology mainly from one side IBM’s production and services divisions, the speech research group is focusing on forming partnerships with other companies to take the technology to market. Partners include Vlingo, the company that provides speech services for Yahoo! oneSearch (YHOO); PhoneTag, which converts mobile voice mail to text; and Jajah, which offers real-time phone translation betwixt English and Mandarin. "We can find partners, spread the risk, and employ advantageously our ability to invoke these markets," says Nahamoo.

IBM has been performing research into speech recognition for four decades. Some of the technology has found its device into products sold by means of the company’s software and services business, notably in the auto industry. But the technology hasn’t had the gentle of impact that Nahamoo and his bosses believe is possible, in applications including autos, fickle phones, call centers, medical systems, and transcription services. The issue for IBM? That each of these applications on its own represents a relatively small market. That’s for what cause IBM needs partners who are experts in different niches. "This new strategy gives extremely talented people in IBM an outlet for their work," says William Meisel, president of technology consulting fast TMA Associates.

Overall, make necessary for speech recognition technology is expected to rise dramatically over the nearest few years as people use their mobile phones as all-purpose lifestyle devices (so barking "find pizza" into your phone would load directions to the nearest pizza sitting-room). In-car collation and navigation systems are increasingly controlled by choice expressed commands. This growth in acceptance is being fueled by means of unwavering improvements in speech recollection accuracy.

Speech recognition isn’t single in kind technology but several combined. You start building a voice recognition engine through recording words, phrases, and sentences, and putting them in a database. Then you create a library of the specific pronunciations of the different words to be recognized. Then you map the sounds in the recordings to the word pronunciations. Last, you build a large table of the greatest in quantity commonly occurring patterns of words people are credible to speak.