A comparison of automated methods for the analysis of style in fifteenth-century song intabulations
Bibliographic record
Abstract
Background in historical musicology A repertory of several thousand secular songs survives from the fifteenth century. Much of it is not attributed to any particular author, and frequently, even the approximate place of origin is uncertain. For us, the origin of a piece is a concern, so that we can better chart the development of musical style. Researchers have tried many approaches to attribution, or to style-classification in a broader sense: manuscript studies of all descriptions, studies of structural elements such as cadence degrees, ornamental style, elements of melodic behaviour such as contour, favoured intervals, and prevalence of leaps; dissonance treatment, and others. However, a comprehensive analysis of all these elements in a sufficiently large body of pieces is too time-consuming for one person to do by hand. Background in music information retrieval Information technology has made it possible to analyze large amounts of data in a reduced timespan, as compared to traditional methods. While this capability has been available for some time, the analysis of multiple musical works by computer is still relatively unexplored in music theory. Modern classification techniques require the extraction of features from sets of data, which are then resolved using higher level constructions. Aims To detail an approach and toolset for feature-set-based analysis of musical works of the fifteenth century as applied to the Buxheim Organ Book, to show some initial results, and to suggest further avenues for musicological exploration of the Buxheim Organ Book and related repertoire. Main contribution Several hundred intabulations of secular songs from the Buxheim Organ Book (ca. 1450–1470) have been analysed to produce individual sets of approximately fifty features using the Humdrum toolkit, as well as specially-constructed software tools. Some of these were general statistical features and others were features commonly examined in style studies of the mid-fifteenth-century secular song repertoire. This paper focuses on details of the initial tools developed for this project, some overall properties of the entire Buxheim set, and their relationship to previous music-theoretical work on the subject. Implications While some researchers have developed useful automated tools for musical analysis, these have rarely been combined with detailed musicological study of earlier repertories. Applying multiple automated tests to a single body of music gives musicologists an opportunity to compare the effectiveness and usefulness of such tools for specific tasks. Solutions specific to the analysis of the chosen repertory have been proposed, and the large-scale results will allow us re-evaluate existing musicological ideas about these pieces.
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 | 0.006 | 0.014 |
| Meta-epidemiology (narrow) | 0.002 | 0.000 |
| Meta-epidemiology (broad) | 0.002 | 0.002 |
| Bibliometrics | 0.008 | 0.005 |
| Science and technology studies | 0.001 | 0.001 |
| Scholarly communication | 0.003 | 0.002 |
| Open science | 0.002 | 0.002 |
| Research integrity | 0.002 | 0.001 |
| Insufficient payload (model declined to judge) | 0.006 | 0.003 |
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".