Structured Representation of Harmony for Music Retrieval
Bibliographic record
Abstract
Harmony is one of the main property of the Western music. Structured systems based on this property are generally dedicated to music analysis. For music retrieval purposes, we propose to consider the harmony of a musical piece as an ordered tree. Five levels are considered, from notes to the main tonality. Each level is relevant for music comparison purpose. This tree structured representation takes into account all these levels and all the links between them. The consideration of such a tree structure, instead of a list of sequences, requires techniques for tree comparison. An editing algorithm allowing the comparison between two trees has been implemented. Preliminary experiments considering only two levels of the tree have been performed. The first results are promising: our structured representation succeeds on some retrieval of pieces where systems only considering note or chord sequences fail. Such results show the interest of taking into account more than one level for comparison purposes based on harmony, whereas, to our knowledge, all the existing retrieval systems consider only one level. Furthermore, we work on the analysis methods that can provide the parameters of the harmony tree from a musical piece. Preliminary experiments indicate that the consideration of the information on a level improves the analysis of the father level.
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 | 0.000 | 0.001 |
| Meta-epidemiology (narrow) | 0.000 | 0.000 |
| Meta-epidemiology (broad) | 0.001 | 0.000 |
| Bibliometrics | 0.001 | 0.002 |
| Science and technology studies | 0.000 | 0.000 |
| Scholarly communication | 0.001 | 0.002 |
| Open science | 0.001 | 0.001 |
| Research integrity | 0.001 | 0.001 |
| Insufficient payload (model declined to judge) | 0.011 | 0.004 |
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".