What does this AWS Solutions Implementation do?
The AI Powered Speech Analytics for Amazon Connect solution provides customer insights in real time, and helps agents and supervisors better understand and respond to customer needs so they can resolve customer issues and improve the overall customer experience. The solution includes pre-trained AWS artificial intelligence (AI) services that enable customers to transcribe, translate, and analyze each customer interaction in Amazon Connect, and presents this information to assist contact center agents during their conversations.
The solution combines Amazon Transcribe to perform real-time speech recognition and create a high-quality text transcription of each call into text; Amazon Comprehend to analyze the interaction, detect the sentiment of the caller, and identify keywords and phrases in the conversation; and Amazon Translate to translate the conversation into an agent’s preferred language. You can use the transcribed information with your knowledge management and customer relationship management (CRM) systems to suggest responses or recommended solutions to better respond to the caller's needs.
AWS Solutions Implementation overview
AWS offers a solution that provides the combination of speech-to-text transcription, multi-language translation, and insights for agents and supervisors all in real time. The diagram below presents the architecture you can automatically deploy using the solution's implementation guide and accompanying AWS CloudFormation template.

AI Powered Speech Analytics for Amazon Connect architecture
This 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 in 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.
AI Powered Speech Analytics for Amazon Connect
Version 1.0.2
Last updated: 03/2020
Author: AWS
Estimated deployment time: 20 min
Note: To subscribe to RSS updates, you must have an RSS plug-in enabled for the browser you are using.
Features
Speech to text translation
Entity detection and keyword spotting
Pre-trained AI services
Native-language call transcriptions
API to share insights

Browse our library of AWS Solutions Implementations to get answers to common architectural problems.

Find AWS certified consulting and technology partners to help you get started.

Browse our portfolio of Consulting Offers to get AWS-vetted help with solution deployment.