Architecture Overview - AI Powered Speech Analytics for Amazon Connect

Architecture Overview

Deploying this solution builds the following environment in the AWS Cloud.


        AI Powered Speech Analytics for Amazon Connect architecture on AWS

Figure 1: AI Powered Speech Analytics for Amazon Connect architecture on AWS

The AI Powered Speech Analytics for Amazon Connect solution extends your existing Amazon Connect environment by using the included AWS CloudFormation template to deploy the AWS services necessary to transcribe, translate, and analyze customer interactions. When a customer calls into your Amazon Connect call center, their call progresses through a contact flow, customer audio is streamed in real time through Amazon Kinesis Video Streams. An AWS Lambda function consumes the audio stream and uses Amazon Transcribe to convert the audio into text. The Lambda function then stores the transcript segments and contact ID into an Amazon DynamoDB table.

Once the call is routed to the agent, an agent desktop user interface (UI) establishes a WebSocket connection to an Amazon API Gateway. The customer audio transcript is made available in real time to the agent desktop. Additionally, the solution leverages Amazon Translate and Amazon Comprehend to allow agents to get translated and annotated transcripts so they can quickly find the relevant information and perform recommended actions. Contact center supervisors can mine the contact trace records for additional insights to improve the overall customer experience. The captured transcripts will be uploaded to the solution-created Amazon Simple Storage Service (Amazon S3) bucket, with the Amazon S3 location added as an attribute to the Amazon Connect contact trace record.