I imagine there will be a day soon when I speak more to my computer and other devices than I do type or click. Speech recognition technology has come a long way in recent years with more applications unveiling for uses in the office and home.
It’s a common – and sometimes comical – use on devices like the iPhone and iPad with Siri. But the technology has spread to many devices and applications. While still not as robust as other offerings such as Dragon (a developer of speech recognition technology), Microsoft rolled out drastically improved built-in speech recognition technology in a recent version of Windows 8, allowing users to dictate text and control their computers.
Manufacturers like Ford also are incorporating the technology in their products as a feature. The new Ford SYNC technology allows you to talk on the phone, navigate and listen to music while keeping your hands on the wheel and eyes on the road. Temperature control is next.
The technology is providing professionals with more and more opportunities to perform common tasks hands-free – with the sound of their voice – and companies the opportunity to offer their customers more convenience and productivity. It’s all a part of the move to the human computer interface that I have talked about in previous blogs.
How It’s Used
Years ago, I began using the voice recognition technology in Microsoft Exchange to tell it I would be a little late to my next meeting. It then automatically adjusted my calendar and sent an email to the individuals impacted.
Today, here are some of the key uses:
- Make a call. (Call “Home” or Call “Jeff”).
- Compose, edit and send a text, email and even more formal word-processing letter. (Or in the case of today’s teens, write a paper or report for school).
- Dictate commands to open, close or perform a task on your computer.
- Search a device or the Internet for a piece of information, including weather, directions, traffic reports and more.
More Sophistication
We have had speech to text technology for quite some time. Its’ origin actually dates back to the 1980s with the release of the first commercial products. That’s when Dragon got its start. Research of the speech to text technology began in 1936 and until recently, accuracy and speed had been serious stumbling blocks.
The technology now essentially falls into two categories: speech to text and speech recognition. In both cases you use your voice to create text or direct the device. Speech recognition takes it a step farther by also understanding and somewhat interpreting what you say to complete a task. For example, if you ask Siri to make you dinner, she will provide you a list of nearby restaurants that deliver to your location.
The technology has become far more sophisticated, allowing users to train the solutions on their distinct voice patterns to prevent missing words or misunderstandings. It also covers a variety of languages. Windows’ Speech Recognition technology, for example, understands English, French, Spanish, German, Japanese, simplified Chinese and traditional Chinese.
Dragon remains a leader in the industry with versions available for home, premium, professional and legal. Dragon crosses multiple devices and promises 99 percent accuracy. Even the home version includes a comprehensive vocabulary sufficient for most users, including many professionals.
Speech recognition is becoming a product feature focus and most of the major players have solutions on the market. Siri, Apple’s speech recognition solution, is the most widely known. Android also has its own version and series of apps built on the speech to text or speech recognition technology.
The technology is ready and the applications are ripe for the picking so it will not be long before we see speech recognition integrated in everything from our ability to turn on lights and home appliances to change the channel on the television or temperature of the room. We’ll see the human computer interface take over in the next few years as the applications explode and seep into how we drive, live, work and play.
