Deploying ASR system for scalability and robustness on AWS

Abstract

The project aims to provide a robust solution for deploying automatic speech recognition (ASR) system on Cloud. The solutions will enable the system to be provisioned at a lower cost and also simplify the process of deploying systems on Amazon Web Service(AWS). The solutions are implemented based on the concept of Infrastructure as Code (IaC). This enables the process of building and destroying speech recognition system to be completed in minimum steps which come in convenient at the development stage. This report will introduce the solutions in terms of the architecture diagram, comparison over different services, frameworks, and tools. The report will demonstrate the provision of the infrastructure of ASR on AWS using Terraform.