Voice recognition features provide help, but know pitfalls

iPhones featuring Suri’s built-in voice recognition have received much attention, but the Apple iPhone brand isn’t the only phone, tablet or device with voice activation features.

Speech recognition software has helped users for years. Now that technology has come to the iPad.

Whether sending an e-mail, filling out a web form, or writing a proposal for work, knowing how to use speech recognition on the iPad saves users time.

 

Dragon Naturally Speaking: Windows versus iPad

Many use Dragon Naturally Speaking on a Microsoft Windows-based machine. Others have downloaded the application (app) through Nuance for the iPad. The iPad operating system is different from the PC version. The Dragon app needs a wireless Internet connection, works only with e-mail and not with many programs.

The Dragon app needs a good WiFi or Internet connection to work. Translation is done remotely. A message is dictated, it’s sent to a remote server and then sent back to the hand-held device. The user’s words don’t remain his exclusive property. Why? Most handheld devices don’t have the processing capabilities and Nuance uses the data to improve and refine accuracy of its other speech-recognition software.

Users can only dictate about 20 to 30 seconds of material at once. Another downside is that it lacks an auto-save feature and work is lost if it isn’t saved to the clipboard when a call comes in.

Dragon Mobile Apps also provides the app for BlackBerry, iPad, iPhone or iPod Touch users with fast, accurate and easy-to-use, voice-enabled solutions for e-mailing, texting, surfing the mobile web and more.

 

Different Apps

Dragon Search is the way to search online content on an iPhone and iPod Touch using voice. The Dragon Search carousel allows users to access results from multiple sources.

Dragon Dictation is a voice-recognition application powered by Dragon NaturallySpeaking that allows users to speak and see text content for everything from e-mail messages to blog posts on an iPad, iPhone or iPod Touch.

Dragon Search is a fast, easy and smart way to search online content on an iPhone using voice. It is important to speak clearly for this feature to work reliably and accurately.

It is important to understand the difference between a voice-recognition app and a built-in voice control.

Voice-control has a limited vocabulary of commands which controls a few instructions by using the voice. The iPad can be set up with Jailbreak for voice control (Siri). Many good demonstrations of setup can be found on YouTube.

For (almost) hands-free calls in the car, iOS’s built-in Voice Control is the best bet. Press and hold the Home button (or the equivalent on the headset). After the beep, speak a command such as “call” or “dial” followed by the name or number. Or users can initiate a FaceTime connection by saying “Face-Time” and then a name and location.

There are many other voice input apps available through iTunes and Google Play.

By far the closest comparison to Siri is Vlingo, a free app which has its own voice-recognition engine, a powerful cloud-based back end, and almost all of Siri’s functionality, including booking restaurants.

But it can’t set reminders, although a new release might fix that. And unlike its Android brother there doesn’t seem to be a voice-activated hands-free, in-car mode. There’s also a Vlingo app for just about every platform, including BlackBerry and Nokia phones, and Windows, but not Mac.

Dragon Go is a free voice interface to a wide variety of web services, including Wolfram Alpha, Google, Yelp and Google Maps. It interfaces with Pandora, Spotify and Netflix. There’s also Dragon Diction, which is all about dictating messages or longer notes. You can then send your voice-recognized musing via e-mail, Twitter, Facebook or SMS.

Voice recognition isn’t a straightforward method of access for the iPad compared to options available on the Macintosh and PC operating systems. It takes technical know-how to set up and use many options for the iPad, especially for more complex use. Users may want to investigate simple solutions for voice to become the main access method or use another program geared toward users with disabilities.

Jennifer Mundl, MS, ATP is the lead assistive technology specialist at Courage Center

Leave a comment

Send a Comment

Your email address will not be published.