Combining two user-friendly machine learning tools increases species detection from acoustic recordings
Bibliographic record
Abstract
Passive acoustic monitoring usually generates large datasets that require machine learning algorithms to scan sound files, although the complexity of developing machine learning algorithms can be a barrier. We assessed the ability and speed of two user-friendly machine learning tools, Kaleidoscope Pro and BirdNET, for detecting the American toad ( Anaxyrus americanus (Holbrook, 1836)) in sound recordings. We developed a two-step approach, combining both tools to maximize species detection while minimizing the time needed for output verification. When considered separately, Kaleidoscope Pro successfully detected the American toad in 85.9% of recordings in the validation dataset, while BirdNET detected the species in 58.4% of recordings. Combining the two tools in the two-step approach increased the detection rate to 93.3%. We applied the two-step approach to a large acoustic dataset ( n = 6194 recordings). We started by scanning the dataset using Kaleidoscope Pro (species detected in 417 recordings), then we used BirdNET on the remaining recordings without confirmed presence. The two-step approach reduced the scanning time, the time needed for output verification, and added 37 additional species detections in 45 min. Our findings highlight that combining machine learning tools can improve species detectability while minimizing time and effort.
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 | 0.019 |
| Meta-epidemiology (narrow) | 0.002 | 0.001 |
| Meta-epidemiology (broad) | 0.002 | 0.001 |
| Bibliometrics | 0.003 | 0.001 |
| Science and technology studies | 0.001 | 0.001 |
| Scholarly communication | 0.002 | 0.003 |
| Open science | 0.001 | 0.003 |
| Research integrity | 0.002 | 0.002 |
| Insufficient payload (model declined to judge) | 0.003 | 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".