Four years ago, I wrote that to me, Transformers' most exiting application could be translating whale's songs. I was obviously very wrong (won't be the first time, won't be the last), but I imagine recording of birds should be more numerous than whales', so maybe someday, hopefully, transformers would integrate bird songs to the list of languages they can translate to and from.

▲

moi2388 3 days ago | parent | next [-]

How will you train this? I understand it replicating bird songs, but what data will it use for actual translation?

▲

tomrod 3 days ago | parent | next [-]

It would operate a lot like image recognition tasks, probably in frequency 0 domain for a concrete space to operate in. SLID or other information theoretic approaches could isolate common signals, then translate that to captured environmental information (e.g prairie dogs identifying predators).

Animals don't use a known syntax per se, so it wouldn't be authentic translation, but a transliteration may be possible. Also, there is no guarantee that one animal doing something (like a dog's behavior for going to the bathroom) maps to many or all dogs.

▲

chrisco255 3 days ago | parent | prev | next [-]

The Crowsetta Stone

▲

crowsettastone 3 days ago | parent | next [-]

Here you go.

https://claude.ai/public/artifacts/ec289f75-9daf-49bd-96ae-a...

▲

imglorp 3 days ago | parent [-]

Amazing, I gave it a recording and it gave an analysis.

Do you know how to hear the generated sounds? Pressing the buttons shows a "playing" console message but there's no audio.

	▲	crowsettastoner 3 days ago \| parent [-]
		[dead]

▲

crowsettastoner 3 days ago | parent | prev [-]

[dead]

▲

bhickey 3 days ago | parent | prev | next [-]

Probably the same way many other models are trained: autoregression or autoencoding. You'd either predict the next symbol, or you compress it into a latent space and reconstruct the original. My assumption is that birdsong is sequential, but this isn't something I know about. An entire song might be the smallest semantic unit, like the alien language in Arrival, though I think this is unlike.

	▲	cluckindan 2 days ago \| parent [-]
		Sometimes birds communicate via melody (songbirds), sometimes via repetition (ducks, geese), sometimes via timbre (pigeons, doves), and sometimes via a combination of the former and sound-making in general. Sometimes birds communicate nonverbally as well, as in gaze direction and body posture.

▲

diggan 3 days ago | parent | prev | next [-]

> but what data will it use for actual translation?

I'm no ornithologist, for forgive my ignorance, but shouldn't there be bunch of papers out there where researchers try to infer the meaning of various sounds birds produce, together with a description of the sound and even samples of it? I don't know how numerous that could be, but could maybe be used as a starting point at least.

▲

ileonichwiesz 3 days ago | parent [-]

There are large datasets of bird sounds (eBird, Cornell Labs, etc), but the descriptions are usually limited to the species, location, and something like “mating call” or “contact call”. Hugely useful for building models that can recognise birds by call (apps like that already exist, I recommend Merlin Bird ID), but definitely not enough for something approaching actual translation.

FWIW there’s no research to indicate that the sounds birds make are what we’d call language. They’re avid communicators, and some species are known to be highly intelligent, but of course it’s not like “caw” means “to fly” and “craah” is “forward”.

▲

cluckindan 2 days ago | parent [-]

I’ve been winter feeding the local birds for a couple years now, and especially the great tits acknowledge my presence via a special call I haven’t heard anywhere else. It’s distinct from the calls they use when they find food otherwise. Bird ID applications consistently fail to recognize the species based on that call.

There are stationary feeders in the neighborhood, but the birds don’t seem to associate the humans filling them with their food, and subsequently just use warning calls when they see humans approaching the feeders.

But whenever they see me, even in the summer, they use that call. Blue tits have their own, shorter variation of it.

I like to think they’ve given me a name in their language :-)

	▲	diggan 2 days ago \| parent [-]
		> I like to think they’ve given me a name in their language :-) Probably best for everyone involved to not understand the meaning of the name they gave you too! :)

▲

cluckindan 2 days ago | parent | prev | next [-]

It would need contextual information of what the bird is communicating about and to whom. 360 degree video with object/species detection and a custom bird/flock behavior classifier?

▲

macrolime 3 days ago | parent | prev [-]

YouTube videos of birds?

	▲	loveparade 3 days ago \| parent [-]
		I hope the EditorBird added subtitles.

▲

pjmlp 3 days ago | parent | prev | next [-]

I would actually be quite curious what the crows get to talk around 6 AM on nearby trees for about half an hour, before leaving for their daily duties.

Not sure how everything would go, if we finally managed to talk with fellow species, given how wrong it goes even with other humans.

▲

jacquesm 3 days ago | parent [-]

That's the country wide weather report. And they need to recite it so whole that it spreads from the point of origin otherwise it would be just a local update. Fascinating stuff. Humans used to do much the same when radio first came along.

▲

pjmlp 3 days ago | parent [-]

Lovely. :)

	▲	jacquesm 3 days ago \| parent [-]
		Plot twist: 50 years from now they really decode it and it turns out to be exactly that. I'll be eating some crow if that should be the case.

▲

princeofwhales 3 days ago | parent | prev [-]

It may be that whales are using their song not just as inter-species communication, but as a farming method for their desired food. Could it be a "lullaby" to the krill? Or a signal which causes the krill to group closer together, thereby increasing the efficiency of the whales' feeding activities?

Many bat species use ultrasonic pulses to detect moths and other flying insects while hunting, so whalesong may even be some form of longer range food detecting sonar? I'm not sure if that amount of distributed biomass would be detectable, but we don't know enough about their sensing apparatus to completely rule it out. Interestingly, some moth species have learned to jam the signal sent by bats by emmiting loud clicks, disrupting the return signal to throw off their target triangulation ability. I don't think the krill are so equipped, unfortunately for them! My guess is if their (whale) numbers were higher, they wouldn't consume their preferred food source in an unsustainable manner, giving the krill time to recover and moving on to larger patches to allow the recently "grazed" areas time to recover. One thing is for sure, their song activity is at least partly related to their feeding and migration activity in some way:

https://www.upi.com/Science_News/2020/10/01/Blue-whale-singi...

Also, studies have found that whalesong differs in frequency range depending on where in the world they are, possibly relating to water temperature and overall salinity/acidity, as colder/warmer and alkaline/acidic water will have different sonic properties due to density changes in the transmission medium, or the increase in ocean activity from shipping and ULF emmissions from submarines, and the overall effect of sea surface temperatures increasing. Blue Whales for example are known to feed at relatively shallow depths (<200m) as that's where the krill gather during the daytime. The interesting thing is there is an overall downward trend in the sonic frequency observed in the last several decades:

https://www.encyclopedie-environnement.org/en/zoom/decline-f... & https://www.theatlantic.com/magazine/archive/2019/10/whale-s...

The recent articles in the press regarding the decline of Blue Whales' song in the pacific seems to point to the fact that they signal for abundance of their food source after locating it, like ringing a dinner bell when it's feeding time. This along with other factors like simply conserving their energy for further search activity could explain the increasingly infrequent song activity. With their population still recovering as a result of industrial whaling (global estimates are ~10,000-15,000), perhaps this behaviour is emergent, like a social call to help other whales feed, boosting their long term chances of survival in the changing ocean environment:

https://www.nationalgeographic.com/animals/article/ocean-hea...

Finally, I spotted this interesting looking project regarding whale communication if you're interested (unsure how active it is currently):

https://www.whaleweb.org/intersp/homepage.html