Enhancing marine mammal species classification: A feature fusion approach for whistle calls
Bibliographic record
Abstract
Whistles are transient, narrowband calls of marine mammals. This transience makes using whistles for species classification challenging. The literature uses spectral features to classify whistle calls across species (e.g., common dolphin within the dolphin genus). Spectral features are limited as they may not capture nuanced temporal (e.g., zero-crossing rates) information for species classification. Toward inter-species classification, separate classifiers for individual species demand considerable effort in data collection, annotation, model training, and computation resources. To address the gap in the spectral features’ representation and intra-species classification, a novel classification model—Temporal, Spectral, and Cepstral (TSC)—BiLSTM, was investigated. This model uses feature-level fusion strategy to integrate hybrid TSC features to capture rich and complementary whistle information not evident in temporal, spectral, or cepstral features alone. The BiLSTM network then learns these fused TSC whistle representations to classify calls from beluga, dolphins, narwhal, killer, and pilot whales. The results show the proposed TSC-BiLSTM model outperforms three baseline methods (e.g., ANN (F1-score = 64%), CNN (F1-score = 74%), and LSTM (F1-score = 84%), achieving 90% accuracy, 89% precision, 87% recall, and 88% F1-score. These findings suggest TSC-BiLSTM is a valuable tool to classify species based on passive acoustic marine mammal whistle measurements. JASCO Applied Sciences is a sponsor of this work.
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 | 0.001 | 0.001 |
| Meta-epidemiology (narrow) | 0.001 | 0.000 |
| Meta-epidemiology (broad) | 0.001 | 0.001 |
| Bibliometrics | 0.001 | 0.000 |
| Science and technology studies | 0.000 | 0.000 |
| Scholarly communication | 0.001 | 0.001 |
| Open science | 0.001 | 0.001 |
| Research integrity | 0.001 | 0.001 |
| Insufficient payload (model declined to judge) | 0.001 | 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".