Detecting Bat Calls: An Analysis of Automated Methods
Bibliographic record
Abstract
Long-term and large-scale acoustic surveys of bats have become possible with the increased availability of recording hardware and advances in battery and memory storage technologies. The volume of data generated in surveys necessitates automated call detection, either in real time via a triggering function or offline, yet researchers are hesitant to replace traditional hand analysis without a thorough understanding of the accuracy and costs of automated detection. We compared detection accuracy and computational cost of the underlying algorithms used in commercial detectors (a zero-crossing detector, a spectral peak detector, and a high-band energy detector) with a model-based analysis method called the links detector. We predicted that the links detector would be more accurate than the other detectors, producing a larger effective detection range, because the links detector uses more information to make detection decisions. We also predicted that the links detector would be the most computationally expensive algorithm because of the processing needed for the extra information. We quantified the performance of the detectors using a synthetic recording environment, which provided an absolute ground truth for the experiments and allowed us to measure the effective detection range of each algorithm. The zero-crossing and high-band energy detectors, the fastest, were about 40 times faster than the links detector. Most of the computational cost was attributed to the filter used to remove low-frequency noise. The links detector, the most accurate, increased effective detection range by 6–12 m compared to the other detectors depending on species. The results will allow bat researchers to better understand the costs and benefits of automated detection methods.
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 | 0.001 |
| Science and technology studies | 0.000 | 0.000 |
| Scholarly communication | 0.000 | 0.000 |
| Open science | 0.000 | 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".