Speech Technology Magazine

 

Can VUI and GUI Survive an Interface Marriage?

Even though voice user and graphical user interface designs differ greatly, some practitioners are committed to making their union work.
By Michele Masterson - Posted Nov 15, 2013
Page1 of 3 next »
Bookmark and Share

The popularity of multimodal applications can make for some strange bedfellows. Take voice user interface (VUI) and graphical user interface (GUI) designers. Once tasked with very separate missions, increased consumer demand for talk, touch, and type on mobile devices has encouraged a new pairing between them.

VUI and GUI apps are typically referred to as multimodal applications, explains Bill Scholz, president of the Applied Voice Input Output Society (AVIOS), and "the potential for their growth on mobile devices is, in a word, 'extensive.'

"Already sales of multimodal-capable mobile devices are eclipsing sales of desktop personal computers," Scholz said in an email. "Multimodal apps touch such a broad spectrum of application areas that marketers and sales professionals have a wealth of new tools at their disposal that can significantly facilitate their professional activities."

That said, can the marriage of two sometimes very contrary sides of interface design survive?

"The big problem is in finding the sweet spot where graphical and voice designers can actually solve problems together," says David Pelland, director of VUI at Genesys Telecommunications Laboratories. "The next step is to do a better integration of those two things, meaning finding a polar app, so to speak, [that combines] what graphical [designers] do really well and what voice [designers] do really well and solves user problems."

However, it's not as easy as it sounds. Several elements must be addressed to overcome these obstacles.

Does GUI Reign Supreme?

Some industry experts agree that speech interfaces are sometimes seen as today's technology outcast compared to visual interfaces. From a user interface perspective, although graphics used on mobile devices haven't been around as long as voice user interfaces have, some argue that speech has a way to go before it catches up.

While speech technology has been around for decades, "it really didn't take off in terms of consumers and the mass market" until just recently, says Daniel Ziv, vice president of voice of the customer analytics at Verint.

Despite improvements in speech technology in recent years, voice user interfaces still have some limitations. "VUIs are system-directed; the system leads by asking questions, and this is inherently slower than GUIs. Graphical user interfaces are faster because they're user-directed; the users decide what to do next," according to James Larson, vice president of Larson Technical Services and an AVIOS board member.

Additionally, in strictly VUI interactions, it is not advisable to have an IVR present more than a few options. "In the IVR channel, voice is not persistent. Users can't remember things," says Kathy Brown, director of speech services and analytics at [24]7. "It's very frustrating, and there's cognitive dropout."

Nonetheless, when coupled with graphical user interfaces, speech technologies can be a friend to the user experience. "The screen really opens up the opportunity for voice to expand the [multimodal] experience," Brown says. "It can be made a richer experience and make information persistent."

Brown explains that with multimodal interactions, when users come into the IVR via a smartphone and select a particular task, they can be immediately taken to a visual application that can display, for example, bank charges. If those charges were read out loud, it would generally be by way of text-to-speech, which is not always intelligible, and the user might have difficulty completing the task. But by getting users to complete the task visually, they can see what the charges are and not have to remember what they've heard.

"The problem in a standard IVR," she adds, "is that users can't always control the pace, but if there's a visual display, they can control the pace in which they want to read."

Page1 of 3 next »
Learn more about the companies mentioned in this article in the Speech Technology Buyer's Guide:
Learn more about the companies mentioned in this article in the Vertical Markets Guide: