Can You Hear Me?

Your introduction to the concept of speech recognition (SR) technology will likely vary depending on your age. You may recall pop culture portrayals of machines responding to the human voice including Hal 9000 in 2001: A Space Odyssey, the Star Wars robot C-3PO or even the talking Trans Am named KITT from the TV series Knight Rider. While primitive working versions of this technology have been around since the 1950s in laboratory settings, recent advances have enabled its practical application in a growing array of consumer uses.

Beyond a mere convenience, the motivations for further perfection of SR are several. It is becoming increasingly clear that the weak link in our growing relationship with technology is right at our fingertips: the keyboard. While the invention of the mouse greatly improved our efficiency in interacting with computers, it was far from a perfect solution. Recent developments in touch screen technology are also a valiant attempt to bypass more of the inherent limitations of keyboards. As our technology has become more personal and portable, we have a genuine need to keep our heads up and our hands free from typing on tiny keyboards. It is interesting to note that Google Glass also makes significant use of SR for exactly these exact same reasons.

Many of us interact daily with SR in one form or another. Personally, I use Siri on my iPhone to schedule events, remind me of tasks and look up information on the internet. I also frequently use speech to text software in composing text and email messages on my smart phone. More and more cars and OnStar are making use of SR to enhance drivers’ experiences. One of the more annoying widespread uses of SR is the auto-attendant that has replaced actual people on many corporate telephone systems.

The arrival of Siri in 2011 marked a huge advance in SR use, adding both significant interpretive skills and a virtual personality to the technology. Since then, more apps are developing uses for the endless possibilities represented by SR technology.

Until we are somehow hardwired to our technology and communicate through brainwaves, speech recognition will likely continue its current trend of increased use and function in previously unimagined ways.