Deployment

• 🌐 The frontend is hosted on AWS Amplify, while the backend is deployed on AWS EC2 Instance.
• 🛠 Status: Website is under maintence. Switching to different speech analysis API due to high cost.
• </> Source Code: GitHub Repository

Project Overview

• 🚀Objective: Develop a web app to help users improve their English pronunciation.
• 🎤 Functionality: Allows users to record their pronunciation of English words, providing real-time feedback on each syllable if pronounced incorrectly.

Short Demo

Technology Stack

• 💻 Developed the frontend using React, hosted on AWS Amplify. Implemented best coding practices for scalability and maintainability.
• 📱 Implemented responsive design for various devices, from mobile to desktop screens.
• 🐍 Utilized Django for backend development, hosted on AWS EC2 instance.

Integration of APIs

• 🖨 Leveraged the Google Text to Speech API for seamless text-to-speech functionality.
• 🎙 Implemented React speech recognition to facilitate voice input.
• 🌍 Employed Microsoft Azure Speech Analysis to conduct in-depth evaluations of pronunciation.
• 🌍 Integrated openAI API for providing real-time feedback based on the results of Azure Speech Analysis.

Enhancements Planned

• 💡 Introduction of a new feature enabling users to practice pronunciation for phrases and sentences.
• 📊 Development of an assessment page designed to evaluate users' English pronunciation proficiency.
• 🤖 Integration of an AI chatbot to facilitate real-life scenario-based language practice.