Definition of the Antarctic and Pygmy blue whale call templates. Application to fast automatic detection
Why this work is in the frame
A frame that forgets how it found something cannot be audited. These are the routes that admitted this work.
Bibliographic record
Abstract
This paper deals with the automatic detection of low-frequency Antarctic (Balaenptera musculus interme dia) and Pygmy (B. m. brevicauda) blue whale sounds produced in the Southwestern Indian Ocean.A new detection method based on a matched filter is introduced.Four original match templates are presented and tested against original blue whale subspecies calls.The mathematical formulas of these templates, defined by Gaussian curve models, are provided.The detection threshold is based on the correlation coefficients.The threshold was set to reduce false detections obtained on simulated signals at various signal-to-noise ratios.We focus our work on the true detections of whale calls.Moreover, to obtain a real-time system, we decrease the computational time by decimating the recorded signal (Fs=250Hz).We show that this new method enables us to effectively detect both subspecies in various ambient noises, in the Southern Ocean. RESUMEDans ce papier, les sons de basses frquences mis par les baleines bleues Antarctique (Balaenoptera muscu lus intermedia) et pygmes (B.m. brevicauda) dans le secteur sud -ouest de l 'Ocan Indien ont t dtect au tomatiquement partir d 'une technique de filtrage adapt.Pour ce faire, des signaux synthtiques ont t crs partir de signaux originaux en modlisant leurs quations mathmatiques partir de courbes gaussiennes.La dtection se fait alors par la corrlation entre le signal entrant et le modle calcul (template).Le seuil de dtection a t choisi au pralable en simulant une srie de signaux dans des rapports signal sur bruit diffrents.Au final, un seuil de dtection lev a t choisi pour minimiser les fausses alarmes au risque d 'augmenter les dtections manques.Pour diminuer le temps de calcul, le signal original (Fe=250Hz) a t dcim.Cette mthode originale c 'est rvle trs efficace pour dtecter les sons mis par ces deux sous espces de baleines bleues dans des niveaux de bruit ambiant trs varis comme c 'est le cas dans cette partie de l'Ocan Indien.
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.
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 | 0.000 | 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 | 0.000 |
| Scholarly communication | 0.000 | 0.000 |
| Open science | 0.000 | 0.001 |
| 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 it