The abstract of report.pdf describes the project: In this project, a combined dataset comprising data from six individual speech emotion recognition datasets is constructed. After pre-processing steps ...

This project implements a Speech Emotion Recognition (SER) system using LSTM neural networks. The system analyzes audio recordings to classify emotional states such as anger, joy, sadness, and more.

The automatic speech recognition (ASR ... If it gives you some ideas, head over to the project’s GitHub repository and get hackin’!