Testing a new tool for alignment of musical recordings
Bibliographic record
Abstract
Audio-to-audio alignment of musical recordings is the mapping of events in one recording to their corresponding events in other recordings of the same underlying musical piece.Among other applications, musical audio-to-audio alignment is used for: comparing and analyzing musical performances; finding different performances and arrangements of a musical work in a database; discovering musical motifs in field recordings of folk music; automatically synchronizing multiple takes (rerecordings of specific excerpts) in a recording studio; and aligning a musician's performance to a score in realtime, for purposes of interactive performance such as automated accompaniment.This thesis investigates audio-to-audio alignment by an algorithm that has not previously been applied to music, the continuous profile model (Cpm) (Listgarten et al. 2005).In this thesis, the Cpm is used to align pairs of recordings (pairwise alignment) as well as groups containing more than two recordings (multiple alignment).A standard evaluation methodology is used to systematically compare pairwise alignment by the Cpm to pairwise alignment by dynamic time warping (Dtw), the algorithm most frequently used for audio-to-audio alignment of music.The evaluation methodology is then generalized to multiple dimensions in order to compare two approaches to multiple alignment: simultaneous multiple alignment with the Cpm and iterative pairwise alignment with Dtw.This project would not have reached completion without the time, energy, and support of a number of people and organizations:Many thanks are due my advisor, Professor Ichiro Fujinaga, without whom this project would not have been possible.
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 | 0.007 | 0.050 |
| Meta-epidemiology (narrow) | 0.002 | 0.001 |
| Meta-epidemiology (broad) | 0.001 | 0.001 |
| Bibliometrics | 0.003 | 0.002 |
| Science and technology studies | 0.001 | 0.001 |
| Scholarly communication | 0.003 | 0.005 |
| Open science | 0.003 | 0.004 |
| Research integrity | 0.002 | 0.002 |
| Insufficient payload (model declined to judge) | 0.012 | 0.005 |
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".