A survey of published research, from the Essentia Memoria newsroom. It lists real papers, each looked up at its DOI registry; the game has not repeated their results.
Research survey
What AI research has found: whale culture and sound
Happened: · Published:
12 published works on whale culture and sound, each looked up at its DOI registry before it was listed here, with what each one reports in plain words.
Watch
Explanatory visualisation, drawn from the record's numbers. It is not footage of the event: nobody filmed it.
Listen
Transcript
News from the Essentia Memoria game universe. What AI research has found: whale culture and sound. 12 published works on whale culture and sound, each looked up at its DOI registry before it was listed here, with what each one reports in plain words. This survey lists what each paper reports. The game has not repeated these results. A search finds papers that match its words, so a listed paper may use AI only in part. The search is limited to the fifty most-cited matches, so the newest results may be missing until they are cited. This report was written from the world record by a fixed template. The full story and its source records are on essentiamemoria.com.
The question
What have machines learned from the songs and clicks of whales, and is there a culture in them?
Claims, and where each one comes from
- Where this research lives in the game (a place the world grammar builds)harbour → port
Game simulation · Set in code
src/lib/world-grammar/place-grammar.ts · resolvePurpose('harbour') - Published works in this survey, each resolved at its DOI registry12
Real-world knowledge · Source [1] [2] [3] [4] [5] [6] [7] [8] [9] [10] [11] [12]
- Neural networks detect sperm whale clicks and tell apart their codas, the rhythmic patterns families share.Bermant 2019
Real-world knowledge · Source [1]
- A network listened to years of underwater recordings and found humpback whale song in them.Allen 2021
Real-world knowledge · Source [2]
- A roadmap for recording, labelling and modelling sperm whale communication at a scale machine learning can learn from.Andreas 2022
Real-world knowledge · Source [3]
- Sperm whale codas vary with the conversation and are copied between whales, so they combine into far more signals than once thought.Sharma 2024
Real-world knowledge · Source [4]
- Beluga whale acoustic signal classification using deep learning neural network modelsZhong 2020
Real-world knowledge · Source [5]
- Automatic detection and classification of baleen whale social calls using convolutional neural networksRasmussen 2021
Real-world knowledge · Source [6]
- Detecting, classifying, and counting blue whale calls with Siamese neural networksZhong 2021
Real-world knowledge · Source [7]
- A machine learning pipeline for classification of cetacean echolocation clicks in large underwater acoustic datasetsFrasier 2021
Real-world knowledge · Source [8]
- North Atlantic Right Whale acoustic signal processing: Part I. comparison of machine learning recognition algorithmsDugan 2010
Real-world knowledge · Source [9]
- A multimodel deep learning algorithm to detect North Atlantic right whale up-callsIbrahim 2021
Real-world knowledge · Source [10]
- Whale counting in satellite and aerial images with deep learningGuirado 2019
Real-world knowledge · Source [11]
- The neural network classification of false killer whale (Pseudorca crassidens) vocalizationsMurray 1998
Real-world knowledge · Source [12]
References, checked at their registry
[1] Bermant (2019). Deep Machine Learning Techniques for the Detection and Classification of Sperm Whale Bioacoustics. Scientific Reports. doi:10.1038/s41598-019-48909-4
Verified: the work exists and matches · checked at Crossref on Oct 28, 2026, 11:21 PM UTC · the registry holds “Deep Machine Learning Techniques for the Detection and Classification of Sperm Whale Bioacoustics” (2019)
[2] Allen (2021). A Convolutional Neural Network for Automated Detection of Humpback Whale Song in a Diverse, Long-Term Passive Acoustic Dataset. Frontiers in Marine Science. doi:10.3389/fmars.2021.607321
Verified: the work exists and matches · checked at Crossref on Oct 28, 2026, 11:21 PM UTC · the registry holds “A Convolutional Neural Network for Automated Detection of Humpback Whale Song in a Diverse, Long-Term Passive Acoustic Dataset” (2021)
[3] Andreas (2022). Toward understanding the communication in sperm whales. iScience. doi:10.1016/j.isci.2022.104393
Verified: the work exists and matches · checked at Crossref on Oct 28, 2026, 11:21 PM UTC · the registry holds “Toward understanding the communication in sperm whales” (2022)
[4] Sharma (2024). Contextual and combinatorial structure in sperm whale vocalisations. Nature Communications. doi:10.1038/s41467-024-47221-8
Verified: the work exists and matches · checked at Crossref on Oct 28, 2026, 11:21 PM UTC · the registry holds “Contextual and combinatorial structure in sperm whale vocalisations” (2024)
[5] Zhong (2020). Beluga whale acoustic signal classification using deep learning neural network models. The Journal of the Acoustical Society of America. doi:10.1121/10.0000921
Verified: the work exists and matches · checked at Crossref on Oct 28, 2026, 11:21 PM UTC · the registry holds “Beluga whale acoustic signal classification using deep learning neural network models” (2020)
[6] Rasmussen (2021). Automatic detection and classification of baleen whale social calls using convolutional neural networks. The Journal of the Acoustical Society of America. doi:10.1121/10.0005047
Verified: the work exists and matches · checked at Crossref on Oct 28, 2026, 11:21 PM UTC · the registry holds “Automatic detection and classification of baleen whale social calls using convolutional neural networks” (2021)
[7] Zhong (2021). Detecting, classifying, and counting blue whale calls with Siamese neural networks. The Journal of the Acoustical Society of America. doi:10.1121/10.0004828
Verified: the work exists and matches · checked at Crossref on Oct 28, 2026, 11:21 PM UTC · the registry holds “Detecting, classifying, and counting blue whale calls with Siamese neural networks” (2021)
[8] Frasier (2021). A machine learning pipeline for classification of cetacean echolocation clicks in large underwater acoustic datasets. PLoS Computational Biology. doi:10.1371/journal.pcbi.1009613
Verified: the work exists and matches · checked at Crossref on Oct 28, 2026, 11:21 PM UTC · the registry holds “A machine learning pipeline for classification of cetacean echolocation clicks in large underwater acoustic datasets” (2021)
[9] Dugan (2010). North Atlantic Right Whale acoustic signal processing: Part I. comparison of machine learning recognition algorithms. IEEE Long Island Systems, Applications and Technology Conference (LISAT). doi:10.1109/lisat.2010.5478268
Verified: the work exists and matches · checked at Crossref on Oct 28, 2026, 11:21 PM UTC · the registry holds “North Atlantic Right Whale acoustic signal processing: Part I. comparison of machine learning recognition algorithms” (2010)
[10] Ibrahim (2021). A multimodel deep learning algorithm to detect North Atlantic right whale up-calls. The Journal of the Acoustical Society of America. doi:10.1121/10.0005898
Verified: the work exists and matches · checked at Crossref on Oct 28, 2026, 11:21 PM UTC · the registry holds “A multimodel deep learning algorithm to detect North Atlantic right whale up-calls” (2021)
[11] Guirado (2019). Whale counting in satellite and aerial images with deep learning. Scientific Reports. doi:10.1038/s41598-019-50795-9
Verified: the work exists and matches · checked at Crossref on Oct 28, 2026, 11:21 PM UTC · the registry holds “Whale counting in satellite and aerial images with deep learning” (2019)
[12] Murray (1998). The neural network classification of false killer whale (Pseudorca crassidens) vocalizations. The Journal of the Acoustical Society of America. doi:10.1121/1.423945
Verified: the work exists and matches · checked at Crossref on Oct 28, 2026, 11:21 PM UTC · the registry holds “The neural network classification of false killer whale (<i>Pseudorca crassidens</i>) vocalizations” (1998)
Review
Not peer reviewed. No human scientist has reviewed this survey. Its template and landmark summaries were written with an AI assistant (Claude); the papers it lists are real and each was checked at its registry, so anyone can follow the links and read them.
- Each listed DOI was resolved, and its title, year and first author matched the listing.
- Each work the search found is held by Crossref, a registry independent of the search.
- Each number in the headline and summary is accounted for by a listed claim.
- No candidate work was dropped: every one the desk found or named was confirmed by its registry.
Code version: deb216f03447
What the record does not say
This survey lists what each paper reports; the game has not repeated these results. A search finds papers that match its words, so a listed paper may use AI only in part. The search is limited to the fifty most-cited matches, so the newest results may be missing until they are cited.
How this was written
Landmark works named by the desk, then the most-cited works with a DOI that OpenAlex returns when titles and abstracts are searched for (whale OR cetacean) AND (vocalization OR vocalisation OR song OR coda OR acoustic) AND ("machine learning" OR "deep learning" OR "neural network" OR "neural networks" OR "artificial intelligence" OR convolutional OR "reinforcement learning" OR "language model" OR transformer); a hit is kept only if its own title names the field and its title or abstract names an AI method, as whole words, and the hits that name the most of these words in their title come first. Each candidate was looked up at Crossref (OpenAlex as second resolver) and its title, year and first author compared; a work the search found is shown only when Crossref holds it. Landmark summaries were written by the desk; the other works are listed by their own titles.
Source records: code:src/lib/world-grammar/place-grammar.ts#resolvePurpose · doi:10.1038/s41598-019-48909-4 · doi:10.3389/fmars.2021.607321 · doi:10.1016/j.isci.2022.104393 · doi:10.1038/s41467-024-47221-8 · doi:10.1121/10.0000921 · doi:10.1121/10.0005047 · doi:10.1121/10.0004828 · doi:10.1371/journal.pcbi.1009613 · doi:10.1109/lisat.2010.5478268 · doi:10.1121/10.0005898 · doi:10.1038/s41598-019-50795-9 · doi:10.1121/1.423945