In the Contact Center: Speech Analytics Software Buying Guide
Updated · Feb 26, 2013
People once spent years lying on a couch pouring out their deepest secrets so a psychotherapist could analyze the underlying meanings. Now call centers use software to analyze what customers are saying in real time.
While call center speech analytics software won’t resolve their relationship with their mothers (though that may be coming in later releases), no appointment is needed, there is no hourly fee and the process doesn’t take years — and some say the analysis is far more accurate.
“Beyond the ability to search for keywords on the fly or set up categories that auto-sort incoming calls, it is like having an army of analysts listening in on every call,” says Daniel Ziv, vice president, Voice of the Customer Analytics at Verint. “It can analyze 100 percent of calls, and track every word and phrase mentioned in all of them to help uncover the things organizations didn’t know to ask about.”
In addition to helping companies discover what customers are thinking, speech analytics software can reveal how well staff is performing and offer ways to improve customer service. These benefits probably go a long way toward explaining the rapidly growing popularity of speech analytics software in the contact center.
Here are five options to consider:
Verint Impact 360 Speech Analytics
With Impact 360 Speech Analytics, enterprises can automatically surface words, phrases and categories from thousands of recorded calls, alerting them to potential opportunities for action.
“Verint takes speech analytics further than transcription and phonetics,”says Ziv. “Organizations can use it to extract insights from actual customer conversations in order to provide business value.”
The software can be deployed on its own or as part of the Impact 360 Workforce Optimization Suite. It is built for analyzing massive amounts of data – up to 20 million calls in a single in-memory index. A busy call center agent can generate 100,000 words of customer interactions per day. Rather than operating off a pre-defined list of words and categories, Verint’s Complete Semantic Index (CSI) catalogs every word and phrase identifiable in every customer conversation.
It isn’t limited to ad hoc queries. Call centers can set up their own categories, and Impact 360 will populate the categories with past data and new calls as they come in. “It points out the potential root causes of such things as long handle times to declining satisfaction scores and key processes to improve without having to listen to any calls,” says Ziv.
Nexidia Interaction Analytics
Nexidia Interaction Analytics is a multi-channel platform that captures and analyzes 100 percent of customer audio and text from phone calls, chat, emails and surveys. It can track trends, evaluate the effectiveness of improvement plans and present the data to management as a dashboard or in reports.
“Common metrics such as first call resolution and agent performance are best measured and improved when comparing trends using 100 percent of audio versus a random sample,” says Nexidia’s COO Jon Ezrine. “This drives a need for a speech analytics solution that easily scales to meet these needs while keeping hardware requirements minimal.”
In order to capture and analyze all the relevant data, the software can search up to 2 million files at a time. Nexidia recently added social media mining and metadata filtering capabilities to the software. It groups calls into categories by subject and monitors metrics for each. It has expanded the number of languages it supports to 35. Rather than using a dictionary approach, the software analyzes the speech in terms of the 400 phonemes that are the foundation of all human languages.
Autonomy Speech Analytics
Autonomy Speech Analytics utilizes Autonomy’s IDOL speech analytics platform. In addition to analyzing the meaning of the speech, its Sentiment Analysis feature determines the degree to which a sentiment is positive, negative or neutral for the entire interaction or a segment of the interaction. It will combine interactions from the call center, website, point-of-sale and social media into a unified analysis, and can alert users to new topics that are suddenly popping up in customer conversations. It also monitors call activity and alerts to compliance risks.
Nice Interaction Analytics
Nice Interaction Analytics is a cross-channel analytics platform that analyzes speech, call flow, Web interactions, email and online chat conversations, customer surveys and agents’ desktop activity, to construct a unified view of the customer interactions. The analytics software ties in with other Nice business solutions targeting issues such as first contact resolution, reducing customer churn and improving collections. Each of those solutions is available to run on-premises or in a hostedsoftware-as-a-service (SaaS) environment.
CallMiner Eureka combines text and speech analytics from phone, email, chat and social media. It automatically evaluates every contact for sentiment/acoustics, categorization and performance scoring. Agents, supervisors and managers can set up their own customized portals (myEureka) to track pertinent metrics. It can be used with CallMiner Redactor, a standalone product for PCI compliance that will replace sensitive data in recorded calls with generic information for compliance and privacy purposes.
Drew Robb is a freelance writer specializing in technology and engineering. Currently living in California, he is originally from Scotland, where he received a degree in geology and geography from the University of Strathclyde. He is the author of Server Disk Management in a Windows Environment (CRC Press).
Drew Robb is a writer who has been writing about IT, engineering, and other topics. Originating from Scotland, he currently resides in Florida. Highly skilled in rapid prototyping innovative and reliable systems. He has been an editor and professional writer full-time for more than 20 years. He works as a freelancer at Enterprise Apps Today, CIO Insight and other IT publications. He is also an editor-in chief of an international engineering journal. He enjoys solving data problems and learning abstractions that will allow for better infrastructure.