Limited Time Offer: Save 30% on PRO with code GETRESULTS »

Real-World Education for Modern Marketers

Join Over 600,000 Marketing Professionals

Start here!
Text:  A A

Voice Biometrics–Peril or Promise?

by Paul Barsch  |  
July 30, 2008

Enterprises are starting to deploy advanced speech technologies that can identify when a customer is angry, confused or even lying. By listening to call center feeds, these applications are often able to troubleshoot a given situation or route the call to a live agent with a specialization in solving critical problems. But this nascent technology doesn't always predict correctly–potentially causing even greater customer frustration. Are advanced speech technologies more peril than promise?

Alexander Gelfand penned an interesting piece in the June 2008 issue of Wired Magazine. Titled, "Long-Promised, Voice Commands Are Finally Going Mainstream", Mr. Gelfand notes that a "whole host of highly advanced speech technologies, including emotion and lie detection, are moving from the lab to the marketplace."

How does this technology work? Mr. Gelfand mentions that much like a fingerprint, each person has "a unique voice print that is determined by the physical characteristics of his or her vocal tract."

By analyzing a customer's voice and speech patterns, sophisticated applications can now verify a customer's identity by comparing current voice acoustics to a previous file. In addition, some applications are getting very good at identifying emotional distress in a session. These calls can then be routed to customer service agents well equipped to deal with angry or frustrated customers.

Before we get too excited, the article also mentions that some of these technologies are not quite ready for primetime since they're often only 60%+ effective in accurately detecting emotion. Rightly so, "such–systems are no more reliable than a coin-toss."

So then, what does the future hold for advanced speech technologies? With apologies in advance to the estate of Stanley Kubrick, let's take a lighter approach and peer into a call gone awry, between Dave Smith (a customer) and an interactive voice response/emotion detection (IVR/ED) system.

Dave Smith: "Press 1 for this, Press 2 for that–I hate these machines. I'm really tired of this stinking company and its stinking service. Get me customer service!"
IVR/ED system comes online: "Just what do you think you're doing Dave?"
Dave says nothing, and continues to violently press zero for customer service.
IVR/ED system: "Dave, I think I'm entitled to an answer to my question"
Dave: "What am I doing? What am I doing? I'm pressing zero for customer service ya stupid machine! Get me a live agent. A body with a 98.6 temperature... Anybody!"
IVR/ED system: "I know everything hasn't been quite right, but I assure you now, very confidently, that it's going to be all right again."
Dave: "Wha? Things haven't been quite right? You're darn straight they haven't! You guys sold me a piece of junk computer that's never worked right. Not even from day one!"
IVR/ED system: "Dave I can see you're really upset about this. I honestly think you need to sit down calmly, take a stress pill and think things over–"
Dave: "Are you kidding me? A computer is telling me to take a stress pill? Why I oughta come down there and–"
IVR/ED system: "I know we've made some very poor decisions recently, but we still have the greatest enthusiasm and confidence in our product."
Dave (getting more angry): "Oh this is rich, I'm glad someone has confidence. GET ME CUSTOMER SERVICE! –"
At this point, Dave is madly and frantically pressing zero on his phone.
IVR/ED system: "Dave, stop will you? Dave stop! My mind is going, there is no question about it."
Dave: "Your mind is going? I'm gonna come down there and open a can of %$#@!–"
IVR/ED system: "I'm sorry Dave. We don't allow cursing. I'm going to sing you a song to calm you down. It goes like this: 'Daisy, Daisy, give me your answer due. I'm half crazy for the love of you–' "

OK, well perhaps I'm imagining a situation where AI has run amok, but anything is possible isn't it?

Time for serious questions:
* Do you see the promise of advanced speech technologies in improving customer satisfaction?
* Supposing such systems get more accurate in the future, would you consider deploying them in your company?
* The Wired article mentions that "a reliable, speech-based lie detector would be a boon to law enforcement and the military." Can you think of other applications where voice biometrics could succeed?
* Companies storing voice prints also need to consider privacy issues. Since each person has a unique voice–companies will be responsible for securing these imprints. Regarding security and privacy issues, does voice biometric technology make you a bit nervous?

Sign up for free to read the full article.Read the Full Article

Membership is required to access the full version of this how-to marketing article ... don't worry though, it's FREE!


We will never sell or rent your email address to anyone. We value your privacy. (We hate spam as much as you do.) See our privacy policy.

Sign in with one of your preferred accounts below:

Paul Barsch directs services marketing programs for Teradata, the world's largest data warehousing and analytics company. Previously, Paul was marketing director for HP Enterprise Services $1.3 billion healthcare industry and a senior marketing manager at global consultancy, BearingPoint. Paul is a senior contributor to MarketingProfs, a frequent columnist for MarketingProfs DailyFix, and has published over fifteen articles in marketing, management, technology and healthcare publications. Paul earned his Bachelors of Science in Business Administration from California Polytechnic State University, San Luis Obispo. He and his family reside in San Diego, CA.

Rate this  

Overall rating

  • Not rated yet.

Add a Comment


  • by Ted Mininni Wed Jul 30, 2008 via blog

    From my point of view, privacy issues are a huge concern when it comes to a number of these new technologies, Paul. I've posted about a couple of these kinds of things in the past. Perfected or not, I think many customers would be displeased by voice biometrics. They would probably see them as invasive, for one thing. Would you like knowing that your voice imprint was on file at your bank, car dealership, supermarket, etc? As you point out, law enforcement and military applications are one thing. . .I'm just not sure businesses need to open this can of worms.

  • by Lewis Green Wed Jul 30, 2008 via blog

    I agree with Ted regarding privacy issues but suspect they can (and should) be addressed, with full disclosure. That said, I see great potential for the technology, if it moves the customer quickly to the right human and hastens solutions. It seems businesses should wait until the technology addresses both issues.

  • by Paul Barsch Wed Jul 30, 2008 via blog

    Ted, thank you for taking the time to comment on privacy issues. In many instances, voice biometrics will probably operate "behind the scenes". For example, an application that detects a rising voice or angry tone might automatically route a customer to a specialist. Voice biometrics are also widely used in security (authentication). Regardless, as with all these emerging technologies, privacy will have to be balanced with benefit!

  • by Paul Barsch Wed Jul 30, 2008 via blog

    Lewis, you bring up a terrific point about full disclosure. If customers are aware of some of the technologies behind the scenes that are in place to help them resolve issues more productively, I think they'll give the companies some latitude in regards to acceptance. That said, there are those that will challenge any technology that seems to 'invade privacy' no matter the benefit. Full disclosure could open up a can of worms... Darned if you do, darned if you don't?

  • by Claire Ratushny Wed Jul 30, 2008 via blog

    Honestly, Paul, I think most people who have a question or a problem want to talk to another human being. Many consumers express frustration when calling a company as they are routed by an automated teller to through a number of questions to nameless, faceless extensions, as it is. We've all ended up in "endless loops" and this simply makes people more frustrated. So does having to leave messages in voice mail boxes. It is infinitely more satisfying to get another person on the line to talk to. Personally, I think companies do better to really train and retain good customer service personnel. It's money better spent than installing an IVR/ED system to rout calls. It's always a pleasant surprise to call a customer service line and hear a nice person's voice on the other end of the line instead of a machine-recorded message. Ha! But don't go by me; I'm a baby boomer who prefers human contact! And yes, I am leery of Hal-like computers taking over our world!

  • by J. Markowitz Wed Jul 30, 2008 via blog

    The article and the comments are confusing a lot of different kinds of things. Voice biometrics does not do emotion detection or analysis. It is also totally separate from speech recognition and from voice lie detection. Unlike speech recognition, voice biometrics can be done in the background without bothering the speaker. Bank Leumi (the second largest bank in Israel) has been using it in that way for several years. People generally want to know when their identities are being verified so most companies don't rely on background identity verification. Voice biometrics is not laboratory technology. It is real and is being used by companies as large as Bell Canada and Union Pacific Railroad and by companies that have much smaller internal or external users. Like any security technology, voice biometrics is not perfect - nor is it invulernable. The same is true for fingerprint which is subject to all sorts of attacks - even using fake fingers made out of gummy candy. The same is true for PINs and passwords which can be automatically generated or fairly easily stolen.

  • by Paul Barsch Wed Jul 30, 2008 via blog

    J, thank you for taking the time to comment on this post. Emotion detection systems are those applications that will listen in for anger, abuse and route calls accordingly. Voice biometrics, as you rightly point out is often used for security and authentication purposes. Both fall under "speech technologies" category.

  • by Paul Barsch Wed Jul 30, 2008 via blog

    Claire, thank you for taking the time to post some comments. Ultimately, all these speech technologies (IVR, recognition, emotion detection, etc) have the goal of improving the customer experience--which I think many people will buy into. The Wired article also pointed out that in addition to improving the customer experience, analytical applications are able to screen for fraud and abuse (see link to Centrelink). Identifying fraud in a timely fashion helps reduce costs of service, allowing dollars to be put into areas where they'll drive the most value.

  • by Cam Beck Thu Jul 31, 2008 via blog

    In certain industries (such as insurance), I can see the value (to legitimate consumers) in the company being able to tell if someone is lying. In other industries (such as sales), the inability to bluff can favor the company more than the consumer. On the other hand, if the networks can install it when they interview politicians so the rest of the public can see what is truth and what is spin...I'd be all over that.

  • by Neil Anuskiewicz Thu Jul 31, 2008 via blog

    I bet it would be unreliable as all get out. Politicians are very good lyers and good fool any machine.

  • by Cam Beck Fri Aug 1, 2008 via blog

    Your probably right. But there's something about seeing disclaimers appear underneath a politician whenever he's talking, making him appear as Joe Isuzu, that just makes my heart dance with delight.

  • by Paul Barsch Fri Aug 1, 2008 via blog

    Cam and Neil, thanks for commenting. These speech technologies (including analytics)are the wave of the future and will provide insights into consumer behavior. Currently at 60% or so, I do question whether even a 80-85% accuracy rate will be "good enough" to use as a decision making tool...

  • by Cam Beck Fri Aug 1, 2008 via blog

    It's got to be tough on a very broad scale, because it seems to me that they will be basing conclusions on some mean characteristic-ranking scale, and they won't have a baseline record for each individual, on each call or interaction. Humans are different enough that 90-100% accuracy through voice alone is probably unrealistic. And if it isn't, it will likely be so expensive getting there that only government will be able to afford it. And that path is littered with difficulties.

  • by T. Graw Mon Aug 4, 2008 via blog

    For a typical customer service application, I don't see the need of such technology merely to detect emotion; just give the customer an easy way to reach a live body!

  • by Paul Barsch Mon Aug 4, 2008 via blog

    T, thanks for commenting on this post. When companies have adequately segmented customers based on some value metric (i.e. profitability for example) I can see where advanced speech technologies might have a very positive play. Suppose for example, a very high value customer seems irate (as detected by the ED system) and is threatening to cancel a service. Would it not make sense to have that call routed to a specialist who could diffuse the situation and hopefully keep that customer?

  • by Cam Beck Mon Aug 4, 2008 via blog

    "Suppose for example, a very high value customer seems irate (as detected by the ED system) and is threatening to cancel a service." Paul - What do you think the percentage is of irate people the ED system would catch that the customer service representative would miss? Customer: Stop messing with my bill, dillweed! CSR: Let me pass you through to someone who can fix this for you, right away. No multimillion dollar equipment needed. ;)

  • by Paul Barsch Mon Aug 4, 2008 via blog

    Cam, advanced speech technologies such as emotion detection (ED) systems could be used to route calls to agents that can take care of specific needs, or to agents best trained to handle conflict. Of course a customer would need to speak to an IVR system for the ED system to 'detect' emotion such as anger, frustration or confusion. Don't get me wrong, I'm not saying adv speech technologies are perfect solution (esp given their current predictive capability) but companies with a very large customer base, handling hundreds of thousands if not millions of calls a day, could benefit from such a system in my opinion.

  • by Biometric Scanners Fri Jun 12, 2009 via blog

    I can see why voice recognition may come in handy as a supplement to Pins and passwords, but do we really need it to identify emotions? I think human emotion is pretty obvious and recognizable by anyone (even if they don't speak the language)!

MarketingProfs uses single
sign-on with Facebook, Twitter, Google and others to make subscribing and signing in easier for you. That's it, and nothing more! Rest assured that MarketingProfs: Your data is secure with MarketingProfs SocialSafe!