👀 You can SPEAK with your dog?!

Want to have a conversation with your dog? It’s coming…

Inter-species communication barriers are soon to be erased. Scientists are studying animal communication patterns with the hope of developing machine-learning products that can allow for us to speak with our pets.

New technology powered by artificial intelligence is poised to provide significant insights into animal communication. Whether animals communicate with one another in terms we might be able to understand is a question of enduring fascination. With recent breakthroughs in AI, “people realize that we are on the brink of fairly major advances in regard to understanding animals' communicative behavior,” says Christian Rutz, a behavioral ecologist at the University of St Andrews in Scotland.

So, should we expect a “Dr. Doolittle device”?

No. But according to scientists, developing a "Dr Doolittle device" is not the only way to decode the languages that animals use to communicate.

Instead, it is necessary to invent a technique to translate not only our own words and conversations into language that they can understand but also animal languages as a whole.

Many animals use different modes of communication simultaneously, just as humans use body language and gestures while talking. Any actions made immediately before, during, or after uttering sounds could provide important context for understanding what an animal is trying to convey. Traditionally, researchers have cataloged these behaviors in a list known as an ethogram. With the right training, machine-learning models could help parse these behaviors and perhaps discover novel patterns in the data.

I get it. So having a conversation with my dog wouldn’t be completely vocalized.

Exactly. That being said, if you want to experience vocalized identification, you can already use one kind of AI-powered analysis with Merlin, a free app from the Cornell Lab of Ornithology that identifies bird species. To identify a bird by sound, Merlin takes a user's recording and converts it into a spectrogram—a visualization of the volume, pitch and length of the bird's call. The model is trained on Cornell's audio library, against which it compares the user's recording to predict the species identification. It then compares this guess to eBird, Cornell's global database of observations, to make sure it's a species that one would expect to find in the user's location. Merlin can identify calls from more than 1,000 bird species with remarkable accuracy.

Machine-learning models could someday help us figure out our dogs. For a long time animal behaviorists didn't pay much attention to domestic pets, says Con Slobodchikoff, author of Chasing Doctor Dolittle: Learning the Language of Animals (link to his book for anyone interested). When he began his career studying prairie dogs, he quickly gained an appreciation for their sophisticated calls, which can describe the size and shape of predators. That experience helped to inform his later work as a behavioral consultant for misbehaving dogs. He found that many of his clients completely misunderstood what their dog was trying to convey. When our pets try to communicate with us, they often use multimodal signals, such as a bark combined with a body posture. Yet “we are so fixated on sound being the only valid element of communication, that we miss many of the other cues,” he says.

Now Slobodchikoff is developing an AI model aimed at translating a dog's facial expressions and barks for its owner. He has no doubt that as researchers expand their studies to domestic animals, machine-learning advances will reveal surprising capabilities in pets. “Animals have thoughts, hopes, maybe dreams of their own,” he says.

So, we can expect the complete package some day?

Here’s the fundamental problem preventing that: Language models are great at finding patterns. They aren't great at actually deciphering meaning—and they definitely aren't always right. Even AI experts often don't understand how algorithms arrive at their conclusions, making them harder to validate. Benjamin Hoffman, who helped to develop the Merlin app before joining the Earth Species Project, says that one of the biggest challenges scientists now face is figuring out how to learn from what these models discover. “The choices made on the machine-learning side affect what kinds of scientific questions we can ask,” Hoffman says.

Grasping the structure of a language is not a prerequisite to speaking it—not anymore, anyway. It's now possible for AI to take three seconds of human speech and then hold forth at length with its same patterns and intonations in an exact mimicry. In the next year or two, Raskin predicts, “we'll be able to build this for animal communication.”

We’ll stay patient.

Boo! Halloween is a month away and our friends at Petsmart have your covered. Pet parents and their pet can join in the Halloween fun with PetSmart’s proprietary Thrills & Chills™ collection. Your one-stop shop for all things Halloween can be found here!

Let sleeping dogs lie? Go ahead…they’re listening.

Those eyes are closed, but did the sandman pay them an actual visit?

Most dogs respond in specific ways to certain vocalizations, such as another dog barking or humans using certain tones of voice. Of course, this all happens while the dogs are awake.

Now, a new study suggests that they can also process vocalizations during sleep. The work, titled "Event-related potentials indicate differential neural reactivity to species and valence information in vocal stimuli in sleeping dogs," was published in Scientific Reports.

A team of researchers from ELTE University in Budapest, Hungary, conducted a small explorative study in which they measured the “event-related potentials” (ERPs, a term for measurable neural responses) in family dogs to vocalizations from human family members and other dogs while the subjects were asleep.

Studies have shown that much like humans, dogs in wakeful states respond with differing behaviors depending on the valence (levels of positivity and negativity) of vocalizations they hear. They can correlate vocalizations of both dogs and humans with respective facial expressions, and with appropriate pictures. Moreover, in dogs and in humans, sleep has been shown to be important for emotional processing and memory consolidation.

With this logic, that all-nighter you pulled to cram for that exam actually has a negative effect on your mind retaining the information whenever it’s time for that test.

So, in this study, would the dogs in various sleep stages have different reactions to either dogs or humans? In other words, do different species alter their sleepy reactions?

They hypothesized that the research subjects would show sensitivity to both, and recruited owners and dogs (sample size = 13) from the database of the Family Dog Project at Eötvös Loránd University's Department of Ethology.

The research team measured the dogs' neural responses only with surface electrodes (it’s a painless process so don’t come at them).

To place the electrodes, they gained the dogs' cooperation via positive reinforcement (praise and treats). Each dog was tested individually, and just before the testing began, the dog settled down for its daily nap with its owner sitting at its side.

From another room, while the dog was in states of wakefulness, drowsiness, and non-REM sleep, a research team member played recordings of non-verbal vocalizations from humans and dogs, each of which had been previously rated as having positive or neutral valence. To avoid startling or waking the dogs, no sounds of extremely negative valence were included. Each sound file lasted one second, and each was played at the same volume.

Positive vocalizations from dogs included growls, grunts, moans, pants, and whines; while neutral vocalizations included barks, grunts, moans, and yelps. From humans, positive vocalizations included general and laughing sounds; neutral included coughs, general sounds, moans, sighs, and yawns. No human vocalizations were used, which leaves this writer asking for more…

The intensity of the dogs' responses was recorded in milliseconds, and each testing session lasted approximately three hours. The dogs produced neural responses to each stimulus while they were awake, while they were drowsy, and during non-REM sleep, with varying intensities and slightly longer response times at each successive stage.

The findings show clearly that ERPs can occur in dogs during states of drowsiness and non-REM sleep, and that the dogs' brains are able to process them according to species and valence factors, similar to the way humans can process certain sounds as they sleep.

"This finding is significant," the research states, "insofar as it is the first evidence of complex auditory processing during sleep in dogs."

Indeed, these results expand our knowledge of dogs' neural processing abilities and provide a basis for further studies in this area…but it begs the question…

…are you going to watch what you say while your dog is napping now? 👀

Overheard at a coffee shop:

“The Squeeze”: Dog News In 60 Seconds

• 😬 “Real beauty is on the inside” - Austin, Tx… a coffee shop in Austin is hosting a “beauty pageant” for the city’s most charmingly unattractive dogs.

• 👔 We’re calling a three-peat: California’s dog mayor eats his third office tie in a month. Congratulations on holding office and supporting business casual attire, Max!

• 💨 Remember the couple that sit next to a farting dog for 14 hours on an airplane? Well…they were just refunded $1,400. Flatulence has its perks…

• 🥇 Does your dog have a laundry fetish? This Canadian dog just took 21 socks off of human feet… and Guinness is giving him world record recognition.

• 👟 In case you couldn’t fall asleep without knowing this: Tucker Carlson says Ron DeSantis did not kick his dog.

• 📸 Sure, Paris Jackson slayed the runway…but did anyone else SEE HER DOG?!

Today’s Last Laugh:

Let him in this INSTANT.

@ambatukamyesiammhm

#foryou #dogs #dog #cutedogs #putbulls #fyp #fy #fypfy