Deploying speech recognition system using high availability and scalability kubernetes cluster with kubernetes and docker

• Main Author: Wong, Seng Wee
• Other Authors: Chng Eng Siong
• Format: Final Year Project
• Language: English
• Published: Nanyang Technological University 2020
• Subjects: Engineering::Computer science and engineering::Software::Software engineering
• Online Access: https://hdl.handle.net/10356/137980
• Institution: Nanyang Technological University

This project aims to improve the scalability of the existing speech recognition system such that it can support dynamic increase in workload (phone calls) requesting for its service. This project aims to use containerisation technology such as Docker and container orchestration tool such as Kubernetes to orchestrate the use of resources in the cloud server to process the incoming speech-to-text decoding requests efficiently and effectively. The report will present the proposed architecture to increase the availability and scalability of the speech recognition system and detail its characteristics. In addition, the report will also discuss the use of a dashboard to present the metrics monitoring the health of the Kubernetes cluster supporting the speech recognition system. The cost and performance of the proposed system architecture will be evaluated against the objectives of this project.