BPA Featured Article

Speech Analytics Takes Call Monitoring to the Next Level

By Tracey E. Schelmetic, TMCnet Contributor
January 14, 2016

In an effort to improve the quality of customer support offered today, many companies use monitoring coupled with data analytics to keep track of customer journeys, including website visits, clicks, emails, ratings and words on review sites. While this is all great, it’s important to understand that customers may not be communicating the most important information via these channels. Speech is still the most natural form of human communication, and the telephone remains customers’ number one choice of media when they need real help. In other words, if your company isn’t capturing the customer’s voice (the real human voice) and analyzing the information in it, the picture of the customer experience a company is getting isn’t complete.

There are solutions available today that use speech-to-text technology: automatically transcribed voice calls are converted to text, and that text is run through an analytics algorithm. In some cases, more advanced solutions don’t even need the transcription step, and instead are optimized to go from speech right to analytics. Whichever type of solution a company chooses, it’s a great way to uncover root causes and hidden insights into customer behavior and intent. (Alternatively, a company might turn to a third-party call monitoring provider that is already optimized for this kind of analytics-driven monitoring.)

In a recent article for Tech Republic, Mary Shacklett, president of research group Transworld Data, recounted a case study involving Sekerbank, one of the leading financial institutions in Turkey. The company, aware that its customer interactions were not the best, was seeking to improve the quality of customer interactions in its Desmer telephone contact center, but there was no way manually to accurately analyze all of the calls that came in on a daily basis until it turned to technology.

“The bank decided to adopt speech-to-text technology that through analytics was able to uncover root causes and hidden insights by transcribing calls to digital text,” wrote Shacklett. “It also implemented an emotion-detection software that analyzed and published important findings about problematic conversations that resulted from customer dissatisfaction by using the ratios of anger, monotony, interruption, and silence as evaluative criteria.”

While it’s true that there is a lot of insight in what customers say, there is even more insight into what customer’s don’t explicitly say. Using profanity, for example, indicates anger, even if the customer does not say, “I’m angry.” Agents and customers talking over one another indicates conflict, and long periods of silence may indicate that the agent isn’t properly trained.

“Textual and emotional analysis and various data mining methods were applied on the transcribed audio, and Sekerbank was able to gain important insights about call center efficiency, agent performance, and customer satisfaction,” wrote Shacklett. “The analytics work contributed to reductions in call center operating costs, and the call center's overall handle time and first call resolution rates improved. The bank was also able to assess customers' reactions to marketing efforts and attitudes toward competitors.”

If you’re looking for a competitive edge in your customer support, or simply struggling to find out what your customers want and need, consider listening to them. Not evaluating one call a month, or conducting two customer surveys a year, but really listening to everything they say (with the help of call recording and data analytics, of course). There may be some obvious fixes you can make to your processes that will boost the quality of your customer experience significantly. You just don’t know about it yet, because you haven’t been listening. 



Powered by Technology Marketing Corp. © 2021 Copyright. | Ph: (800)-243-6002 (203)-852-6800 Fx: (203)-853-2845 | Contact Us