Squeak Squeak, Buzz Buzz: How researchers are using AI to talk to animals

[CLIP: Bird songs]

Kelso Harper: Have you ever wondered what songbirds are actually saying to each other with all their chirping?

Sophie Bushwick: Or what could make your cat howl so early in the morning?

[CLIP: Cat meowing]

Harper: Well, powerful new technologies are helping researchers decipher animal communication. And even start responding with non-humans.

Bushwick: Advanced sensors and artificial intelligence could push us to the brink of interspecies communication.

[CLIP: Show theme music]

Harper: Today we’re talking about how scientists are beginning to communicate with creatures like bats and honeybees, and how those conversations are forcing us to rethink our relationships with other species. I’m Kelso Harper, Multimedia Editor at Scientific American.

Bushwick: And I’m Sophie Bushwick, Tech Editor.

Harper: You’re listening to Science, Quickly. hey sophie

Bushwick: Hi Kelso.

Harper: You recently spoke to the author of a new book called The Sounds of Life: How Digital Technology is Bringing us Closer to the Worlds of Animals and Plants.

Bushwick: Yes, I had a great conversation with Karen Bakker, a professor at the University of British Columbia and a fellow at the Harvard Radcliffe Institute for Advanced Study. Her book examines how researchers are using new technologies to understand animal communication, even in the burgeoning field of digital bioacoustics.

Harper: Digital Bioacoustics. Hm. So what does it actually look like? Are we trying to get animals to talk like humans using translation collars like in the movie Up?

[CLIP: From Walt Disney’s Up]

Doug the Dog: My name is Doug. My master made me this caller so that I could speak to squirrels.

Bushwick: Not quite, but it’s similar to what happened in the 1970s and 1980s when researchers first tried to communicate with animals, which means they tried to teach animals human language. But many scientists today have moved away from this human-centric approach and instead want to understand animal communication in their own terms.

Harper: So instead of trying to teach birds to speak English, we’re deciphering what they’re already saying to each other in bird-speak or bird-speak.

Bushwick: Right, exactly. This new field of digital bioacoustics uses handheld field recorders, which are like miniature microphones you can place just about anywhere – in trees, on mountain tops, even on the backs of whales and birds.

They’re recording sounds 24/7 and creating tons of data, and that’s where artificial intelligence comes in. Researchers can apply natural language processing algorithms like those used by Google Translate to recognize patterns in these recordings and decipher what animals might be saying to each other.

Harper: Wow, that’s wild. What have scientists learned from this so far?

Bushwick: One of the examples Karen gives in her book is about Egyptian fruit bats. A researcher named Yossi Yovel spent two and a half months recording audio and video footage of nearly two dozen bats. His team adapted a speech-recognition program to analyze 15,000 of the sounds, and then the algorithm correlated specific sounds with specific social interactions in the videos, such as talking to each other. B. Fights over food or scuffles over places to sleep.

So this research, combined with some other related studies, has shown that bats are capable of complex communication.

Harper: All I remember is that bats were taught to make high-pitched noises to echolocate when they were flying around, but it sounds like there’s a lot more to it than that.

Bushwick: Yes, definitely. We learned that bats have so-called signature calls, which act like individual names.

Harper: Wow.

Bushwick: And they differentiate between the sexes when they communicate with each other.

Harper: What?

Bushwick: They have dialects. They argue about eating and sleeping positions. They socially distance themselves when they are sick.

Harper: Are you serious?

Buschwick: Yes. They’re better at it than us in some ways. So one of the coolest things is that mother bats use their own version of native language with their young.

So when people talk to cute little babies, we use native language. We raise our pitch, you know how, oh what a cute little yam. And bats also use a special tone to talk to their young, but they lower their pitch instead… oh, what a cute little yam.

This gets the baby bats to babble back, and it might help them learn certain words or reference sounds in the same way that native language helps human babies learn language.

Harper: That’s crazy. Or I don’t know. Is it? Do I just think it’s because I fell into the trap of thinking that humans are somehow totally different from other animals and that we have, I don’t know, a uniquely sophisticated way of communicating? Are we learning that maybe we’re not as special as we thought we were?

Bushwick: Sort of, yes. This work raises many important philosophical and ethical questions. Philosophers have long said we could never tell if animals had a language, let alone be able to decipher it or speak it. But these new technologies have really changed the game.

One thing Karen said during our interview is that we can’t talk to bats, but our computers can.

You and I can’t hear, much less keep up with, the fast, shrill communication between bats. And we certainly can’t speak it ourselves, but electronic sensors and speakers can.

And with artificial intelligence, we can begin to track patterns in animal communication that we never could before.

People are still debating whether we can call it animal language, but it’s becoming increasingly clear that animals have much more complex ways of communicating than we previously thought.

Harper: Apparently. What other examples of this can you find in the book?

Bushwick: Karen also told me the story of a bee researcher named Tim Landgraf. So honey bee communication is very different from our own. They use not only sounds but also the movements of their bodies to speak. Have you heard of the famous wobble dance?

Harper: Yes. Is that the one where the bees shake their fluffy asses in different directions? Or explain where to find nectar?

Bushwick: That’s it. But the wobble dance is just one form of honeybee communication. Landgraf and his team used a combination of natural language processing. As in the bat study and computer vision analyzing images to decode both the sounds and wobbles of bee chatter. They are now able to track individual bees and predict the impact of what one bee says to another.

Harper: That’s so cool.

Bushwick: Yeah, they have all sorts of specific signals that the researchers gave it that weird name. So bees does [CLIP: Bee toot sound] and quacks [CLIP: Bee quack sound] for they have a panting sound for danger [CLIP: Bee whooping sound]. Piping signals related to swarming [CLIP: Bee piping sound]and they use a mute or stop signal to get the hive to calm down [CLIP: Bee hush sound].

Harper: Wow. I love the image of a croaking bee.

Bushwick: Landgraf’s next step was to encode what he had learned into a robotic bee he called… drum roll, please… Robobee.

Harper: Classic.

Bushwick: After seven or eight prototypes, they had a Robobee that could actually go into a hive and then send out commands like the stop signal and the bees obeyed.

Harper: Those are bananas. Just one step closer to the very science-based world of B-Movies.

Bushwick: The Height of Cinematic Achievement.

[CLIP: From DreamWorks Animation’s Bee Movie]

Bee: I have to say something. do you like jazz

Harper: Oh, well, before we wrap up, is there anything else you’d like to add from your conversation with Karen?

Bushwick: I would like to end with a quote from her. She said: The invention of digital bioacoustics is analogous to the invention of the microscope.

Harper: Wow.

Bushwick: The microscope opened up a whole new world for us and visually laid the foundation for countless scientific breakthroughs. And that’s exactly what digital bioacoustics does with audio for the study of animal communication. Karen says it’s like a “planetary hearing aid that allows us to hear anew with both our prosthetically enhanced ears and our imaginations.”

Harper: What a great analogy.

Bushwick: Yeah, it’s going to be really interesting to see where the research goes from here and how it might change the way we think about the so-called human-non-human divide.

Harper: Yes, I’m already questioning everything I thought I knew. Well Sophie, thank you for sharing all of this with us.

Bushwick: Squeak, squeak, hum, hum my friends.

Harper: And the buzz, buzz, right back to you.

If you’re still curious, you can read more about it on our website and in Sophie’s Q&A with Karen Bakker. And of course in Karen’s new book The Sounds of Life. Thank you for tuning in to Science, Quickly. This podcast is produced by Jeff DelViscio, Tulika Bose and myself, Kelso Harper. Our theme music was composed by Dominic Smith.

Special thanks today to Martin Bencsik from Nottingham Trent University and James Nieh from the University of California, San Diego for providing excellent examples of honey bee tuts and quaks and woops.

Bushwick: Don’t forget to register. And for more in-depth science news, podcasts and videos, visit ScientificAmerican.com. For Scientific American Science Fast. I’m Sophie Bushwick.

Harper: And I’m Kelso Harper. Until next time.

Harper: I’m so excited. Also, I’ll turn your bubbly bass yam into a boob job. I will be.

Buschwick: Yes. That’s all I wanted.