Voice User Interface Design VUI

I recently read the story about how Netflix is using its call center agents as a strategic weapon and differentiator against their competition - particularly Blockbuster.

Could this finally indicate a tipping point in the way corporations view their “Cost Centers” “Call Center”? Not only are they eliminating the use of email to manage customer service inquiries but they are also implementing things no one would even consider in a customer service environment - live 24 hour service, prominently displaying their toll-free number on their Web site, removing requirements on call durations and empowering agent to make decisions that could make customers happy.

In my opinion, the next move in their strategy should be the use of automation but not as a replacement of that live interaction (which is what the email strategy was all about) but rather as a filter to handle the simple calls they seem to receive (for example, rearranging titles in the queue) so that more complicated and valuable calls (such as those dealing with possible cancellations) can be handled personally by agents.

Furthermore, their decision to set up the call center in the United States instead of outsourcing it to other countries seems to follow a recent trend in which callers are so disappointed by the service provided by non-native English speakers, that they’ve reported they would prefer automation than outsourced live agents.

Finally, one more interesting point in the article is how they decided to set up the call center in Portland instead of other cities where the costs would’ve been lower… simply because of the standard “politeness and empathy” that Oregonians show on their daily interaction with each other. Anyone know about any commercial “personas” from that area?

First of all, I would like to apologize for my absence this past month. To be honest with you, I’ve been going through some life-changing experiences (including a new baby and a career move) which have taken priority over my posts.

Nevertheless, I’m happy to say that I’m back and very excited about the future!

As part of that, if you’re planning to attend SpeechTEK East this year (taking place in New York, August 20-23), I would like to invite you to my presentation:

Track: B101 – Whose VUI Is It Anyway? User versus Business Requirements
Location: New York Marriott Marquis, Empire Room (7th floor)
Date and Time: Monday, August 20th, 10:15 am – 11:15 am
Title: “Customers Request the Darndest Things: 10 Challenges for VUI Designers”

Hope to see you there!

And stay tuned for a post of my presentation in case you cannot make it, or if you want to share it with others afterwards (yes, I think it’s that good)

I was reading an article this morning about things we can learn from Social Design. In particular, what I liked was the fact that they weren’t trying to analyze the typical examples - Facebook, YouTube, SecondLife, etc. - but rather learn from the mistakes of other less-known ventures.

In particular, there were four “Lessons Learned” that Joshua points out that I think apply to Voice User Interface design and any type of self-service application:

1. Not attracting enough users (aka. not retaining enough users or having them choose other service alternatives such as a live agent)

If you design and develop a great self-service system and nobody uses it (or opts out), you have this problem. What’s even worse, some companies think that they way to solve it is to make it hard for callers to talk to an operator, add more options, or spend more money marketing the system, which is the wrong move. Good applications (like social sites) build value one user at a time. As Joshua points out, “If one user finds value, then they’re much more likely to tell others or invite their friends.” Therefore, one-size fits all systems aren’t the answer. Instead designers (and businesses) should focus on succeeding on a smaller level, focusing on individual users and their needs. One very interesting point I loved was “One strategy in particular is to design for your friends, get the system working well for them, and then release it to a broader audience”. What would happen if we started to design our apps for our friends and families instead?

2. Trying to do many things at once

Too many times I’ve heard the casual customer request: “The system should provide the same functionality the old system had, plus the new features the website offers, along with some new initiatives we’ve been thinking about.” (I can already feel the goose bumps). Since any new design (or redesign) is considered an opportunity to ‘upgrade’, it is hard for businesses to understand that ‘enhancing’ it not necessarily a function of adding things but maybe removing things. Unless you focus on those things that customers really care about and need to be successful, callers will continue to hate the systems we design - no matter how ‘useful’ we consider them to be.

3. Lack of Sustained Execution

Most systems tend to be developed, rolled out, and then become static pieces of art - aside from the casual updates (e.g. changes in the hours of operation) or sporadic tunings (which tend to happen once a year). On the other hand, what makes Social Web applications so successful is the fact that they are in a continuous state of evolution, they keep changing and never stop getting better. As Joshua points out, “It’s too easy to fall into the desktop software mindset of build, release, and wait for the next cycle.”, but I truly agree with his comment about this being a mindset issue - “If you see it as an opportunity for continual improvement, your outlook will be more positive.”

4. Pointing the Finger when Missteps Happen

It may not be that apparent considering the current state of the speech industry, but reactions such as the SNL sketches, the Citi Simplicity campaign (”press 0″) and the GetHuman movements, provide hints that the consumers are starting to become much more vocal regarding their experiences and expectations regarding self-service ad automation in general. Therefore, we as “manager of these communities” must act accordingly, accept responsibility for our caller base and earn their trust and respect.

Any others I might have missed?

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?

It seems in this new era of YouTube shows and video-generated content, it wouldn’t take long after the success of some of those SNL sketches for someone to come up with a full-fledged movie in our space - the Call Center Movie.

We all need a good laugh every now and then, plus it doesn’t hurt to remember that self-service solutions aren’t always worse than having a human being on the other end of the phone… Enjoy!

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.

Techcrunch along with other news services and blogs are continuously reporting and providing updates on Guy Kawasaki’s newest venture: Truemors.

The service basically allows you to report ‘rumors’ via email, text messaging, and yes… phone. They have a partnership with Spinvox which I wrote about back in February as a startup to watch because they provided “voice-to-screen” messaging, or in this case, “voice to rumor”.

Once again, it is becoming obvious to me that the future of Speech Technologies will not be as a stand-alone technology in the Call Center/Self-Service industry but rather as a complimentary technology to other Web 2.0-like technologies that give customers full control over when and how to interact with them.

Once these sorts of technology integrations reach mainstream adoption, the question will turn out to be if existing Speech Service vendors/providers will be able to offer, understand and deliver a compelling and seamless experience for our customers’ customers. In other words, are we ready for Speech 2.0?

NPR has a very interesting that explores how human behavior isn’t limited to real world interactions but actually extends to others types of interactions, including virtual worlds such as Second Life.

Which makes me wonder… if it’s in our nature to balance things such as personal distance and eye contact in both the real and virtual world, what other ‘rules’ are we bringing in into our day to day interactions with the phone?

I know similar topics have been discussed previously in articles and books such as Clifford Nass’ “The Media Equation” , but it was fascinating to me to realize that those same behaviors aren’t exclusive to people-to-computer interactions but that also affect virtual representations of ourselves.

This of course explains why callers sometimes have such gut reactions to some of the designs and interactions out there - reactions that are hardwired in their systems or have been socially learned. And why when we violate some of those interaction conventions and real-world rules, it makes it psychologically uncomfortable for our callers.

Let’s just keep that in mind (and let’s remind our customers) the next time we model systems around real-world interactions.

Apparently so… I’ve been using Tellme and its services for a long time. Some of them were extremely good - such as the Traffic Report application which then got phased out once the government implemented local 511 services such as the one in Arizona.

On the other hand, Web 2.0 seems to be surrounded by a series of keywords such as blogs, podcasts, social networks, etc., one of which I really felt would apply to Tellme. But then today I was reading a report from the Web 2.0 Expo talking about the Top 5 Web 2.0 services from the conference, and certainly enough, Tellme was at the top of the list thanks to its new downloadable application that allows you to get useful business and directory listing information on your mobile devices and phones.

In particular, I think the multi-modal functionality provided by the application is a clear indication of how companies can leverage some of these Web 2.0 technologies. In the case of Tellme, you can call in and find 411-like information using speech recognition, you can send a text message with your request, or you can download the application to your phone and get the results displayed on the phone screen.

Kudos for Tellme for *discovering* that users not only want features, but want control over the interactions as well as freedom of choice on how the want to interact with it. Any other applications like this out there?

It is very interesting to see how this new Web2.0 wave allows apparently disparate technologies to be merged together and implemented in radical new ways.

Robert Scoble recently covered how Nexidia is using phonetic search to index video and audio content which then can be searched. And not only that, but by having a textual representation of the content along with some indexing information (such as the position of a certain phrase within a video), they can seamlessly integrate Google AdWords into a viewer and present relevant ads based on the what’s currently being played or listened to.

You can either watch the video interviews provided by Scoble or play with the demo provided b Nexidia.

Now, if there are technologies that allow things such as this to happen, why hasn’t anybody explore its use in the field of self-service? Imagine this. You call into a company’s self service solution and can either be asked an open-ended questions (How may I help you?) or with a directed dialog interaction (Here’s what you can do…). In either instance, and without the need for Statistical Language Models (SLMs) or other advanced recognition techniques, you could be ‘listening’ in real time to what your callers are saying or requesting. Then, based on a pre-defined piece of text, keywords or concepts, you could in real-time drive the interaction by either using those phases as shortcuts, by offering intelligent menu choices based on what they say (not on what you’re offering), and being able to make your system a lot more dynamic by maybe integrating it with a live FAQ back-end or support system that based on things that are taking place in other contact points (fax, email, web, blogs, podcasts, video, etc.) can offer new content/solution over the phone.

Wouldn’t that be sweet?