ex5_ml

Speech Command Classification using PyTorch with CNN

This is a PyTorch implementation of speech command classification using Convolutional Neural Networks (CNNs). The model used in this implementation is based on the VGG architecture.

Requirements

• PyTorch
• NumPy

Dataset

The Google Speech Commands Dataset was used to train and evaluate the model. The dataset consists of 30 short (1 second) audio clips, each of which corresponds to a different word.

Usage and Results

See ex5_report.pdf

Author

This code was written by DeanZi as part of a university programming project. Feel free to use and modify it as you like.