MERIDIAN open-source software for deep learning-based acoustic data analysis
Bibliographic record
Abstract
Deep neural networks have the potential to transform our approach to developing acoustic detection and classification models, enabling acousticians to develop or re-purpose such models through a fully data-driven approach requiring minimal knowledge of signal processing, algorithm design, and programming. However, open-source software to facilitate this data-driven workflow is currently lacking. MERIDIAN is working towards filling this gap through the development of several open-source software products, including the Python package Ketos and the MAIPL (Marine AI PLatform) suite of web applications. While Ketos provides a high-level programming interface for training deep neural networks at detecting and classifying sounds, MAIPL is a modular cloud computing service that supports the full model-development workflow. In this contribution, an overview of Ketos and MAIPL will be given and their functionalities will be demonstrated through their application to the HALLO (Humans and ALgorithms Listening for Orcas) project. We highlight one of the MAIPL tools, the MAIPL-Annotator, which provides a user-friendly interface for collaboratively annotating sound samples and validating model predictions. Future developments will also be described, highlighting new MAIPL applications under development such as the MAIPL-Adapter, a tool for adapting acoustic deep learning models to new acoustic environments.
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 | 0.002 | 0.004 |
| Meta-epidemiology (narrow) | 0.002 | 0.001 |
| Meta-epidemiology (broad) | 0.001 | 0.002 |
| Bibliometrics | 0.001 | 0.001 |
| Science and technology studies | 0.000 | 0.001 |
| Scholarly communication | 0.002 | 0.002 |
| Open science | 0.003 | 0.003 |
| Research integrity | 0.001 | 0.003 |
| Insufficient payload (model declined to judge) | 0.054 | 0.026 |
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".