No Jitter is part of the Informa Tech Division of Informa PLC

This site is operated by a business or businesses owned by Informa PLC and all copyright resides with them. Informa PLC's registered office is 5 Howick Place, London SW1P 1WG. Registered in England and Wales. Number 8860726.

Amazon Chime SDK Simplifies ML with call analytics feature

Amazon Web Services (AWS) has announced new call analytics features for Amazon Chime SDK, designed to help businesses extract valuable insights from their call data using machine learning (ML). The new features, which include real-time transcription, call categorization, post-call summary, speaker search, and tone-based sentiment analysis, will allow businesses to improve customer satisfaction, enhance staff training, and ensure regulatory compliance with greater speed and efficiency.

One of the primary benefits of the new call analytics features is the significant reduction in deployment time for ML-based call analytics solutions. Previously, implementing these solutions could take months, but with the new features, businesses can deploy them in just a few days. This means that businesses of all sizes can now leverage the power of ML to extract insights from their call data in a more timely and cost-effective manner.

The new call analytics features come with pre-built integrations with Amazon Transcribe and Amazon Transcribe Call Analytics, allowing business users to easily stream call audio from Chime SDK Voice Connector to AWS ML services with just a few clicks. Additionally, insights can be consumed in real-time or after the completion of a call, and users have the option to use pre-built dashboards in Amazon QuickSight or any data visualization tool of choice.

Voice tone analysis is one of the most notable additions to the new call analytics features. Voice tone analysis uses machine learning to extract sentiment from a speech signal based on a joint analysis of linguistic information (what was said) as well as tonal information (how it was said). This tool is helpful for businesses that want to analyze customer sentiment around their products, services, or experiences, and can help them improve customer experience and retention rates.

Another key feature is speaker search, which helps match speakers to an existing database. This real-time voice insight tool leverages machine learning to take a short voice sample from the call audio and returns a set of closest potential matches from a database of known voices. However, the decision to match the current speaker with a known speaker from an organization is up to your application. 

The new call analytics features from Amazon Chime SDK also allow businesses to create and manage call recordings in the cloud for regulatory compliance and analytics purposes. They can also configure real-time alerts triggered by events such as poor caller sentiment or specific words spoken during the call. Furthermore, businesses can obtain machine learning-powered insights and call metadata merged into a queryable and searchable data lake, providing them with a wealth of data to analyze and leverage in future decision-making processes.

IPC, a leading provider of secure, compliant communications and multi-cloud connectivity solutions for the global financial markets, will use Amazon Chime SDK to transcribe and record trader calls for compliance. “In our industry, transcribing and recording trader calls is required for regulatory compliance. With all that recorded call data, machine learning is ideal to monitor calls for compliance and acquire better insights about the trades that are occurring,” said Tim Carmody, CTO of IPC. 

The new call analytics features have applications across a wide range of industries, including wealth management, mortgage advisory, financial trading, collections, and remote product troubleshooting. For example, wealth management advisors can use these features to increase their productivity by extracting insights from their calls, while remote troubleshooting teams can use them to identify product issues more quickly and efficiently.

Call analytics has also proven its ability to reduce deployment time for customers. According to Carmody, “Working with AWS, IPC was able to execute this quickly: where 12 months prior it would have taken over a week to implement a machine-learning-powered solution like this, Amazon Chime SDK’s media analytics was deployed in just a couple days.”

Overall, the new call analytics features from Amazon Chime SDK offer businesses a powerful solution to extract insights from their call data using machine learning. By reducing the deployment time for ML-based call analytics solutions, Amazon continues to make it easier for businesses to leverage the power of ML to improve customer experience, increase productivity, and reduce compliance costs. 

To learn more, visit the Amazon Chime SDK on AWS.