Speech recognition technology has advanced to the point that it has almost become ubiquitous .We have become accustomed to having it in our GPS systems as well as our cell phones, and because it has become so commonplace, everyone literally and figuratively “gets” it. Or maybe not.
The truth is that automatic speech recognition (ARS) has not yet completely evolved and it’s questionable how many people actually understand the technology behind it. In his Mashable blog today, Ben Parr dove headfirst into the subject of speech recognition and these issues, and even asserted in his headline that it is “changing our world.”
To help readers get a better grasp on ARS technology as well as its development, Parr directed readers’ attention to an infographic created by Medicaltranscription.net that credits 14 outside sources as contributing to the compilation of the information.
The infographic begins by explaining some of the challenges ARS faces. This includes the fact that it cannot distinguish between voices which means background noise creates a problem. It cites a 2006 Microsoft (News - Alert) Vista demonstration that bombed because the technology misinterpreted the presenter.
It also says computers depend on a database of words for speech recognition, but “cannot yet reliably determine the meaning of words,” and therefore they rely on “statistical probability to determine the word based on digital context.” That means they often botch words that are homonyms, for example, heir and air.
Despite these downfalls, the infographic draws a timeline from 1993 when speech recognition technology was only accurate 10 percent of the time until the period between 1999 and 2001 when speech recognition technology’s accuracy rate soared to 81 percent. Nevertheless, the infographic states that there has been no further advancement in accuracy since 2001.
That stagnation will most likely change. The infographic points out that Google’s (News - Alert) automatic speech recognition systems have great odds of improving speech recognition accuracy because Google stores all of the search terms people speak and type which increases the database from which the speech recognition software can draw and “determine probability based on commonality of searches.”
The take-away on all of this is that in spite of some challenges, automatic speech recognition has permeated our everyday lives—think smartphones, GPS, answering systems and digital dictation, as well as government—military aircraft control—and business—medical translations. But has speech recognition technology actually changed the way people work and live their lives? That’s the question Parr posed to his readers. A pretty safe guess would be that most will answer yes.
Want to learn more about the latest in communications and technology? Then be sure to attend ITEXPO West 2011, taking place Sept. 13-15, 2011, in Austin, Texas. ITEXPO (News - Alert) offers an educational program to help corporate decision makers select the right IP-based voice, video, fax and unified communications solutions to improve their operations. It's also where service providers learn how to profitably roll out the services their subscribers are clamoring for – and where resellers can learn about new growth opportunities. To register, click here.
Linda Dobel is a TMCnet Contributor. She has been an editor in the contact center space for more than 25 years, and has the distinction of being the founding editor of Customer Inter@ction Solutions (CIS) magazine. To read more of her articles, please visit her columnist page.
Edited by Juliana Kenny