Speech Analysis is Required for your Call Center, Now More Than Ever!

By Mingren Xiang

Remote Agent Success is Predicated using Speech Analytics

The Coronavirus pandemic is unprecedented for its global impact, forced work habit change, and uncomfortable transition in our daily lives. A shocking “new normal” characterized by the sudden need to shift toward a remote workforce under unexpected stress demands new tools and approaches. Speech Analysis is needed for your Call Center more than ever.

CX Delivery Challenges

Agents who have suddenly shifted to work-from-home or another remote situation may be challenged by unfamiliar equipment or new procedures. Speech analytics identifies CX impacting attributes and prioritizes changes to mitigate negative engagements.

Emphasizing speech analytics in the new digital era of remote working can pick up agent issues even when not expressed by an agent or customer in words. For example, long block of agent silence during calls, or long periods of inactivity between calls, are frequently key indicators that a procedure or response aren’t meeting standards in this new environment and need to be resolved.

Macrosoft’s CallMiner Services

Download Macrosoft’s CallMiner Implementation Services brochure to learn more how Macrosoft can help you achieve your Customer Satisfaction goals remotely.

Discovery tools enable quick identification of new topics that haven’t previously appeared, as well as changing volumes of topics that do appear. Reviewing desired outcomes and the conversations that led to them enables an enterprise with speech analytics to drive agent behavior towards those desired actions.

For example, mentions of “coronavirus” by callers that are met with great uncertainty and very minimal (if any) empathy by remote agents are red flags for a lack of training and support to help deal with worried callers. Using speech analytics to measure a defined “Brand Purpose” that positively aligns with a positive (or sometimes return to neutral) customer sentiment can demonstrate that the brand was properly represented by the agents’ responses and actions to effect that change, even when working remotely.

Measuring both Agent and Supervisor Effort in a Digital Era

Real-time analytics can proactively identify agent challenges in a virtual world. Example of metrics include “percent silence” and “understandability” can help to pinpoint peaks in effort expended by agents even when they are not specifically expressed in words. Comparison to peers on granular behaviors, such as out-of-norm silence due to hold or declining understandability scoring are creative methods for proactively discovering which agents are experiencing the biggest challenges and working with them individually to improve. Agent effort can and should be measured regardless of the location or circumstance to help front-line employees encourage favorable interactions as well as contribute toward a more effective and engaging employee experience.

It is more difficult to sense agent challenges as well as to huddle for coaching when supervisors can’t walk around the contact center to engage with their agents. Being able to share actionable insights due to automated scoring for behavioral indicators supported by emotionally engaging audio examples help draw a remote workforce together. Supervisors can confidently establish a benchmark for quality with performance metrics scored persistently, objectively and accurately without manually searching for what to coach on, or the need to be physically co-located with their teams. So long as supervisors can turn on a laptop or tablet and access their dashboard, they can manage and coach their teams from anywhere.

Macrosoft’s CallMiner Services

Download Macrosoft’s CallMiner Implementation Services brochure to learn more how Macrosoft can help you achieve your Customer Satisfaction goals remotely.

Share this:

By Mingren Xiang | May 27th, 2020 | General

About the Author

Mingren Xiang

Mingren is a Data Science professional at Macrosoft. He is Macrosoft's technical lead in voice and conversational analytics using the CallMiner suite of utilities. The practice includes both partnering with CallMiner to deliver speech analytic solutions and developing customized NLP applications. Mingren has a Master of Science from the University of Wisconsin-Milwaukee.

Aside from leading the speech analytics practice at Macrosoft. Mingren's research work focus on Deep Learning applications for medical image processing. He presented the Master thesis on training a CNN (Convolutional Neural Network ) based Encoder-Decoder model to reconstruct CT scans using only one X-ray image. Such a task remains to be one of the hardest challenges in the computer graphic community

Coming from a strong computer science background, Mingren is also sufficient in multiple programming language such as Java, Python, C/C++, various JavaScript libraries and SQL scripts. His specialty in software development is to utilize API to create functional backend services using web development framework like Java Spring and Django in Python.

Recent Blogs

PDF Morph: Macrosoft’s Latest Automation Tool
Read Blog
Analytics & RPA: The Transformative Digital Enabler
Read Blog
CallMiner Ingestion APIs
Read Blog
Introduction to CallMiner’s APIs
Read Blog
TOP