24-04-2025
Study Finds Dolphins Can Make Human Vowel Sounds as Experts Launch AI-Powered Dolphin Translation
New research reveals that dolphins can mimic human vowel sounds, indicating their potential for interspecies communication
The study highlights a dolphin named Zeus and the marine mammal's intentional communication with humans
Google's AI model, DolphinGemma, is advancing human-dolphin communication, helping researchers identify mimicked sounds and better respond to dolphins' requests
Could humans have entire conversations with dolphins in the future? A new study found that the marine mammals already know part of the human language.
In a press announcement published on Tuesday, April 23, J & J Publishing, a dolphin-focused education and science publisher, released a research paper titled "Novel Dolphin Vocalization." It reveals the "intricate cognitive capabilities of dolphins and their sophisticated understanding of mimicry as a tool for interspecies communication."
The study notes that dolphins have developed the ability to produce specific sounds, measured by complexity, frequency, amplitude, and duration, that mimic vocalizations resembling the human vowel sounds, "A, E, O, and U."
Related: Once-Extinct Bird Is Now Laying Eggs in the Wild for the First Time in Nearly 40 Years
Unlike humans, who auditorily communicate with their mouths and vocal cords, dolphins' vocalizations come from their blowholes and air sacs. The sounds emitted can create a range of octaves, some even too complex for the human ear.
Researchers from SpeakDolphin focused on a dolphin named Zeus for the study after noticing the animal's spontaneous vocalizations.
"I missed it at first," confessed lead researcher Jack Kassewitz. "Because they live in aquatic environments, dolphins' brains have adapted to process sound much faster than humans. As researchers, it's often challenging to recognize dolphins' very fast-paced acoustic patterns while recording on location."
However, once the researcher caught on, he realized the vowel sounds were distinct from Zeus' normal dolphin vocalization. "I am convinced that some dolphins, Zeus in particular, are as determined to communicate with us as we are with them," said Kassewitz. "We have heard anecdotal reports over the decades of similar dolphin mimicry. Finally, we can analyze these specialized vocalizations with our advanced software."
Related: 'Extremely Rare' Hybrid 'Rockaroni' Penguins Caught on Camera Evolving 'Before Our Eyes' (Exclusive)
Kassewitz explained the difference between the sounds dolphins make connecting with each other versus the sounds made towards humans above water. "When dolphins vocalize above the water surface, it is almost certainly to get the attention of nearby humans," he noted. "Zeus' vowel vocalizations — made with his head above water and directed at our research team — demonstrated how intentional his efforts were."
The study comes only weeks after Google announced its progress in human-dolphin communication using AI.
On April 14, in celebration of National Dolphin Day, Google — in collaboration with researchers at Georgia Tech (led by Google DeepMind Research Scientist and Georgia Tech professor Dr. Thad Starner) and field researchers led by the Research Director and founder of the Wild Dolphin Project (WDP) Dr. Denise Herzing — revealed the developments made to their foundational AI model, DolphinGemma.
The AI model uses the SoundStream tokenizer, a Google audio technology, to recreate dolphin sounds to identify recurring sound patterns, clusters, and reliable sequences.
Related: New Details Emerge About the Seizure and Death of Pet Influencer Peanut the Squirrel
From decades of underwater observations, WDP has analyzed specific sounds with behavioral correlations for dolphins. For example, signature whistles (or names) are used to call the calves back to them; burst-pulse 'squawks' are used during fights; and clicking 'buzzes' are heard during courting and shark chases.
WDP has furthered its communication exploration by creating the Cetacean Hearing Augmentation Telemetry (or CHAT) system, alongside Georgia Institute of Technology, to establish a more stable, more straightforward shared vocabulary with the marine mammals.
Researchers use the CHAT system to create synthetic dolphin sounds and then associate those sounds with objects that the dolphins they're studying enjoy, including sargassum, seagrass, or scarves. From there, the CHAT system listens for the dolphins to mimic the sounds it creates, identifies which whistle was mimicked, and informs the researcher which object the dolphin is referring to. This allows the researcher to provide the requested item quickly, building the vocabulary and connection between the two.
With DolphinGemma, CHAT can anticipate and identify mimicked sounds faster. This increases the speed at which researchers can respond to the dolphin's requests, allowing for a more fluid communication sequence.
Read the original article on People
