HPCC Summer Internship Program 2019
Machine Learning and the Forensic Applications of Audio Classification:
An exploration of the forensic applications of sound classification using Artificial Neural Networks
This blog will follow the HPCC Summer Internship 2019 project Machine Learning and the Forensic Applications of Audio Classification through its three month development process.
The projects aims to use Neural Nets and HPCC Systems to help create a program that can take a sound recording as an input and then output the dimensions or attributes of the room it was recorded in.
Check in here for weekly updates and other information on this project.
Muiredach O’Riain week: 1Starting: 1st July 2019 – 1/7/19 My main plan for this week was deciding Deciding Upon and Defining the Relevant Features to ClassifyFinding relevant Impulse ResponsesFinding a series of clean sounds to be convolved as a basis for the training data The problem of finding suitable Impulse Responses solved thanks to the… Read more
Blog Post 8 Optimizing the NN This week I began testing different configurations of Neural Nets with tensorboard to find out which gave the most promising results. Previously , when I was training on the raw wav data, I found the best results with models that included 1 or more 1D Convolutional layers. Interestingly, when… Read more
Blog Post 7 Data Issues: This week came with a couple of setbacks and some pretty cool break throughs. At the end of last week I had a pretty robust model that could acuratley classify a sound file on weather it had been recorded in one of two rooms. After this I decided to up… Read more
Follow My Blog
Get new content delivered directly to your inbox.