A Real-Time Harmonically Responsive Algorithmic Melody Writing Assistant, Realised Using Procedural Programming with Interactive Control Parameters
Bibliographic record
Abstract
This thesis describes the development and realisation of a computer algorithm that generates musical melodies based on the harmonic information in a chord chart, inspired by the common practice of jazz soloing. The algorithm is based on a conceptual model of an improvising musician as a person who possesses knowledge of applicable rules of music theory, and who makes choices about how to implement those rules. This concept was developed into a two-tier algorithm architecture consisting of a processes tier and a choices tier, which was ultimately developed successfully into a melody writing assistant. The algorithm behind the melody writing assistant is realised using procedural programming techniques, resulting in a deterministic system in which every detail of every step is known and controlled. This study shows that the inherent rigidity and inflexibility typically resulting from such rule-based systems can be largely overcome through the application of carefully-selected control parameters which affect how the rules are applied at any given moment. The user is provided with real-time interactive controls to allow manipulation of these control parameters. The workings of the algorithm are disclosed in sufficient detail to allow the techniques and approaches to be borrowed, copied, or built upon by others. This study contributes a novel control scheme for tonality consisting of tonal baseline and tonal gradient controls. It also contributes an approach to generating a cohesive whole by implementing beat level as a common reference for separately-generated musical elements. As well as documenting the process and the result, this thesis covers some of the more important detours and dead ends that contributed to the development.
Fetched live from OpenAlex and de-inverted. Abstracts are not stored in this database: the inverted indexes are 8.6 GB of the frame’s 9.3 GB of text, and the host has 13 GB free.
How this classification was reachedexpand
Full frame machine prediction
Teacher imitationNot calibrated prevalence, not ground truth. Human validation pending. The Gemma side is a direct model label for every work in the frame, read from the title-only record. The Codex side is a classifier learned from the 10,348 direct Codex labels and calibrated to design-weighted sample rates; fields without enough sample support carry no Codex call. Candidate is the union of the two sides; consensus is their intersection. These outputs are machine_predicted_unvalidated and are not human labels.
Distilled classifier scores by category (both heads)
| Category | Codex | Gemma |
|---|---|---|
| Metaresearch | 0.001 | 0.002 |
| Meta-epidemiology (narrow) | 0.000 | 0.000 |
| Meta-epidemiology (broad) | 0.000 | 0.000 |
| Bibliometrics | 0.000 | 0.000 |
| Science and technology studies | 0.000 | 0.001 |
| Scholarly communication | 0.002 | 0.001 |
| Open science | 0.002 | 0.001 |
| Research integrity | 0.001 | 0.001 |
| Insufficient payload (model declined to judge) | 0.006 | 0.002 |
Machine scores (provisional)
The two teacher heads of the student model, read on this work. A score orders the frame for review; it never asserts a category, and the validation status ships verbatim with every row.
Baseline scores from an immature model (maturity gate not passed, 7 training rounds). Scores rank; they never assert a category.
score_only:v0-immature-baseline · verbatim from the scoring run: score_only means the number may rank works, and no category label ships from itClassification
machine, unvalidatedMachine predicted; a candidate call from one source (direct Gemma or distilled Codex), not a consensus.
How this classification was reached, model by model and score by score, is at the end of the page under "How this classification was reached".