Gender Classification From Audio Clips

Posted on March 31, 2023  •  1 minutes  • 76 words

🔎 Project Overview

This project was done as a part of CSE 472: Machine Learning sessional offered by Dept of CSE, BUET. In this project, we used a large audio dataset to train machine learning models to identify gender of a person from their voice recording clips. The project uses an image representation of the audio (Mel Spectrogram & MFCC) instead of raw audio.

💻 Tech Stack

Tensorflow, Resnet50, Pandas

📄 Source Code

GitHub Repo: https://github.com/fazledyn/gender-classification-from-audio-clips