Emotion Recognition from Audio (ERA)

Project Overview

Emotion Recognition from Audio (ERA) is an innovative project that classifies human emotions from speech using advanced machine learning techniques. The frontend is built with Next.js, and the backend uses Flask. The project leverages datasets such as RAVDESS, CREMA-D, TESS, and SAVEE to train an Artificial Neural Network to detect and classify various emotional states from audio inputs.

Technologies Used

• Frontend: Next.js
• Backend: Flask
• Machine Learning: Various Python libraries for data processing and neural network implementation

Getting Started

Prerequisites

• Node.js
• npm (Node Package Manager)
• Python
• pip (Python Package Manager)

Backend Setup (Flask)

1. Navigate to the backend directory:

cd backend

2. Install the required Python packages:

pip install flask flask_cors tensorflow pickle numpy librosa

3. Start the Flask server:

python main.py

Setting up the Frontend (Next.js)

1. Navigate to the frontend directory:

cd frontend

2. Install the necessary npm packages:

npm install

3. Start the Next.js development server:

npm run dev