Research
Academic research in music technology
Music Technology Thesis
Applying multi-modal large language models to music analysis, exploring the intersection of AI and creative expression. Gemini and Qwen models are used for music information retrieval tasks and compared with state-of-the-art techniques.
Capstone Project
Polyphonic Wavetable Synthesizer with per-voie, per-source processing. See the Programming page for more.
WaveVerb
Feedback delay network reverb plugin with karplus-strong string synthesis. The delay lines feed into each other to create a complex and tonal reverb effect.
FireFader
Force-feedback musical interface using motorized faders. Project started previously, worked to improve firmware, rebuild hardware, and design physically-inspired interaction in Max/MSP
Temporal Convolutional Network Training
Design and training of TCN networks for real-time audio style transfer. Trained multiple models which can be used in any DAW using Morpho by Neutone.
Audio and Video Analysis
Extraction of audio and video features for analysis of infant-directed singing. Research conducted with Dr. Shannon de l’Etoile, Dr. Soyoen Ahn, and Cameron Riopelle. Presented at the 2025 International Conference of Music Perception and Cognition (ICMPC)