I like to keep things fun. I hope this format gives a good impression of my personality.
Please enjoy!
-Ian Coleman
I am a graduate student at Boston University pursuing a Master’s in Engineering in Electrical and Computer Engineering.
My primary interests are in machine learning, artificial intelligence, statistics, signal processing, and software engineering. I enjoy making numbers have meaning and have interest in both statistical analysis of data and quality analysis of data or capture methods.
Most recent project: Transformer Based Text-To-Speech Model
To hone my skills and to familariize myself more with audio signal processing, I created a toy implementation of a transformer based text-to-speech model using the LJSpeech dataset. I aim to write blog posts explaining how the model works as well as update GitHub with the code. For now, please enjoy these pieces of the project without much explanation.
Original Audio
[reconstructed from the spectrogram using the Griffin-Lim algorithm]
Predicted audio from custom toy model
[also reconstructed using the Griffin-Lim algorithm
Just for fun