To Redact or Not to Redact? How is the Question!

By Mingren Xiang

Automated Redaction of Audio and Transcripts for Compliance, Training and CX Awareness

Many regulatory standards require organizations to capture recordings. In addition, companies benefit greatly from capturing the Voice-of-the-Customer. This allows them to analyze information and adjust how responses and work with customers delivering a more efficient and positive customer experience.

Why Redact?

There is Risk associated with the capturing of sensitive customer data. Once you capture information, it becomes your responsibility. You are immediately in charge of security, ensuring compliance and are on the hook for all the associated costs and risks.

A recent survey of contact center agents for a large enterprise bank found that more than 55% of agents confirmed that customers share credit or debit card information with them over the phone. It doesn’t take long to consider how many financial institutions issue credit and debit cards and how many agents they employ to realize just how big the potential for a problem are.

Macrosoft’s CallMiner Services

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

What is Automated Redaction?

Automated Redaction leverages speech recognition to find and remove sensitive numeric data in customer calls. It can be applied to real-time, post-call and other audio utterances to safely review and share recorded audio and transcripts for customer experience insight, agent training and compliance. Automated redaction supports PCI/PII compliance while removing the threat of over/under redaction commonly encountered with agent pause and resume recording errors.

Introducing CallMiner Eureka Redact

CallMiner Eureka Redact is a cloud-based compliance solution that applies machine-learning and human curated algorithms to identify and remove sensitive numerical PCI, PII and for some GDPR elements from call transcripts and audio recordings ensuring PCI compliance, risk mitigation, and secure insight.

The ability to safely share audio and transcription data for agent coaching, customer experience analysis and compliance is enabled by eliminating credit card data, social security numbers and more from voice and multichannel interactions. Advantages of the Eureka Redact Modules includes:

  • Precise – Sophisticated redaction algorithms accurately identify and remove potentially sensitive PCI/ PII numeric data.
  • Flexible – Support for non-sensitive number exclusions (e.g. dollar values, phone numbers, dates, etc.), real-time/post-call source audio and multiple languages.
  • Protected – Eliminates sensitive numerical data in real-time and in recordings and transcriptions to mitigate internal and external security risks

Key Benefits of Redaction Technology

There are many benefits to implementing redaction technology in your operations. Here are a few bound to get the attention of your compliance, risk and security teams.

  • Identify and remove sensitive numeric data with sophisticated redaction algorithms without customer or agent impact
  • Reduce legal exposure and compliance risk through automated redaction for both post-contact and real-time interactions
  • Adapt to evolving call volumes and metadata with scalable, cloud-based platform

Macrosoft’s CallMiner Services

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

Share this:

By Mingren Xiang | March 25th, 2020 | CallMiner

About the Author

Mingren Xiang

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

Power Automate AI Builder and Scenarios
Read Blog
Dazzle 3.0 Pre-Launch : Custom-built .NET Framework for Legacy Conversion
Read Blog
Speech to Text Quality Assessment and Analysis: Part 2
Read Blog
Cypress Web Automation: It’s Expanding Role in Macrosoft’s Web App Development Projects
Read Blog