Voice User Interface Design VUI

Here in the VUIDesign blog, we’ve covered more than a few free cell phone services that provide great value (particularly considering the cost), are very easy to use, convenient and flat out helpful.

Therefore I was very happy to see Mr. Pogue cover three of my favorites on his Personal Tech blog (the video is particularly interesting, you should give it a look). Most of them take advantage of speech recognition, but they all make a good job of taking the complexity away from the users - which I wish every service out there would strive for.

Here’s a quick summary of what each one does, but nothing compares with calling the real thing and taking it for a ride:

1.  Google’s Free 411 (1800-GOOG-411) - Free 411 service that allows you to find and connect with local businesses. Some of the extra cool features offered include the capability of saying “text message” to get a text message with the business details (name, address, phone, etc.), “map it” or a map showing its location, or simply stay silent and getting connected to that business. Only thing I wished they had is foreign languages of the same service (currently English only)
2.   ChaCha (1800-2CHACHA) - Free mobile answers service where you can just dial their number, ask any question in “conversational English” (as if you were doing a web search), and after a minute or so you receive the answer in the form of a text message. Part of the secret sauce of course is the fact that searches are actually performed by “guides” which get paid about $0.20 for each answer they provide.
3. Jott (1866-JOTT-123) - Free voice to text service that basically allows you to convert your voice into all sorts of textual representations such as text messages, email, reminders, lists, etc. In particular, this service has become very popular amongst bloggers and twitters since it’s relatively easy to take this one step further and set it up in such a way that you can send the messages to web services that would publish them automatically to the web.

I would be interested in hearing your experience with these services as well as any others you might have found just as usable (and hopefully just as free)

I recently ran across a series of posts and a SpeechTEK magazine article about a new service currently in Private Beta called Fonolo.

The premise is definitively very interesting. What this Canadian start-up is attempting to do is to replicate the concept of bookmarking and deep linking (process of linking pages in the lower levels of a Web site from a home page - or other pages - to help search engines index them) so common these days on the web. What this means for a phone user is that they don’t need to get to the application’s “home page” (aka Main Menu) every time to then have to traverse the phone tree to reach a specific destination…

According to their founder’s pitch, the way it works is that you “bookmark” a spot deep inside a telephone’s system tree. To do this, you go to the Fonolo’s website, find the Company you need, review a transcription of their menu structure, find the spot you need and click on it. By doing that, they call the company for you, navigate the menu up to that specific spot and call you back so you can continue your transaction from that point on.

How do they know what systems look like? Well, as noted in the VoIP weblog, they seem to be using a combination of voice recognition and human editors to generate “maps” of the interactive voice response system.

Aside from the obvious privacy concerns a service like this might raise, the hottest one in my opinion is the service they refer to as “Intelligent Call History”. Since in reality all your calls start from their home page, they are attempting to become something like a Google of sorts for “phone sites”. What I mean by that is that they would keep track of all the interactions you’ve had with a certain company (regardless of the phone you used), along with the actual recordings of those conversations!

In the web world, we’re all familiar with how certain companies keep logs that track your web habits which could then be linked to your IP address. The biggest difference to me is that they mostly keep track of where you’ve been and where you’re going, but not of what’s happening when you are there… and in this case, since you’re using them as a bridge to connect to a Company, how can you be sure those recordings (which may contain account numbers, PINs, etc.) are kept safe and out of anybody’s reach?

Presumably the advantage of something like this is that in case of a dispute, you could play back a recording from the actual conversation and prove a certain transaction happened. But is this benefit really worth the risk? Particularly when it is known that once it becomes available to the public, it will be ad-supported.

On the other hand, they have also expressed that their ultimate goal is to craft partnerships with those companies Fonolo has mapped so that those companies can notify them “when they change or update their IVR” to the point where they hope companies will indeed send transcripts of their IVRs so they don’t have to be mapped anymore

Again, I definitively like the idea of empowering users and allowing them to accomplish their task in the most efficient way, but I think a system like this would be a much better fit for an actual device feature (similar to the GOOG411 dedicated button now present in some phones) - which you could turn on at the beginning of a call and stop once you reach the spot you want to “bookmark” so that in the future your phone would simply repeat the steps you followed and get you to that same spot. And of course, rather than finding more ways to patch user-unfriendly architectures, companies should be looking at fixing the root problem, which in the short term can be somewhat addressed via the deployment of more SayAnything/ SpeakFreely-type menus so callers can say what it is they need right at the beginning of an application…

I recently got a link from Amy Quinn pointing out an article entitled “101 Five-Minute Fixes to Incrementally Improve Your Web Site” provided by InsideCRM, and though it might be helpful to go over some of those points in the list and hence suggest “21 Quick Fixes” (granted they might take a little more than 5 minutes) that can be adapted and applied to Voice User Interfaces and Voice Applications:

Copywriting

1. Tell callers why they should perform a task. “People are trained to follow a request, as long as you give them a good reason to do it”. Therefore, put yourself in your caller’s shoes (or ears), and make sure you’re not only offering something of value to them, but that you’re clear in why they should go through it (e.g. shorter wait times, 24×7 availability, etc.)

2. Make the most highly trafficked menus easier to listen to. If your system contains menus that are too long and you can’t reduce the number of choices, think about grouping some of them or break the menu up so it’s easier to process in short term memory.

3. Make choices meaningful. Be sure to change any vague or cutesy menu options to something more up-front, meaningful, that callers can understand (no jargon please)

4. Stay consistent. Check your prompts and terminology for consistency, or else the experience will seem unstable, unprofessional or patchy.

5. Stay simple. You just can’t beat that. Granted some processes are complex by nature, that doesn’t mean they need to be complicated. Strive for clarity!

6. Avoid making hollow promises. Including those callers are taken for granted nowadays, such as pressing 0 and expecting to talk to an agent.

7. Be concise. ‘Nuff said.

8. Go with what works. And if you don’t know what works, ask your users – that’s why Usability was invented for in the first place!

Usability

9. Make navigation consistent. Listen to your users, understand how they think and what steps they need to follow to complete a task, and then stick to that flow.

10. Never ask for more information than you need. Related to #1, this includes only requesting relevant information at appropriate times (why ask for the last 4 of the SSN when all you want is the hours of operation?). “When you get greedy for data, you’ll turn off some visitors”.

11. Add a search box. Or in the case of VUI design, think about adding a SpeakFreely/SayAnything-type of implementation where callers can say what it is they need right at the beginning of the call.

12. Use plenty of contrast. In our case, we’re looking for ’sound contrast’. You’ll need to make sure you coach the voice talent properly so as to not only get a good sounding application but also intonations that convey the right message and elicit the right responses.

13. Test it on real users. Oh, if we could just make this a law…

Accessibility

14. Modify color. In our case, we’re looking for ’sound color’. This might include having multiple personas and voice ‘sets’ to account for playback speed and other traits that are necessary to support multiple caller’s ages, audible ranges, etc.

15. Identify the language. Explore the use of alternative DNIS numbers for each language so as to avoid requiring language menus (“For Spanish, press 2…”) in which case don’t forget to make one of them the default.

16. Supplement navigational aids. Explore the use of professionally generated earcons that not only serve as branding elements but also have an impact on application usability (for example, a quick tone preceding the playback of a confirmation number).

17. Define shortcuts. Take advantage of any Usability and Tuning findings you discover that might involve real users employing certain keywords/phrases as shortcuts often enough to justify adding them as ‘hidden shortcuts’

Design

18. Place important information “above the fold”. In our case, either at the beginning of a certain task (e.g. providing account balance before attempting a transfer), or at the end of a sentence so as to facility short term memory recall, particularly if the information provided is new to the caller. (e.g. “Your due date is May 15th.”)

19. Reduce choices. If your system contains menus with too many choices, reduce the number of choices to the very minimum necessary for callers to accomplish their task and maybe add a “something else” choice for everything else.

20. Nix banners. Which in our case might also include unwanted advertisements and legal disclaimers (“This call may be recorded for quality purposes.”) whenever possible.

21. Stay consistent. Check to make sure the design and prompt recordings are not only consistent throughout the entire experience but also consistent with the system persona and user profiles.

How good is automation when it only works for part of the process? That’s what I often wondered while traveling since in many occasions I’ve found myself trying to use technology only to find out it didn’t save me from having to get in line at the airport. For example, sometimes you try to check-in online but get a message about having to stop by the counter to get your final seat assignment (aka someone overbooked the flight and will scramble at the gate to get you in). In other cases, you get an electronic version of the boarding pass yet have to go to a counter to check-in baggage.

Therefore you can imagine how happy I was when I read about Continental offering a real electronic check-in option, without the paper trail. Basically you get the equivalent of a boarding pass in the form of a two-dimensional encrypted bar code that gate agents and security personnel can simply scan.

Now, if they could just link that same code with an RFID tag attached to my luggage, I could also skip that lost luggage line…

I know for some people Google’s announcement about Android wasn’t as exciting as the expectation of hearing them announce an actual “Gphone” (as it was often called there was still a rumor Google was working on an actual device), yet it seem implementations and applications based on this open and free mobile platform are finally coming out (albeit only as prototypes) and demonstrating how such an approach can in fact result in easier ways for consumers to obtain access to a wide variety of applications.

The prototype included a Google browser, phone dialer, audio player, Google maps, camera, games, calendar, contacts manager, calculator and notes. Sweet!

Since it seems the idea itself and its implementation are definitively feasible, it seems now the only remaining questions have to do with all the other non-technical reasons that will have a definitive impact on other players in the wireless and mobile arena. As Gigaom cleverly pointed out, some of those include:

1. All users of carriers that aren’t part of the Open Handset Alliance
2. Device-makers which now have to worry about yet another OS
3. Application developers, which will now have to deal with a significant number of handset/carrier/OS combinations
4. Support departments at participating carriers dealing with non-supported application issues
5. Users having to adapt to yet another set of user interfaces and frameworks

And to this I would like to add a 6th one: “UI Designers having to deal with new interaction paradigms, higher customer expectations, while maintaining design simplicity.”

This is definitively a great opportunity for us UI designers to start thinking about new challenges we’ll be facing when these applications/frameworks become available to the masses, in particular when user habits and natural ways of interacting with them call for the use of speech recognition as either the primary way of interaction, or as a back-up/supportive mode for certain types of goals and contexts.

Forget about Persona! We all know personalization is the new black, and everyone strives to make devices, systems and interactions as individualized as possible so as to gain better and faster acceptance.

I’m glad to see these ideas are starting to expand to new areas. In this particular case, I recently learned about a company called YourPND which basically allows you to record your own navigation voice recordings using your own computer and a microphone. Getting the full prompt set done takes about 7 minutes, and after that, the system creates a file ready to be used by your navigation device along with the installation instructions.

And not only that, but they take this concept of recording your own instructions a step further and encourage users to get creative by either adding your own catchphrases, or by using them as a gift to others (imagine grandpa following little Jimmy’s directions to get to their house) in the form of a USB flash drive containing all the instructions.

It’s currently only available in Dutch with an English version coming out soon. Furthermore, it only works on TomTom’s navigation devices even though other systems are scheduled to be supported as well. But at any rate, this is a pretty good idea which definitively adds a personal touch to automation and gives us a clue about some of the things we can try to make automation a little more interesting, fun and “familiar”.

So, anyone looking forward to hear “I’m sorry, I still didn’t hear myself”?

As some of you might have seen in TV ads, Ford Motor Co. recently announced a partnership with Microsoft along with the availability of a new technology called SYNC that allows you to control your stereo and phone while driving simply using your voice.

What made this even more interesting to me was the fact that they are trying to reach the market by combining the ‘cool’ factor speech technology provides as well as by using some clever advertising partnerships to target specific demographics such as the engagement with Juanes to target Hispanics of Generation Y.

But advertising aside, one obvious challenge for UI designers has to be the design of these control and command interfaces since on one side we hear about the safety advantages of the use of voice vs. typing (see video below), but on the other we hear about all the research that has been done regarding cell phone use on the road which suggests “you’re better off drinking and driving than phoning and driving.” and showed that users are four times more likely to be involved in a crash.

With the advent of new mobile and multimodal solutions, it becomes apparent that good design and low cognitive load will play a critical role moving forward. So far no one has died from being misrecognized when asking for an account balance, but things might change if we eventually move towards something like hands-free driving (Caller: Stop. Car: Sorry, I didn’t get that.Caller: Stop!! Car: Sorry, I still didn’t get that. Crash!).

As I mentioned back in March, I loved the idea of having a single universal phone number that then makes all other registered phones ring (home, office, cell phone) making us accessible all the time thanks to GrandCentral.

Well, it seems the idea of consolidated phone numbers and voice mails that are accessible from the web was too good to pass on, and the rumors of Google thinking about acquiring them turned out to be true.

Wesley Chan’s Google blog entry announced the acquisition while highlighting the fact that the purchase made sense considering “the technology fits well into Google’s efforts to provide services that enhance the collaborative exchange of information between our users.”

Of course the interesting part is not only to think about where Google might take the service now (think availability, scalability and support), but how will the service integrate with other existing services such as Google Talk, Google Maps, Google 411 or even Gmail. Russell Shaw brings up a really good point that the integration will take at least a few months, and will require more than API and UI work, and I would also add that VUI work will be needed too.

Here’s more coverage from Techmeme.

I was recently asked the question about where did I see speech recognition moving towards in the near future. In my mind, the two directions I’m seeing have to do with who is using it and the reason they are using it.

On one hand, I see speech recognition becoming a critical player on the multi-modal market. This is the market dominated by tech-savvy, young customers, who are used to be always online, anywhere, using various devices, not only cell phones. Therefore, they are bringing to the phone a similar set of expectations from what they experience online. This can be observed in the amount of activity taking place from a Web 2.0 and social media perspective, where users are being given the choice of their preferred input method, whatever it might be - text, audio, video, etc. - while being offered innovative applications of the technology as well as well-crafted “Mashup”applications and services.

And on the other, I see speech recognition evolving from a server architecture towards a networked model where the cell phone simply becomes the equivalent of a ‘web browser’ that gives them access to a whole suite of services that exist on the network cloud. This can be observed in the amount of consolidation activity taking place in our industry (Nuance and Bevocal, Microsoft and Tellme), in the integration of speech recognition as part of the platform itself or the Operating System (as seen in the recent Nuance competition and Microsoft’s Vista), as well as in the new offerings from startups such as Mobeus who will soon offer speech to text capabilities for cell phones.

As explained in this video, Mobeus follows the network-based model in the sense that the cell phone contains a small ‘client’ that performs the voice capture (end-pointing, compression, etc.), which then processes the utterance on a network of powerful servers and then returns the results back to the client. This is a similar play to what AT&T has been offering its wireless subscribers as the #121 service (aka “Voice Info”) which is basically a shortcut into Tellme’s services.

What do you think? Are you seeing other trends in our industry? Which of these models do you think will ultimately survive?

That’s right. We all know how it all started… Customers were stuck in IVR hell and then a savior came along and provided lists of company’s phone numbers and tips on how to circumvent self-service systems and reach an operator as soon as possible. Now, the natural evolution brings up man’s best friend - Bringo!

Being praised as a genuinely useful service, the way it works is pretty simple: You find the company you’d like to call (by name or category), you enter your own phone number, the system then “navigates the phone tree” for you and calls you back when it reaches a human.

As if justifying ROI and Usability wasn’t hard enough, does that mean systems will not only need to be “GetHuman certified” but also Bringo proof?

Wow.