AI Powered Speech Analytics for Amazon Connect

AI Powered Speech Analytics for Amazon Connect provides customer insights in real time, helping contact center agents focus on the caller, track customer sentiment, and use transcribed information to suggest responses or recommended solutions to resolve issues more effectively.

Pre-trained AWS artificial intelligence (AI) services help you to transcribe, translate, and analyze each customer interaction in Amazon Connect. This customer information can be used in conjunction with your knowledge management (KM) and customer relationship management (CRM) systems to respond more directly to the customer’s needs.

Benefits

Speech-to-text translation

Real-time speech-to-text translation improves customer engagement by keeping agents focused on customer interactions rather than tasks such as note-taking.

Entity detection and keyword spotting

AI powered entity detection to find references to people, places, and organizations, and keyword spotting.

Pre-trained AI services

AI Powered Speech Analytics for Amazon Connect uses pre-trained AI models, eliminating the need to manually train models.

Native-language call transcriptions

Agents receive real-time call transcriptions in their preferred language to better understand and respond to customer requests.

API to share insights

When insights are used with your knowledge management and CRM systems, agents are provided actionable recommendations in real time.

Overview

The flow diagram below presents the architecture you can build using the example code on GitHub.

Click to enlarge

AI Powered Speech Analytics for Amazon Connect architecture

AI Powered Speech Analytics for Amazon Connect extends your existing Amazon Connect environment by deploying 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. In the contact flow, the Start media streaming contact block captures customer audio. Then the Invoke AWS Lambda function contact block activates the invocation AWS Lambda function. As the call runs, the customer audio is streamed in real time to Amazon Kinesis Video Streams.
The transcription Lambda function consumes the audio stream and uses Amazon Transcribe to convert the audio into text.
The transcription Lambda function then stores the transcript segments and contact ID in an Amazon DynamoDB table. After the call ends, 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. Contact center supervisors can mine the contact trace records for additional insights to improve the overall customer experience.
When the call is routed to an agent, the agent’s call center application establishes a WebSocket connection to an Amazon API Gateway.
The customer audio transcript is provided in real time to the agent. Additionally, Amazon Translate and Amazon Comprehend can provide translated and annotated transcripts, allowing the agent to efficiently find relevant information and perform recommended actions.