Automated categorization of bioacoustic signals: Avoiding perceptual pitfalls
Bibliographic record
Abstract
Dividing a species acoustic repertoire into biologically relevant categories presents a widespread problem in the study of animal sound communication. Such categorization is fundamental to any attempt to compare repertoires between contexts, individuals, populations or species. Automated procedures allow rapid, repeatable and objective categorization, however, in the past they have often performed poorly at detecting biologically meaningful sound classes. Arguably this is because automated methods have often failed to address the nonlinearities of animal sound perception and a method that incorporates dynamic time warping and an adaptive resonance theory (ART) neural network to avoid some of the problems is presented here. The method was tested on 104 randomly chosen whistles recorded from four captive bottlenose dolphins (Tursiops truncatus). This data set includes known biologically meaningful categories in the form of 42 distinctive stereotyped whistles produced when each individual was kept in isolation. The automated procedure correctly grouped all but two of the stereotyped whistles into their respective categories, and thus performed as good as human observers. However, compared to humans, the automated system provided finer categorization of the remaining non-stereotyped whistles. These results suggest that this methodology provides a repeatable and objective means of splitting bioacoustic signals into biologically meaningful categories.
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 | 0.002 | 0.008 |
| Meta-epidemiology (narrow) | 0.001 | 0.000 |
| Meta-epidemiology (broad) | 0.001 | 0.000 |
| Bibliometrics | 0.001 | 0.001 |
| Science and technology studies | 0.001 | 0.001 |
| Scholarly communication | 0.002 | 0.002 |
| Open science | 0.001 | 0.001 |
| Research integrity | 0.001 | 0.001 |
| Insufficient payload (model declined to judge) | 0.002 | 0.001 |
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".