{"id":335,"date":"2026-09-01T17:41:46","date_gmt":"2026-09-01T17:41:46","guid":{"rendered":"https:\/\/bemjax.com\/blog\/?p=335"},"modified":"2026-09-01T17:43:47","modified_gmt":"2026-09-01T17:43:47","slug":"najnovije-u-svijetu-dekodiranja-kitovskog-govora","status":"publish","type":"post","link":"https:\/\/bemjax.com\/blog\/najnovije-u-svijetu-dekodiranja-kitovskog-govora\/","title":{"rendered":"What\u2019s new in whale speech decoding"},"content":{"rendered":"

Sperm whales talk in clicks. Over the last two years the way researchers represent that talk has changed from a flat list of labels into a factorised, compositional code \u2014 and the tools doing the factorising are the same generative models you already know. Here is where coda research stands, for a reader who knows some ML and nothing about whales.<\/em><\/p>\n

1 · What a coda is, and what the old representation was<\/h2>\n

Sperm whales emit two kinds of click: echolocation clicks for foraging sonar, and codas<\/strong> — short stereotyped sequences of 3–40 clicks, under two seconds long, exchanged in duet-like back-and-forth or in group chorus before diving and while socialising. They are never produced alone<\/strong>. That single constraint is the reason to treat a coda as communication rather than a by-product of sensing.<\/p>\n

Codas are culturally learned, not genetic<\/strong>. Whales segregate into vocal clans of hundreds or thousands that identify themselves by their coda repertoire; each clan dialect carries at least twenty coda types. What a whale “says” is decided by the clan it grows up in.<\/p>\n

Until 2024 the working representation was a flat categorical label set — roughly 20–40 “coda types” named by their inter-click-interval pattern (5R = five regular clicks; 1+1+3). A hand-built vocabulary of discrete labels laid over a continuous acoustic signal. Everything below is the story of replacing that label set with something factorised.<\/p>\n

The corpus is what makes it possible. The Dominica Sperm Whale Project has followed the same identified families<\/em> off Dominica since 2005. Project CETI added fixed hydrophone arrays, clingfish-inspired suction-cup bio-logging tags (three synchronised hydrophones plus GPS, depth, temperature, light and motion), drones and gliders — about 10,000 coda recordings over two decades. The recordings did not exist before the instrument did.<\/p>\n

2 · 2024: from a label set to a factorised code<\/h2>\n

Sharma et al., Nature Communications<\/em> 2024. Instead of asking which of N labels is this coda<\/em>, ask what dimensions generate it<\/em>. Four features — and the split between them is the actual finding:<\/p>\n