Big Brother is Listening To You?

A new patent has been awarded to Charles Humble of the National Institute for Truth Verification (NITV) that establishes numerical values to stress levels experienced when lying, even using recorded speech. Read the entire article here.

The NITV markets the Computer Voice Stress Analyzer (CVSA I and CVSA II) , which purports to be 96%-98% accurate at discerning truth from fiction. It has been marketed primarily to law enforcement and military intelligence agencies, thus far. It uses an algorithm to analyze and graph frequency modulations in unstructured speech. These graphs then display “positively” whether the person has lied in response to a question.
“Micro tremors are tiny frequency modulations in the human voice. When a test subject is lying, the automatic, or involuntary nervous system, causes an inaudible increase in the Micro tremor’s frequency. The CVSA® detects, measures, and displays changes in the voice frequency.” From the web site: (http://www.cvsa1.com/CVSA.htm)

I remember when my apparently prescient mother used vibrations to test my own veracity. She would have me put my index finger in a bowl of water and answer her questions. If the water vibrated, I was lying. She swore by it, but my independent observations were that it was about 50/50—and easily manipulated. Ahem.

Other interesting ways of teasing out the truth include one near and dear to my heart—the magic donkey. (Why? See my portrait on the first blog–Jan 2008.)

…circa 500 B.C. in India. A priest put lampblack on the tail of a donkey in a dark room and all suspects were to pull the magic donkey’s tail. They were told that when the one who was the thief pulled the magic donkey’s tail, he would speak and be heard throughout the temple. The person who did not pull the tail had clean hands and was pronounced the thief and punished.

As if all of this weren’t frightening enough to the average “little white liar”, a South Korean company claims to be able to identify real vs. fake emotion. An article in Cellular News, dated 09/26/2006 says “Nemesysco’s leading technology is also powering KTF’s new ‘Love Detector’ service, which tells the caller the “love level” of the person on the other end of the line every 10 seconds - so that subscribers can tell whether their loved ones share their feelings all through the conversation. Once the call is completed, the subscriber also receives a message ranking the overall level of affection, plus graphs that measure various attributes such as level of interest, attention, expectation, and embarrassment.”

Gives a whole new sensation of terror to the question “Does this dress make me look fat?”, doesn’t it? I wonder if they caught the irony in their company name…Nemesys aka Nemesis. I did!

Supposedly, there are no known countermeasures to the CVSA truth verification methodology. I’d be interested in knowing whether a skilled character actor could deliver lines convincingly enough to fool the system. I hope so. As much I want the truth to win out over lies, there are situations where a half truth, a kind fiction, is a far, far better response than the cold, clinical, absolute truth. And I am sure that the marketing groups, political organizations and pundits of all flavors would agree wholeheartedly, eh?

The power of speech is unmistakable, inescapable. Its power for good and harm is real. Have we reached a place where we are orchestrating a version of Brave New World in which the privacy of our own mind and our heartfelt intentions are lost? What do you think? Speak up. And remember…Big Brother is listening…

The W4’s of Search

When you think about Search today, most people simply “Google”. However Yahoo is trying hard to catch up and recognizing that the desktop war is over; they are focusing their attention on the mobile platform. Their belief is that Search will become much more of a mobile application in the future and that a good Mobile Search will be much more than just typing in what you are looking for and seeing a list of results.

At the Voice Search conference today, Yahoo presented the idea that Mobile Search involves the four “W’s”: What you want; Where you are; Who you are and When you want it. Yahoo has coined the term W4 to describe this concept to those of us who can’t keep up. Or to be more technical, you are really looking at four data types concurrently when performing a mobile search – Topical, Spatial, Social and Temporal. That being said, I think Google is already well down the path to W4 nirvana and Yahoo may be too late (again). Here’s why.

As an avid Google Maps user I can attest to the fact that my desire to “map” before I embark on a road trip (i.e. on my desktop and then print it out) has now been 100% supplanted by my ability to “Google Map” during the trip. Of course this presents its own set of challenges if I am driving.  Also I do find that Google’s sense of direction competes with my wife’s Garmin on a regular basis, resulting in lively discussions about which (i.e. who) is right. (The Garmin usually wins of course! )

However, Google Maps is a great example of a real product that exhibits W3 and possibly W4-ness. If you think about it, I am combining Topical Data (What is my destination) with Spatial Data (Where do I go to get there). I have recently added Google Latitude to my mapping experience which allows me to see where my wife and kids are at any time, assuming they have their devices on. So that’s Social Data, i.e. “Who”. So there’s W3 already. The only thing left to reach a state of W4-ness is Temporal (When). Is that hard to imagine? I can envisage that soon I will be able to ask Google Maps for “places to eat” and that it will only return those things that I could do at the time I asked them. It will show me lunch spots at lunchtime and diners at breakfast. It may only show me ones that have been recommended by my Social Data base if that’s what I want and perhaps only those that are within walking distance if it has ascertained from my GPS that I am in fact walking.

If you assume that Mobile Search is the brave new world of Search then the W4 concept is very compelling. The trick seems to be the one with the most data will win. Can I see myself “Yahooing” from my mobile device at some point in the future…no, not really.

MTI at Nuance Conversations 2008

Sun and Speech, Conversations 2008 is underway at the Rosen Shingle Creek resort in Orlando.  MTI is exhibiting in the “Solutions Showcase” area so if you are attending the conference this year, stop by and say hello.  In addition to meeting some really charming folks at our pod,  you can also find out how we plan to save the economy 1,000,000 minutes at a time…ahem.

Cacophony

Ah…SpeechTek in New York City amid the frenetic activity of hustlers and buskers, business suits and Bermuda shirted tourists of every size, shape and nationality imaginable. What a backdrop for a convention dedicated to trends and technology for Speech IVR applications!

The noise quotient roars in the background—cars and trucks and ambulances and construction and people. It is a voice designer’s nightmare. All of this din competing with the caller’s voice for the hapless speech recognizer to filter, parse and manage to return a reasonable response. And yet, that is the focus of this conference—how to reach and engage the new mobile user—the customer of our future. And this includes dealing with these very conditions. So what seemed dichotomous proves to be a perfect setting.

How will we serve this new breed? Our industry is maturing; the rush for better and better technology is evolving to a new focus on how to do what we do better—how to target and respond in new ways to the challenge of communicating with and selling to these tech savvy, in a hurry, high energy and strongly individualistic people. Turning the clock back in time to see that in choosing machine over personal service, we have taken away the very reason that we need and want to interact with each as customer and vendor.

Once upon a time, when you wanted to speak with someone about something, you went to them, and asked them your question. If they were not available, there was someone there who knew where they were, when they would return, and very likely, be able to answer your question or address your concern for you—personal contact, in a direct context.

In today’s IVR environment, we have a one size fits all response through which the caller must wade step by step, without regard for what she actually needs or wants. She must sit impatiently through menus, marketing messages and jargon before selecting the option of interest. What a waste!

In the brave new IVR of the future, we want to see a return to the personal service that comes from an understanding of the caller–using caller history, reverse ANI matching and demographic information behind the scenes to offer pertinent options and messages, and then displaying them in a multimodal way that allows the caller to respond and track that information in a way that is meaningful and useful for them. The message is “It is all about me. I am The Customer!” That is the voice that rises about all the sound and fury here in New York.

Reducing your IVR footprint using Speech may decrease your risk of cancer and save the planet?

Datamonitor recently put out a report that talked about the value of hosted speech and describes the “IVR footprint”.

“At the end of 2004, revenues from the hosted and premise-based managed IVR market in North America were just north of $1.9 billion. As a result of its large IVR footprint, traditional IVR accounted for the majority, or 78.2%, of revenues. Voice-XML accounted for 21.8% of revenues”

When they refer to Voice-XML I believe they are referring to Speech-based IVR. So it tells me that old-fashioned DTMF based IVR is still in heavy use and Speech is slowly getting acceptance.

It got me thinking about how we are being told by Al Gore and the media that our “carbon footprint” is fueling global warming, polluting the air and generally destroying the environment. I did not come up with an immediate solution to this problem, but I saw a new report from the Univ. of Pittsburg this morning that declares yet again the theory that radio waves from cell phones may be causing brain cancer and I felt there might be a connection. Most people have already decided where they stand on climate change; some people fear cell phone radio waves (did you see the fake YouTube ads?).

Let’s assume that both have some modicum of truth - so how are they related and, you may wonder, how does Speech IVR play a part in the solution?

We can cycle to work (25 miles for me…) turn down the A/C, stop drinking bottled water from the island of Java and use speakerphones but how can we focus our business investments on solving these issues?

We know that IVR works well for routing calls to the right agents in a call center and capturing a limited amount of data. Does traditional IVR reduce call time? In some cases yes, in most cases maybe not. However we do know that using a well-designed Speech application in many cases will reduce call time significantly simply by allowing a more conversational interaction with the IVR, a more efficient presentation of the needed information and as a result very little, if any, agent interaction.

So here’s the basic theory: If we can reduce the amount of time a caller spends on the phone, which includes how long they spend with an agent, then they will be exposed to fewer radio waves from their cell phone. As a result of the reduced call time, companies will be able to use fewer agents which will mean smaller facilities, less people on the road and a reduced carbon footprint overall.

Does this sound either a bit off the wall or possibly too good to be true? Is there a catch? Back to that Datamonitor report:

“The relatively high costs of speech have deterred many businesses from investment. As a result, a number of these businesses have looked to hosting to leverage the benefits of speech without having to put forward the heavy upfront costs for a speech solution. For these businesses the hosted model minimizes cost, time and risk for speech application development, tuning and expansion”.

So there you have it! Help save the planet, reduce your callers’ risk of cancer and spend less money to boot. Take a look at your IVR footprint and your agent footprint. Would the simple implementation of a hosted Speech IVR solution reduce your call time by even 10%? It may well make a difference.

I’d love to hear some comments. Am I on to something here? After all a year ago everyone thought hybrid cars were weird and only for the tree-huggers…how times change!

Next time we’ll look to see whether Speech can turn around the economy, reduce the price of gas and get our troops out of Iraq…stayed tuned.

SpeechCycle Reaches 50,000,000 Automated Interactions

Just wanted to tout an article from Call Centre Clinic featuring one of our partners, SpeechCycle. They have hosted with us since 2002. The technique for which they credit their astounding success in automation is called delegation. Below is an excerpt from Roberto’s recent blog.компютри

The reason for this dramatic increase in automation performance is simple, and is called “delegation”. Rather than having callers perform certain operations or provide certain pieces of information, the dialog system delegates other systems and information repositories to do that. We like to say: “The best question is a question not asked,” to stress on the fact that if there are other ways to collect some pieces of information other that asking the caller, that should be done. By delegating the collection of information or the performing of some actions to external enterprise backends rather than to the caller would lead to better interaction experience and higher automation. Read the whole blog…

It just makes common sense to use the tools you have. Reverse ANI lookup, databases with customer information and configurations, and, when you do need to put a call through to an agent, CTI to pass in any information you have gathered to streamline the call and enhance the user experience. Some of our customers have balked at the additional cost, but when you can quantify the cost of an unhappy caller anecdotally or graphically they usually come around..

The 800 Pound Gorilla NOT in the Room

Last week I attended the CTIA Wireless 2008 Expo in Las Vegas. This event is the annual industry tech fest attended by anyone and everyone who makes a difference in the world of wireless. CEO’s and senior execs of AT&T, Verizon, Sprint, Lucent, Ericsson, Samsung, Microsoft, RIM et al were there making sure that their particular market angle was being hyped. What happened in Vegas last week definitely did not stay in Vegas!

However, embedded in the speeches and announcements was one popular theme – how nervous is the iPhone “ground swell” making everyone? Over 2.3M iPhones have been registered on the various carrier networks in the first few months it was released, a truly astounding statistic for any single wireless device. The fact that about a million more than that have been sold is an odd anomaly that is generally thought to be caused by Asian and European visitors to the US buying them in bulk using cheap US Dollars, taking them home and hacking them to work in their own country.

Well over 20M iPhones are expected to be sold before the year is out and by the end of 2009 close to 50M. I expect we will see iPhone 2.0 announced early next year. One of the biggest VC companies in the known universe, Kleiner Perkins, who has achieved cult status in the Valley over the years with home runs like Google, announced the $100 “iFund” specifically to invest in iPhone app developers. The iPhone has achieved a cult status in 6 months all on its own!

But, amongst all this incessant iPhone chatter - where was Apple? Not a single Apple booth amongst the 1,200 + in the exhibit hall, no senior executive making a key note, no representative in any of the conference sessions, not even an Apple sponsored offsite after-hours cocktail bash.

Maybe it’s me, but for such a game changer in the industry, this lack of presence was truly astonishing. I know Steve Jobs likes to control his world and buck the system, but it is almost like the planners for CTIA forgot to give him a call: “Hey Steve, since you are new to the whole Wireless world, you might want to know about our little conference, we’d love to have you show up and do your thing -its not like the boring PC industry; wireless is really cool and you’d really like the people.”

In the next few years, annual revenues from the wireless industry are expected to exceed $100B which will be bigger than the entire Sports industry ($96B) and almost as big as the Casino industry ($105B). Come to think of it, maybe those cool people at CTIA want to keep quiet about this for a little longer and hope that Apple does not crash their party quite yet.

Microsoft Sneaks Across the Rubicon

I remember several years ago Steve Ballmer (or was it Bill) said something along the lines of “if I could get $10 a month for every single Microsoft customer I would never need to sell another software license.”

Well I think that day may finally be coming. I attended a Microsoft Conference in a suburb of Chicago last week and amongst the Powerpoint overload and mumbled presentations by some newby Microsoftees they stated that they want to give the customer a choice of buying their hosted Microsoft solutions from a partner or direct from Microsoft. What…backup a minute…did you say direct from Microsoft. Apparently this had been announced a few months ago, but based on the subsequent “gulp” that emanated in the audience I can only assume they all missed the memo.

Well the MStees did have a legitimate explanation – “that’s what Google is doing” (oh and a few other like eBay and Facebook – huh?) so we have no choice – of course! Now for a company that prides itself on its partner programs this seems a little disingenuous, especially when they announced a couple of earlier slides how many hosting partners they had managed to sign up since they launched the program.

They have coined an interesting term to further obfuscate the concept – “Software + Services Channel” which sort of, kind-of, means “Software-as-a-Service through the Channel”, but clearly this was not the full story.

Anyway, most of the partners in the audience took it well. After all 1) they have no choice and 2) their customers would never buy direct from Microsoft. Why would they, I mean what would they get from the mothership that they could not get from Larry down the street. Of course people will pay a premium to shop locally, everybody knows that. Did somebody say Walmart…

Well it might take a while, but $10 multiplied by the entire population of the planet (other than the Chinese who use their own stuff) is a big number to be getting every month. Both Steve and Bill will be very proud one day.

GetHuman loses its founder, and its focus

I see that Paul English, of GetHuman.com fame, or perhaps notoriety is a better term, is throwing in the towel. Remember him? Only a few years ago he led the angry mob in a fight against the gnarly evils of telephone automation, providing a list of ways to get around the IVR and to a human agent. Today he is apparently too busy to continue to champion the movement he started, and has turned it over to Walt Tetschner, a self-styled ASR specialist and industry curmudgeon. Walt publishes an online newsletter with slightly whimsical pans and plugs of IVR applications, as well as well researched articles on events and trends in the speech technology arena.

I first ran across him when I was reeling from an encounter of the hideous kind using a Social Security Administration self-service application. Hapless me, I just wanted to find out how to change my social security number to my married name. After 20 minutes of fumbled repeated attempts, I gave up and drove 45 minutes to the nearest office. It was a waste of my time and energy. And such frustration!

I am well schooled in my IVR responses. They are crisp and without disfluencies. But I was stuck in a revolving nightmare of broken steps, recursive paths, illogical phrasing and overwhelming bureaucratic traps. Walt gave it a less stinging review than I would have, but overall, had the same negative perception of the experience that I did.

Since then I have read Walt’s posts in various forums. It will be interesting to see what he does with GetHuman. And whether his vinegar rather than honey approach invigorates or alienates the VUI design standard movement.