Automatic computational models of acoustical category features: Talking versus singing
Bibliographic record
Abstract
The automatic discrimination between acoustical categories has been an increasingly interesting problem in the fields of computer listening, multimedia databases, and music information retrieval. A system is presented which automatically generates classification models, given a set of destination classes and a set of a priori labeled acoustic events. Computational models are created using comparative probability density estimations. For the specific example presented, the destination classes are talking and singing. Individual feature models are evaluated using two measures: The Kologorov–Smirnov distance measures feature separation, and accuracy is measured using absolute and relative metrics. The system automatically segments the event set into a user-defined number (n) of development subsets, and runs a development cycle for each set, generating n separate systems, each of which is evaluated using the above metrics to improve overall system accuracy and to reduce inherent data skew from any one development subset. Multiple features for the same acoustical categories are then compared for underlying feature overlap using cross-correlation. Advantages of automated computational models include improved system development and testing, shortened development cycle, and automation of common system evaluation tasks. Numerical results are presented relating to the talking/singing classification problem.
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 distilled prediction
Teacher imitationNot calibrated prevalence, not ground truth. Human validation pending. Learned from the 10,348 direct Codex labels and 10,348 direct Gemma labels. Candidate is the union of thresholded teacher heads; consensus is their intersection. These outputs are machine_predicted_unvalidated and are not human labels or direct frontier model labels.
Codex and Gemma teacher scores by category
| Category | Codex | Gemma |
|---|---|---|
| Metaresearch | 0.001 | 0.000 |
| 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 | 0.000 | 0.000 |
| Open science | 0.001 | 0.000 |
| Research integrity | 0.000 | 0.000 |
| Insufficient payload (model declined to judge) | 0.000 | 0.000 |
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 teacher head, 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".