Cracking the Dolphin Communication Code | Denise Herzing | Talks at Google

Scientists have struggled to understand dolphin vocalizations, but new computer tools to both track dolphins and decode their complex vocalizations are now emerging. Dr. Denise Herzing has been studying Atlantic spotted dolphins, Stenella frontalis, in the Bahamas for over three decades. Her video and acoustic database encompasses a myriad of complex vocalizations and dolphin behavior. Dr. Thad Starner works on mining this dataset and decoding dolphin sounds, and has created a wearable underwater computer, CHAT (Cetacean Hearing and Telemetry), to help establish a bridge for communication between humans and dolphins. Starner and Herzing will present this cutting-edge work and recent results, including perspectives on the challenges of studying this aquatic society, and decoding their communication signals using the latest technology.

Dr. Denise Herzing has spent three decades researching and communicating with wild dolphins in their natural setting and on their own terms. Denise comes to Google to present this cutting-edge work and recent results, including perspectives on the challenges of studying this aquatic society, and decoding their communication signals using the latest technology.

[asraharrison]

Your research is so important. It exposes how centric each species communication is. It also exposes how complicated it is to understand an intelligent animal that is VERY closely related to us... compared to Extraterrestrial life.

[andreasstratigopoulos]

Such an amazing person and researcher! The world is lucky to have people like Denise Herzing

[ivorytower]

I really hope that Denise and her team have received some serious awards and recognition~!

[coldwavesf]

This is amazing. We're getting closer...

[benw]

If dolphins use "signature sounds" as names, and any dolphin in the group can call that dolphin by name (once learned) -- Then that is a _huge_ clue that they are intelligent, self-aware, aware of others, and have other _words_ and therefore _phonemes_ . A name shows a whole set of intelligent understanding of the world and their own kind. So the trick seems to be to figure out other simple words for nouns and verbs and other types of words.

[benw]

"Two pairs of male diads" -- So, swim buddies? Friends? Guards on duty? Same-sex partners? Brothers or cousins or brothers-in-law? -- Do they pair up from anyone among the group? Or is it typically the same pair? Do the female dolphins also pair up? Do you get male-female pairs for this? Is there a sex-based division of tasks in the group, or what degree of unisex (gender-neutral) versus gender role task division? So many questions. This must be fascinating work to do.

[Zamicol]

Thank you for publishing this. This is amazing.

[katiekane]

I hear some serious smack talk. Even without the computer, I feel like the tone of the communication is pretty clear. Amazing work!

[curvelinedot]

BRING HER BACK I WANT TO SEE HOW SHES DOING AND WHAT NEW THINGS SHE'S LEARNED

[billbusen]

Has anyone taken advantage of the human ear's incredible capabilities by dropping the recordings by seven octaves? This would divide the frequencies by 128, putting everything pretty much on the piano keyboard, and so easily amenable to human aural pattern recognition.

[mamaboocee]

Is there a study of communication between aquatic mammals and horses, elephants, apes and other terrestrial mammals? There is very little information on this . I would like to see gorilla and/or orangutan interactions with whales and dolphins. There is so much to explore!

[DanBray]

What about creating a dolphin headset to control a human robot via sounds, and also converting some dolphin sounds to human audible sounds, with human audible sounds being converted back? This could give them the capabilities to walk on land and speak. The dolphins are shown to mimic us, so give them the capabilities to walk and speak and they can mimic us in a lot more advanced ways, until they have learnt to use their given capabilities. Once one dolphin has learnt the alphabet through the interface, and learnt how to walk using the interface, the dolphin can then share the experience with other dolphins, Therefore, the basics wouldn't necessarily need to be taught over and over to them, and the most intelligent and curious dolphins would be the ones to come forward to use the interface.

The same could also be done in reverse, with us controlling a robot dolphin so that we could swim with them and use a keyboard to make dolphin sounds.

The final step would be to convert human speech to the correct meaning in dolphin sounds, and vice versa in real time. The problem is, there is likely no English translations for most dolphin sounds. It seems like they are too advanced in their communication and could possibly send images as sound faster than what can be described in words.

The possibilities are endless with the right technology.

[GBOPossum]

Please spend more time showing the presentation visuals, especially those with a lot of detailed content

[tebald]

Super interesting talk! I work with machine learning as well and this could be a way to make progress in this area even though it takes a lot of energy to collect data for your specific goal, maybe we can decode the first alien language with our “new” tools. I really hope you make good progress! Best luck! Ps. Have you collected sounds from captive dolphins? Or other tribes. Do the sounds match?

[monoham]

if you put the machines on in real time and hear the words, do you also modulate the HF sounds to human range frequencys? would that even help to hear in real time?

[lcppproductions]

It's crazy that this sort of stuff came from Georgia Tech. I just graduated from there with a degree in CS. I have to do more research this is cool.

[monoham]

so human language is iconic (if you make up words, a khenz is more likely to be a pointy object than a soome) and some birds and monkeys, but what about dolphoins? are objects that are more transparent to echolocation more ephemeral sounds than those that are solid?

[gggg]

Why would you make a noise at all in a hostile environment if you did not intend to communicate?

[nottees]

How well humans communicate with other humans is pretty questionable, let alone other species.

[Chadsprock]

Interesting! Thank you! Fascinating the similarities between early childhood development and the Dolphins observing a system. Interesting that whales & dolphins have a shared go-between language. For teaching the phonemes or symbols or even ideas (e.x. holding/swimming with a scarf/asking for a scarf/relinquishing scarf, gaining control of scarf) to the dolphins, as another option to the correlated created whistle, could one also use high pitched relaxing music, like synthesized flute or guitar sounds triggered from your underwater portable keyboard, since that might be very pleasing/attracting to both species, and instrumentals might function as a shared language? I think that’s cool that the parents might have been like, “Hey this is a shared safe learning environment, so we feel comfortable leaving our kid here for a while” haha. How much dolphins know of humans or might choose to disclose (very high intelligence) is unknown right? haha.
Hitchhikers Guide. Question though…. How do we know the signature whistle greetings are dolphin names? They could be “How are you?” in different forms right? I was thinking, if a dolphin broadcasts through a keyboard, a human voice recording of say “Hey! Check out this blue sky today” with the attempt to teach me how to swim with a scarf, I might not recognize, or it might be harder for me to associate that the recorded human “Check out this blue sky” audio actually meant the association with the visual “scarf“ and so I, might adapt the signal back with “The sky is blue, wahoo” or perhaps if I did realize it, I’d adapt with “the sky is blue, the inverse of this scarf color is too” which of course the receiver mammal might hear as additions or adaptations. That’s why I was thinking music might (or might not) be clearer. Or maybe if I liked the human phrase said to me, I might choose to keep it the same but adapt it with song perhaps with high / octave / harmony / or harmonic guitar pitch frequency stuff 🤪 to make it fresh. I learned that whales, like humans, adapt their songs too. The Cordinated sounds at 19:55 sounded like they were all working together in timing, almost like the cordinated grunts at a gym, or perhaps when doing class exercise, and there might also be chat in the group and gym. Cool! Were their weaves back and forth behavior correlating with the heaving sounds the burst pulses? And the higher squeal’s could be the chat / dialog? I know you mentioned they were two pairs competing. It looked and sounded like the group was trying to imitate a (row) boat maybe 🤪. Thank you again for the talk, I found it very interesting.