Contact Center Solutions Featured Article

NICE Systems on the Advantages of Speech Analytics for the Call Center and the Enterprise

November 01, 2007

Speech analytics continues to see rapid adoption in the call center industry, as companies are starting to discover the many advantages speech analytics solutions have outside the call center as well as inside. Thanks to major advancements in the algorithms used to interpret speech, coupled with faster processors, these automated systems now enable organizations to “mine” their recorded calls and gain insights about their customers - and their agents - which they were previously unable to discover using manual call monitoring.

Unlike the speech analytics solutions of a few years ago, which were mainly used to perform simple “word spotting” in recorded conversations, today’s solutions can actually identify the context of what is being said, thus giving organizations the ability to more accurately categorize calls and analyze customer-agent interactions. In fact, these systems have advanced to the point where they can actually detect emotions, thus giving organizations a powerful new way to measure customer satisfaction. So, not only can these solutions be used to monitor and improve agent performance, they can also be used to find out how customers react in all types of interaction scenarios – whether it is a rude agent that is turning your customers off; something in your agents’ script that is turning your customers off; or call hold times which are simply too excruciatingly long. But beyond that there are other important applications. With speech analytics you can find out how your customers are reacting to a new product launch, and new marketing campaign, or perhaps something that your competitor is doing which is drawing your customers off sides.

As such, today’s speech analytics solutions have just as much, is not even greater value outside of the contact center than inside. Because today’s solutions are capable of mining all of the call data, as opposed to just a small percentage of it, this enables organizations can get a more accurate view of the “big picture” and then take appropriate action. As a result, speech analytics are increasingly being used by executives in sales, marketing and operations to increase revenue, reduce costs, increase customer retention and improve the overall performance of the call center. Interestingly, as organizations come to adopt these solutions, the role of the call center is being redefined into that of a “business intelligence center,” or “central hub of intelligence” for the organization.

To find out more about the advantages today’s speech analytics solutions hold for the call center, and in fact enterprises as a whole, ContactCenterSolutions recently interviewed Barak Eilam, vice president and general manager, interaction analytics, at NICE systems, a leading manufacturer of speech analytics software and other call center solutions. What follows are excerpts to our questions:
How can speech analytics help the average call center?
Contact center management is growing more and more complex, and centers must satisfy increasingly demanding customers while reducing operational costs. They can only do this by leveraging technologies and making the best use of the synergies between them.
NICE uses comprehensive multi-dimensional Interaction Analytics to leverage customer interactions and identify trends and opportunities in a timely manner. Call centers can benefit from speech and other analytics in three main spheres:

--Operations – identifying changes in service KPIs, such as first call resolution, call volume, hold time and so on.
--Customer satisfaction – measuring satisfaction levels for all customers as well as identifying and alerting for specific customer issues
--Market dynamics – providing timely notifications of potential competitive risks (such as a sudden increase in competitor mentions)
What size call center is the technology best suited for?
Interaction Analytics can help any size of a contact center. Obviously, large centers face greater management challenges and as such can benefit from the technology significantly. However, we have also been working with small call centers that are experiencing fast-paced growth. Implanting Interaction Analytics early in the development cycle of such centers helps them to improve significantly the management of such rapid growth and to meet the associated challenges. Any contact center with more than 50 seats can benefit from the technology and see a very good ROI.

How reliable is the speech recognition needed for the speech analytics at this point? Are confidence factors high enough at this point that the results delivered by speech analytics are right all the time?
Speech Analytics technologies have reached a level of maturity that provides unique and significant value to contact centers and enterprises. This is more than a single technology; it is a combination of data dimensions and analysis methods. As a result, very high business accuracy can be gained from multi-dimensional analysis.
How hard or easy is it to get speech analytics solutions integrated with the other functions/solutions in the call center?
Speech analytics technologies are very sensitive both to the source and the quality of the data. For example, to drive the best analysis capabilities it is highly recommended that the interaction is captured in a ‘stereo format’, meaning that the agent and the customer are recorded separately. In campaign effectiveness, for example, analysis of the separate recordings allows the analyst to identify whether it was the customer who asked about the campaign, or the agent who recommended it. Clearly, speech analytics that are closely integrated with Quality Management and recording solutions can ease the deployment process and provide much better value. NICE offer a unique SOA architecture to its customers that supports a smooth and tight integration of Interaction Analytics.

Does it matter where the material to be analyzed by the speech analytics solution resides? What about distributed call centers where the data may reside in many different places?
NICE Interaction Analytics processing can be deployed in both centralized and distributed architecture. In both cases the analytics results are stored in a central datamart that enables end-to-end analysis. The customer’s decision is usually a function of the cost involved, and is based on the trade off between processing costs and network bandwidth costs.

Are the results real-time?
Some results are real time. In most cases, the requirement is to enable near real time rather than an immediate real time results. We call this providing “right-time” results, which is best illustrated by the NICE SmartCenter, which provides an innovative solution for managing contact centers in an insightful, proactive manner, and take action at the right-time. For example, many companies prefer that an alert concerning a dissatisfied customer be provided immediately after a call ends. This allows the supervisor (or the customer care group) to listen to and analyze the interaction before deciding whether to call the customer back.
Do you need to be an IT professional to interpret the results offered by the average speech analytics solution?
Absolutely not. The NICE Interaction Analytics suite is provided with reporting and analysis tools that are tailored to meet the needs of different users with a variety of skills. A potential user could be a contact center supervisor, marketing director, business analyst, or a senior executive. Each of them can access, view and analyze the relevant results quickly and simply.
Speech is still generally considered by many in the call center industry, to be a luxury ... and for call routing only. Can you talk a little bit about the ROI of speech analytics, which I imagine is quite higher and has faster turnaround than the speech technology implementations of just a few years ago?
Speech analytics is capable of yielding a rapid return on investment of three to six months. Success is a function of realistic expectations, concentrating on one initiative at a time, and allocating appropriate resources to the project. Our experience suggests that the key ingredients for a quick ROI are:

--Using advanced and cost-effective technologies of mass analysis (such as phonetics search, emotion detection)
--Deploying a multidimensional analysis that permits analysis from different angles
--Successful integration with the contact center’s basic application such as quality management
--Investment in Interaction Analytics consulting services


Patrick Barnard is Associate Editor for Customer Interaction Solutions magazine and Assignment Editor for ContactCenterSolutions. To see more of his articles, please visit Patrick Barnard’s columnist page.