Use AI to understand customer conversations

Call centres, audio transcription and NLP

Published: Dec 2, 2019 by martoc

I attended this workshop today, I learnt that AWS provides a full stack of services that can help you to integrate your call centre calls or even create your own call centre and from the recording from these sources you can get real information about these conversations, Amazon Connect, Transcribe, Comprehend, Athena and QuickSight were some of the main services I used in this workshop.

In this example, I created the call centre using Amazon Connect, the following diagram shows the main components and how these interact with each other.

Architecture

From my point of view the transcription is the hack that allows us to use our current knowledge in NLP which is completely based on written text, I guess in the next year the processing will be direct from audio.

One nice feature that I wasn’t aware of is that QuickSight now support more datasource types, in this particular case it can read from S3 and show insights, these are the current dataset that it supports

QuickSight

Share

Latest Posts

Kafka Auth Handler Goes Multi-Cloud
Kafka Auth Handler Goes Multi-Cloud

Back in December 2024, I wrote about gcp-kafka-auth-handler, a utility I created to bridge the authentication gap between Apache Beam Dataflow and GCP Managed Kafka. Since then, the project has evolved significantly as part of our broader multi-cloud journey. Today, I’m pleased to announce that the library has been renamed to kafka-auth-handler and now supports both GCP and AWS MSK.

Building an Open Deployment Framework with GitHub Actions
Building an Open Deployment Framework with GitHub Actions

Managing CI/CD pipelines across multiple repositories can quickly become unwieldy. Each project needs versioning, container builds, deployments, and releases—often with subtle variations that lead to duplicated workflow code. This post introduces an open deployment framework built entirely on GitHub Actions, designed to bring consistency and reusability to cloud-native deployments.

GCP Managed Kafka Authentication Handler
GCP Managed Kafka Authentication Handler

When working with Google Cloud Platform’s Managed Service for Apache Kafka, you’ll quickly discover that authentication can be surprisingly challenging, especially when using Apache Beam Dataflow pipelines. In this post, I’ll share a utility I created called gcp-kafka-auth-handler that bridges this gap.