mlsanityData to 14 Oct 2026

Cetacean Translation Initiative: a roadmap to deciphering the communication of sperm whales

arXiv 2104.08614 ↗First posted 17 Apr 2021cs.SD cs.AI cs.CLcited by 3

Not on the map. Why?

Abstract (arXiv)

The past decade has witnessed a groundbreaking rise of machine learning for human language analysis, with current methods capable of automatically accurately recovering various aspects of syntax and semantics - including sentence structure and grounded word meaning - from large data collections. Recent research showed the promise of such tools for analyzing acoustic communication in nonhuman species. We posit that machine learning will be the cornerstone of future collection, processing, and analysis of multimodal streams of data in animal communication studies, including bioacoustic, behavioral, biological, and environmental data. Cetaceans are unique non-human model species as they possess sophisticated acoustic communications, but utilize a very different encoding system that evolved in an aquatic rather than terrestrial medium. Sperm whales, in particular, with their highly-developed neuroanatomical features, cognitive abilities, social structures, and discrete click-based encoding make for an excellent starting point for advanced machine learning tools that can be applied to other animals in the future. This paper details a roadmap toward this goal based on currently existing technology and multidisciplinary scientific community effort. We outline the key elements required for the collection and processing of massive bioacoustic data of sperm whales, detecting their basic communication units and language-like higher-level structures, and validating these models through interactive playback experiments. The technological capabilities developed by such an undertaking are likely to yield cross-applications and advancements in broader communities investigating non-human communication and animal behavioral research.

Key facts. Cited by 3 papers in the map (data through 14 Oct 2026). Builds on 16 of its 131 references that are in the map. First posted on arXiv 17 Apr 2021.

Builds on

16 of 131 references.

References · 16

  1. 2020Language Models are Few-Shot Learnerscited by 32,419
  2. 2019ViLBERT: Pretraining Task-Agnostic Visiolinguistic Representations for Vision-and-Language Taskscited by 2,222
  3. 2015Neural Module Networkscited by 376
  4. 2019vq-wav2vec: Self-Supervised Learning of Discrete Speech Representationscited by 340
  5. 2018Neural Approaches to Conversational AIcited by 165
  6. 2017Unsupervised Neural Machine Translationcited by 149
  7. 2015Grounding of Textual Phrases in Images by Reconstructioncited by 112
  8. 2019Unsupervised speech representation learning using WaveNet autoencoderscited by 90
  9. 2019Compound Probabilistic Context-Free Grammars for Grammar Inductioncited by 76
  10. 2020Vector-Quantized Autoregressive Predictive Codingcited by 69
  11. 2020Vector-quantized neural networks for acoustic unit discovery in the ZeroSpeech 2020 challengecited by 55
  12. 2018Speech2Vec: A Sequence-to-Sequence Framework for Learning Word Embeddings from Speechcited by 52
4 more
  1. 2019Visually Grounded Neural Syntax Acquisitioncited by 48
  2. 2016Audio Word2Vec: Unsupervised Learning of Audio Segment Representations using Sequence-to-sequence Autoencodercited by 34
  3. 2019Unsupervised acoustic unit discovery for speech synthesis using discrete latent-variable neural networkscited by 20
  4. 2020CiwGAN and fiwGAN: Encoding information in acoustic data to model lexical learning with Generative Adversarial Networkscited by 15

Built on by

Cited by year

Citing papers per year: 2022: 1; 2023: 1; 2024: 1.

3 papers.

  1. 2024Biospheric AIcited by 1
  2. 2022What can we know about that which we cannot even imagine?cited by 0
  3. 2023Detecting the presence of sperm whales echolocation clicks in noisy environmentscited by 0