Detection and characterization of marine mammal calls by parametric modelling
Bibliographic record
Abstract
In this paper, we describe a parametric modeling method for detection and characterization o f tonal signals and its application to marine mammal calls.The method tracks dominant frequencies with an adaptive notch filter (ANF), and couples this to a novel, simultaneous detection step.The detection statistic is derived from a measure o f tracking reliability, obtained as a by-product o f the tracking algorithm.Detection therefore comes at little extra computational cost from an algorithm that is fast, simple, and capable of dealing with multiple signals in low signal-to-noise ratios.Frequency estimates are derived directly from the time domain waveform, avoiding the resolution trade-off and other short-comings o f the commonly used spectrogram.The performance of the algorithm is demonstrated on both simulated signals and recordings o f right whale calls.The method is found to be noise robust and capable o f extracting right whale and other calls with a low false alarm rate. s o m m a i r eLe prsent article dcrit une mthode de modlisation paramtrique pour la dtection et la caractrisation des vocalisations tonales de mammifres marins.La mthode consiste poursuivre les frquences dominantes l'aide d'un filtre encoche adaptatif (ANF), coupl une tape de dtection simultane innovatrice.La statistique de dtection est drive d 'une mesure de la fiabilit de poursuite, un sousproduit de l 'algorithme de poursuite.La dtection entrane un cot computationnel additionnel minime, et est la fois rapide, simple, et capable de traiter des signaux multiples et de bas rapports signal sur bruit.Les estimations de frquence sont drives directement du domaine temporel et frquentiel, vitant ainsi les compromis de rsolution de la technique spectrogramme utilise frquemment.Dans une application sur un fichier d 'une dure de 18-min de l'ensemble de donne de l'atelier, il est possible de dtecter quatre vocalisations probables de baleines franches.
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 | 0.000 | 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 | 0.000 |
| 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".