Back to search

Cal Poly

Neurosymbolic Counterpoint Generation

Abstract

dc:description.abstract

Recent advancements in generative artificial intelligence have revolutionized music generation, yet research has predominantly focused on raw audio synthesis over music in symbolic form, i.e. a score. This thesis presents the first neurosymbolic model designed to generate imitative Renaissance counterpoint in symbolic (MIDI) format. By leveraging an autoregressive Transformer architecture, this research explores the capacity of deep learning models to manage independent voices and strict stylistic constraints. We compare multiple data representation strategies with distinct tokenization methods. The proposed model incorporates a symbolic component that enforces fundamental contrapuntal rules. Additionally, this thesis contributes a preprocessed dataset of Renaissance polyphony, in order to facilitate future research in polyphonic music generation. Ultimately, this work demonstrates that flattened sequence models, when combined with appropriate tokenization and symbolic constraints, are capable of generating rich, multi-layered contrapuntal music.

Degree

thesis:*
Name thesis:degree_name
MS in Computer Science
Discipline thesis:degree_discipline
Computer Science

Author and committee

dc:creator, dc:contributor.*
Author dc:creator
  • Jarski, Paul D
Contributors dc:contributor
  • John Clements
  • Computer Science
  • College of Engineering

Subjects

dc:subject × 7

Identifiers

dc:identifier.*
Repository record dc:identifier
https://digitalcommons.calpoly.edu/theses/3244

Chain of custody

source
Harvested from
Cal Poly
Base URL
digitalcommons.calpoly.edu/do/oai/
Last updated
2026-11-19
Source record
OAI-PMH GetRecord
citation

Jarski, Paul D. Neurosymbolic Counterpoint Generation. https://digitalcommons.calpoly.edu/theses/3244