Author ORCID Identifier

https://orcid.org/0009-0005-1808-4710

Date of Award

Spring 6-1-2025

Document Type

Thesis (Undergraduate)

Department

Computer Science

First Advisor

Michael Casey

Second Advisor

Nikhil Singh

Third Advisor

Tim Tregubov

Abstract

Effective practice remains one of the greatest challenges in music education, yet cur- rent digital music tools primarily support only passage engagement or surface-level feedback, failing to provide proactive guidance for overcoming technical challenges within piano repertoire. This thesis presents Coda, a digital system that generates custom piano practice exercises from symbolic music notation based on established piano pedagogy principles that have historically been taught orally.

Unlike existing tools that only provide a viewable symbolic music notation display or only an interface to take notes and record a practice session, Coda uses rule- based algorithmic transformations rooted in pedagogical logic to create musically valid variations of user-uploaded scores. The system implements four categories of practice exercises—Part Splitting, Tempo Shaping, Chordification, and Rhythmic Alteration (Dotted Rhythms)—through symbolic music information retrieval using a novel Music Matrix Representation (MMR) designed upon a three-level Score-Part- Voice hierarchy for scalable, object-oriented, and fast symbolic music generation.

This research applies the full software development lifecycle to present a web appli- cation designed for mobile and desktop usage, available at https://coda-app.onrender.com, successfully bridging the gap between music technology and pedagogical practice for intermediate pianists preparing for performances or competitions.

Download

Share

COinS