Voice and speech recognition technologies have come a long way since their first baby steps back in the 1950’s, when the earliest (and very primitive) systems were developed. Back then, only digits and a handful of English words were recognized, and our grandfathers could only dream with a future of controlling our houses, appliances and even vehicles with a mere utterance. Today, after some decades of awkward, sloppy voice recognition slowly creeping into our personal computers, that dream is coming true.
Speech recognition has finally advanced to the point of causing more satisfaction than frustration, and events such as the appearance of Siri -Apple’s voice-controlled intelligent personal assistant for the iPhone 4S- are foreshadowing a possible future of button-free technology. Voice recognition -strictly speaking, recognition of who is speaking rather than what is being said- has given place to augmented reliability in biometric security methods.
The field of medicine has also been affected, with the appearance of highly specialized software such as Dragon Medical Practice Edition, designed to understand the abstruse medical lingo that physicians speak into their Electronic Medical Record system.
With regards to smart phones and tablets we’ll have to keep our eyes open, since it is in these devices that speech recognition will bloom significantly on the following years, opening a myriad of new possibilities for their users.