SoylentNews is people
SoylentNews
from the so-long-and-thanks-for-all-the-fish dept.
A NewScientist article discusses how pattern recognition software is being used to help us better understand the communications of animals, including a program that can automatically translate dolphin whistles (but only if the meaning is already known):
IT was late August 2013 and Denise Herzing was swimming in the Caribbean. The dolphin pod she had been tracking for the past 25 years was playing around her boat. Suddenly, she heard one of them say, "Sargassum".
... She was wearing a prototype dolphin translator called Cetacean Hearing and Telemetry (CHAT) and it had just translated a live dolphin whistle for the first time.
It detected a whistle for sargassum, or seaweed, which she and her team had invented to use when playing with the dolphin pod. They hoped the dolphins would adopt the whistles, which are easy to distinguish from their own natural whistles and they were not disappointed. When the computer picked up the sargassum whistle, Herzing heard her own recorded voice saying the word into her ear.
...
Herzing is quick to acknowledge potential problems with the sargassum whistle. It is just one instance and so far hasn't been repeated. Its audio profile looks different from the whistle they taught the dolphins it has the same shape but came in at a higher frequency. Brenda McCowan of the University of California, Davis, says her experience with dolphin vocalisations matches that observation.
Since the translatable vocalization has only been used once, it could be nothing more than a fluke, but if we can teach dolphins new vocalizations with a specific meaning and they actually use them, then we could finally understand each other enough to start gathering the data needed for real communication with a non-human species, which would be an incredible achievement (and might finally force people to accept the fact that humans really arent all that different from other animals).
(Score: 2) by umafuckitt on Wednesday April 02 2014, @10:37PM
But such a translator is fictional since it'll only be able to output what you tell it to. It'll essentially just be a state machine that gathers a bunch of behavioral parameters, classifies them, then selects an pre-determined output. Likely you will always be better at pattern recognition than any such device. The only reason it's being suggested for dolphins is because people can't hear or mimic their calls.
(Score: 1) by moondoctor on Thursday April 03 2014, @07:55AM
google translate will testify to the complexity of machine translation.
that shit is no joke... they've been at it for decades and it is still rudimentary for documented languages. for it to ever work properly it gets into AI territory if you ask me.
"It'll essentially just be a state machine that gathers a bunch of behavioral parameters, classifies them, then selects an pre-determined output"
hope not! that would be useless, as you say.
i think of this as getting a start on a "front end".
the "back end" - translating communication by non verbal means like body language, chemicals, ultrasonic, subsonic, etc., will take a lot of time and work. may even prove impossible in the end. doesn't mean it's not worth trying.