Can we learn to talk to sperm whales? | David Gruber | TED

76,718 views ใƒป 2021-04-28

TED


ืื ื ืœื—ืฅ ืคืขืžื™ื™ื ืขืœ ื”ื›ืชื•ื‘ื™ื•ืช ื‘ืื ื’ืœื™ืช ืœืžื˜ื” ื›ื“ื™ ืœื”ืคืขื™ืœ ืืช ื”ืกืจื˜ื•ืŸ.

ืชืจื’ื•ื: Ido Dekkers ืขืจื™ื›ื”: zeeva livshitz
ืืชื ืขื•ืžื“ื™ื ืœืฉืžื•ืข ืืช ื”ืงื•ืœื•ืช ืฉืœ ื”ื˜ื•ืจืคื™ื ื”ื’ื“ื•ืœื™ื ื‘ื™ื•ืชืจ ืขื ืฉื™ื ื™ื™ื
ืขืœ ืคื ื™ ื”ืคืœื ื˜ื”:
ื—ื™ื” ื’ื“ื•ืœื” ื™ื•ืชืจ ืžืื•ื˜ื•ื‘ื•ืก ื‘ื™ืช ืกืคืจ
ืขื ืื•ืœื™ ืฆื•ืจืช ื”ืชืงืฉื•ืจืช ื”ื›ื™ ืžืชื•ื—ื›ืžืช
00:12
You are about to hear the sounds of the largest-toothed predator
0
12375
3309
ืฉืื™ ืคืขื ื”ื™ืชื” ืงื™ื™ืžืช.
00:15
on the planet:
1
15708
1268
(ืกืจื˜ื•ืŸ: ืœื•ื•ื™ืชื ื™ื ืžืชืงืชืงื™ื)
00:17
an animal bigger than a school bus
2
17000
2351
00:19
with perhaps the most sophisticated form of communication
3
19375
3059
00:22
that has ever existed.
4
22458
2310
00:24
(Video: whale clicking)
5
24792
6000
ืืœื” ื”ืงื•ืœื•ืช ืฉืœ ืœื•ื•ื™ืชื ื™ ื”ื–ืจืข ื”ืขืฆื•ืžื™ื,
ื™ื•ื ืง ืขืžื™ืช ืฉื™ื›ื•ืœ ืœืฆืœื•ืœ ืœืขื•ืžืง ืฉืœ ื›ืžืขื˜ ืงื™ืœื•ืžื˜ืจ ื•ื—ืฆื™,
ืœืขืฆื•ืจ ืืช ื”ื ืฉื™ืžื” ืœื™ื•ืชืจ ืžืฉืขื”
00:43
These are the sounds of the mighty sperm whale,
6
43833
2518
ื•ื—ื™ ื‘ื—ื‘ืจื•ืช ืžื˜ืจื™ืืจื›ืœื™ื•ืช ืžื•ืจื›ื‘ื•ืช ื‘ื™ื•ืชืจ.
00:46
a fellow mammal that can dive almost a mile,
7
46375
2893
ื”ืงืœื™ืงื™ื ื”ืืœื” ืฉืฉืžืขืชื,
ืฉื ืงืจืื™ื ืงื•ื“ืืก,
00:49
hold its breath for more than an hour
8
49292
2267
ื”ื ืจืง ื”ืคื ื™ื ืฉืœ ืžื” ืฉืื ื—ื ื• ื™ื•ื“ืขื™ื ืขืœ ื”ืชืงืฉื•ืจืช ืฉืœื”ื.
00:51
and lives in these amazingly complex, matriarchal societies.
9
51583
3851
ืื ื—ื ื• ื™ื•ื“ืขื™ื ืฉื”ื—ื™ื•ืช ื”ืืœื• ืžืชืงืฉืจื•ืช,
00:55
These clicks you heard,
10
55458
1310
ืื ื—ื ื• ืคืฉื•ื˜ ืœื ื™ื•ื“ืขื™ื ืขื“ื™ื™ืŸ ืžื” ื”ืŸ ืื•ืžืจื•ืช.
00:56
called codas,
11
56792
1267
00:58
are just a facet of what we know of their communication.
12
58083
3101
ืคืจื•ื™ื™ืงื˜ CETI ืžื˜ืจืชื• ืœื’ืœื•ืช.
ื‘ืžื”ืœืš ื—ืžืฉ ื”ืฉื ื™ื ื”ื‘ืื•ืช,
01:01
We know these animals are communicating,
13
61208
2393
ื”ืฆื•ื•ืช ืฉืœื ื• ืฉืœ ืžื•ืžื—ื™ ื‘ื™ื ื” ืžืœืื›ื•ืชื™ืช,
01:03
we just don't yet know what they're saying.
14
63625
2976
ืจื•ื‘ื•ื˜ื™ืงื”, ืœืฉื•ื ืื•ืช
ื•ื‘ื™ื•ืœื•ื’ื™ื ื™ืžื™ื™ื
01:06
Project CETI aims to find out.
15
66625
2268
ืžืชื›ื•ื•ื ื™ื ืœื”ืฉืชืžืฉ ื‘ื˜ื›ื ื•ืœื•ื’ื™ื•ืช ื”ื›ื™ ื—ื“ืฉื ื™ื•ืช
01:08
Over the next five years,
16
68917
1559
ื›ื“ื™ ืœืชืงืฉืจ ืขื ืžื™ืŸ ืื—ืจ,
01:10
our team of AI specialists,
17
70500
1684
ื•ื‘ืชืงื•ื•ื” ืœืชืงืฉืจ ื—ื–ืจื”.
01:12
roboticists, linguists
18
72208
1768
01:14
and marine biologists
19
74000
1434
ืื ื—ื ื• ืžืืžื™ื ื™ื ืฉืขืœ ื™ื“ื™ ื”ืงืฉื‘ื” ืขืžื•ืงื” ืœื˜ื‘ืข,
01:15
aim to use the most cutting-edge technologies
20
75458
2310
01:17
to make contact with another species,
21
77792
1892
ืื ื—ื ื• ื™ื›ื•ืœื™ื ืœืฉื ื•ืช ืืช ื ืงื•ื“ืช ื”ืžื‘ื˜ ืฉืœื ื• ืขืœ ืขืฆืžื ื•
01:19
and hopefully communicate back.
22
79708
3476
ื•ืœืขืฆื‘ ืžื—ื“ืฉ ืืช ื”ื™ื—ืกื™ื ืฉืœื ื• ืขื ื›ืœ ื”ื—ื™ื™ื ืขืœ ื”ืคืœื ื˜ื”.
01:23
We believe that by listening deeply to nature,
23
83208
2518
ื–ื” ื›ืžื•ื‘ืŸ ื ืจืื” ื›ืžื• ืžื˜ืจื” ื‘ืœืชื™ ืืคืฉืจื™ืช.
01:25
we can change our perspective of ourselves
24
85750
2476
01:28
and reshape our relationship with all life on this planet.
25
88250
5059
ืื ืฉื™ื ื ื™ืกื• ืœืชืงืฉืจ ืขื ื—ื™ื•ืช ืื—ืจื•ืช
ื‘ืžืฉืš ืžืื•ืช ืฉื ื™ื.
ืื™ืš ื ื•ื›ืœ ืœืขืฉื•ืช ืžื” ืฉืื—ืจื™ื ืœื ื™ื›ืœื•,
01:33
This of course seems like an impossible goal.
26
93333
3393
ื‘ืขื™ืงืจ ื‘ื”ืชื—ืฉื‘ ื‘ื›ืš ืฉืื ื™ ื™ื•ืฉื‘ ืคื” ืขืœ ื”ืกืคื” ืฉืœื™ ื‘ื ื™ื• ื™ื•ืจืง
01:36
People have been trying to make contact with other animals
27
96750
2768
ื‘ืืžืฆืข ื”ืžื’ืคื” ื•ื”ืžื—ืื•ืช?
01:39
for hundreds of years.
28
99542
1309
01:40
How could we do what others could not,
29
100875
2393
ื‘ื™ืœื™ืชื™ ืืช 20 ื”ืฉื ื™ื ื”ืื—ืจื•ื ื•ืช ื›ื‘ื™ื•ืœื•ื’ ื™ืžื™ ื•ื—ื•ืงืจ ืื•ืงื™ื™ื ื•ืกื™ื,
01:43
especially given that I'm sitting here on my couch in New York City
30
103292
4142
ื—ื•ืงืจ ืืช ื”ืื•ืงื™ื™ื ื•ืก ืžื›ืœ ื ืงื•ื“ื•ืช ื”ืžื‘ื˜ ื”ืฉื•ื ื•ืช,
01:47
in the middle of a pandemic and protests?
31
107458
2476
ืžื—ื™ื™ื“ืงื™ื ืœื›ืจื™ืฉื™ื.
01:49
I've spent the last 20 years as a marine biologist and oceanographer,
32
109958
3810
ื”ืจื›ื‘ืชื™ ืฆื•ื•ืชื™ื ื‘ื™ืŸ ืชื—ื•ืžื™ื™ื
ืฉื‘ื ื• ืืช ืžืฆืœืžืช ืขื™ืŸ ื”ื›ืจื™ืฉ ื”ืจืืฉื•ื ื”
01:53
studying the ocean from all different perspectives,
33
113792
3059
ื›ื“ื™ ืœืจืื•ืช ืืช ื”ืขื•ืœื ืžื ืงื•ื“ืช ื”ืžื‘ื˜ ืฉืœ ื›ืจื™ืฉ,
01:56
from microbes to sharks.
34
116875
1851
ื•ืฉื™ืชืคืชื™ ืคืขื•ืœื” ืขื ืžื”ื ื“ืกื™ื
01:58
I've assembled interdisciplinary teams
35
118750
1893
ื›ื“ื™ ืœืชื›ื ืŸ ืจื•ื‘ื•ื˜ื™ื ื›ืœ ื›ืš ืขื“ื™ื ื™ื ืฉื”ื ืืคื™ืœื• ืœื ืžืœื—ื™ืฆื™ื ืžื“ื•ื–ื•ืช.
02:00
that have built the first shark-eye camera
36
120667
2142
02:02
to see the world from a shark's perspective,
37
122833
2226
ืื‘ืœ ื–ื” ืœื ื”ื™ื” ืขื“ 2018
02:05
and have collaborated with engineers
38
125083
1851
ื›ืฉื”ื™ื™ืชื™ ื‘ื—ื‘ืจื•ืชื ืืงื“ืžื™ืช
02:06
to design robots so gentle that they don't even stress a jellyfish.
39
126958
4893
ื‘ืžื›ื•ืŸ ืจื“ืงืœื™ืฃ ืœืžื—ืงืจ ืžืชืงื“ื
ืฉื”ื‘ื ืชื™ ืฉืื•ืœื™ ื”ื“ืจืš ื”ื›ื™ ื˜ื•ื‘ื” ืœื”ื‘ื™ืŸ ืืช ื”ืื•ืงื™ื™ื ื•ืก
02:11
But it wasn't until 2018
40
131875
2143
ื•ื”ืชื•ืฉื‘ื™ื ืฉืœื•
ืœื ื”ื™ืชื” ืจืง ืœืจืื•ืช ืืช ื”ืขื•ืœื ื“ืจืš ื”ืขื™ื ื™ื™ื ืฉืœื”ื,
02:14
when I was on fellowship
41
134042
1309
02:15
at the Radcliffe Institute for Advanced Study
42
135375
2434
ืืœื ืขืœ ื™ื“ื™ ื”ืื–ื ื” --
02:17
that I realized that perhaps the best way to understand the ocean
43
137833
3060
ืขืœ ื™ื“ื™ ื‘ืืžืช ืœื”ืงืฉื™ื‘ ืœืขื•ืžืง.
02:20
and its inhabitants
44
140917
1267
ื ืขืฉื™ืชื™ ืžืขื•ื ื™ื™ืŸ ื‘ืœื•ื•ื™ืชื ื™ ื–ืจืข ื›ืฉืฉืžืขืชื™ ืืช ื”ืงื•ืœื•ืช ืฉืœื”ื.
02:22
wasn't just by seeing the world through their eyes,
45
142208
3101
ื”ื ื ืฉืžืขื• ื›ืื™ืœื• ื”ื ืžื’ื™ืขื™ื ืžื™ืงื•ื ืื—ืจ;
02:25
but by listening --
46
145333
1310
02:26
by really, deeply listening.
47
146667
2142
ืฉื™ืจืช ืกื™ืจื ื•ืช ืฉืฉื•ื“ืจื” ืžืžืขืžืงื™ ื”ื™ื ื”ื—ืฉื•ื›ื™ื.
02:28
I became interested in sperm whales when I heard their sounds.
48
148833
3060
ืืœื” ืœื ื”ื™ื• ืฉื™ืจื™ ืœื•ื•ื™ืชื ื™ื ื”ืจืžื•ื ื™ื™ื
02:31
They sounded like they were coming from another universe;
49
151917
2726
02:34
a siren song being broadcast from the darkest reaches of the sea.
50
154667
4434
ืฉื”ื™ื™ืชื™ ืจื’ื™ืœ ืืœื™ื”ื.
ืืœื” ื ืฉืžืขื• ื™ื•ืชืจ ื›ืžื• ืฉื™ื“ื•ืจ ื“ื™ื’ื™ื˜ืœื™.
ื”ืจื›ื‘ื ื• ืืช ืฆื•ื•ืช ืคืจื•ื™ื™ืงื˜ CETI ื”ืขืชื™ื“ื™
02:39
These weren't the typical harmonious whale songs
51
159125
3393
ื•ื”ืชื—ืœื ื• ืœื“ื•ืŸ ืื™ืš ืœื”ืฉืชืžืฉ ื‘ื˜ื›ื ื•ืœื•ื’ื™ื•ืช ื”ื›ื™ ืžืชืงื“ืžื•ืช
02:42
that I had been accustomed to.
52
162542
1559
02:44
These sounded more like digital data transfer.
53
164125
3268
ื›ื“ื™ ืœืชืงืฉืจ ืขื ืœื•ื•ื™ืชื ื™ื.
ืื—ืช ืžื”ืžืกืงื ื•ืช ื”ืขื™ืงืจื™ื•ืช
02:47
We assembled the future Project CETI team
54
167417
2434
ื”ื™ืชื” ืฉืœืœื™ืžื•ื“ ืžื›ื•ื ื” ื”ื™ื” ืกื™ื›ื•ื™ ื‘ืืžืช ื˜ื•ื‘
02:49
and began discussing how to use the most advanced technologies
55
169875
3351
ืœื”ื‘ื ืช ื”ืชื‘ื ื™ื•ืช ืฉืœ ืชืงืฉื•ืจืช ืœื•ื•ื™ืชื ื™ ื–ืจืข.
02:53
to communicate with whales.
56
173250
2101
ื•ื”ื–ืžืŸ ืœื™ื™ืฉื ืืช ื”ื˜ื›ื ื•ืœื•ื’ื™ื•ืช ื”ืืœื• ื”ื™ื” ืขื›ืฉื™ื•.
02:55
One of the principal conclusions
57
175375
1559
02:56
was that machine learning had a really good chance
58
176958
2685
ืคื™ืฆื•ื— ืงื•ื“ ื”ืชืงืฉื•ืจืช ื”ื‘ื™ืŸ ืžื™ื ื™ืช
02:59
of understanding the patterns of sperm whale communication.
59
179667
2934
ืœื ืจืง ื ืจืื” ืืคืฉืจื™,
03:02
And the time to apply these technologies was now.
60
182625
3684
ื–ื” ื›ืžืขื˜ ื ืจืื” ื‘ืœืชื™ ื ืžื ืข.
ืื‘ืœ ืื™ืš ื ื™ืชื•ื— ืชื‘ื ื™ื•ืช ื™ืขื–ื•ืจ ืœื ื• ืœืชืงืฉืจ ืขื ื”ืœื•ื•ื™ืชื ื™ื
03:06
Cracking the interspecies communication code
61
186333
2726
ื•ื—ื™ื•ืช ืื—ืจื•ืช?
03:09
didn't just seem possible,
62
189083
3018
ื•ื‘ื›ืŸ, ื”ืฉืœื‘ ื”ืจืืฉื•ืŸ ื”ื•ื ืœื”ื‘ื™ืŸ ืืช ื”ืืœืžื ื˜ื™ื ืฉืœ ืชืงืฉื•ืจืช ืœื•ื•ื™ืชื ื™ ื–ืจืข.
03:12
it almost seemed inevitable.
63
192125
2268
03:14
But how can analyzing patterns help us converse with whales
64
194417
2851
ื”ืงื•ื“ืืก ื”ืืœื” ืฉืฉืžืขืชื ืœื ื ืจืื™ื ื›ืžื• ืžืฉืคื˜ื™ื ื›ืคื™ ืฉืื ื—ื ื• ืžื›ื™ืจื™ื ืื•ืชื,
03:17
and other animals?
65
197292
1267
03:18
Well, step one is to understand the elements of sperm whale communication.
66
198583
4393
ืื‘ืœ ื™ืฉ ืžื‘ื ื” ื‘ืจื•ืจ ืื™ืš ื”ื—ื™ื•ืช ื”ืืœื• ืžืชืงืฉืจื•ืช.
ืœื•ื•ื™ืชื ื™ ื–ืจืข ืฉื•ืœื—ื™ื ืงื•ื“ืืก ืื—ื“ ืœืฉื ื™
03:23
These codas you heard don't appear to be sentences as we know them,
67
203000
4059
ื‘ืจืฆืคื™ื,
ื•ื™ืฉ ื ื™ื‘ื™ื ืื–ื•ืจื™ื™ื ื›ืžื• ืžื‘ื˜ืื™ื ื‘ืจื™ื˜ื™ื ื•ืื•ืกื˜ืจืœื™ื.
03:27
but there's clear structure in how these animals communicate.
68
207083
2935
ื–ื• ื‘ื“ื™ื•ืง ื”ืกื™ื‘ื” ืฉืœืžื™ื“ืช ืžื›ื•ื ื” ื”ื™ื ื›ืœื™ ื›ืœ ื›ืš ื—ื–ืง.
03:30
Sperm whales send codas back and forth to each other
69
210042
2934
03:33
in sequences,
70
213000
1309
ื”ื’ื™ืฉื•ืช ื”ืืœื• ืžื ืชื—ื•ืช ืชื‘ื ื™ื•ืช ื•ื™ื—ืกื™ื ื•ืžืžืคื•ืช ืœื”ืŸ ืžืฉืžืขื•ืช.
03:34
and there are regional dialects like British and Australian accents.
71
214333
3976
ืจืง ืœืคื ื™ ื›ืžื” ืฉื ื™ื, ืžื“ืขื ื™ื ื”ืฉืชืžืฉื• ื‘ืœืžื™ื“ืช ืžื›ื•ื ื”
03:38
This is exactly why machine learning is such a powerful tool.
72
218333
3768
ื›ื“ื™ ืœืชืจื’ื ื‘ื™ืŸ ืฉืชื™ ืฉืคื•ืช ืื ื•ืฉื™ื•ืช ืœื ื™ื“ื•ืขื•ืช ืœื’ืžืจื™.
03:42
These approaches analyze patterns in relationship and map meaning to them.
73
222125
4018
ืœื ืขืœ ื™ื“ื™ ืฉื™ืžื•ืฉ ื‘ืื‘ืŸ ืจื•ื–ื˜ื” ืื• ืžื™ืœื•ืŸ,
03:46
Just a few years ago, scientists used machine learning
74
226167
2767
ืืœื ืขืœ ื™ื“ื™ ืžื™ืคื•ื™ื™ืŸ ื‘ืชื‘ื ื™ื•ืช ื‘ืžืจื—ื‘ื™ื ื‘ืžื™ืžื“ื™ื ื’ื‘ื•ื”ื™ื ื™ื•ืชืจ.
03:48
to translate between two totally unknown human languages.
75
228958
3810
ืื‘ืœ ื›ื“ื™ ืฉืœืžื™ื“ืช ืžื›ื•ื ื” ืชืขื‘ื•ื“ ื‘ืืคืงื˜ื™ื‘ื™ื•ืช,
03:52
Not by using a Rosetta Stone or a dictionary,
76
232792
2767
ื”ื™ื ืฆืจื™ื›ื” ืžื™ื“ืข --
03:55
but by mapping them on patterns in higher-dimensional space.
77
235583
4435
ื”ื™ื ืฆืจื™ื›ื” ื”ืจื‘ื” ื”ืจื‘ื” ืžื™ื“ืข.
ื‘ื—ืฆื™ ื”ืžืื” ื”ืื—ืจื•ื ื”,
ื—ื•ืงืจื™ื ื™ืžื™ื™ื ืืกืคื• ื‘ืฉืงื“ื ื•ืช
04:00
But for machine learning to work effectively,
78
240042
2267
04:02
it needs data --
79
242333
1310
04:03
it needs lots and lots of data.
80
243667
2767
ื•ื”ื•ืกื™ืคื• ื”ืขืจื•ืช ื™ื“ื ื™ื•ืช ืจืง ื›ืžื” ืืœืคื™ ืงื•ืœื•ืช ืฉืœ ืœื•ื•ื™ืชื ื™ ื–ืจืข,
04:06
In the past half-century,
81
246458
1726
ืื‘ืœ ื›ื“ื™ ืœืœืžื•ื“ ืชืงืฉื•ืจืช ืฉืœ ืœื•ื•ื™ืชื ื™ ื–ืจืข,
04:08
marine researchers have painstakingly collected
82
248208
3476
ื ืฆื˜ืจืš ืœืืกื•ืฃ ืžืœื™ื•ื ื™ื,
04:11
and hand annotated just a few thousand sperm whale vocalizations,
83
251708
4601
ืื ืœื ืขืฉืจื•ืช ืžืœื™ื•ื ื™ื
ืฉืœ ืงื•ืœื•ืช ืœื•ื•ื™ืชื ื™ ื–ืจืข ืขื ื”ืขืจื•ืช ืžืคื•ืจื˜ื•ืช
04:16
but in order to learn sperm whale communication,
84
256333
2310
ืฉืžืชืื™ืžื•ืช ืœื”ืชื ื”ื’ื•ืช.
04:18
we'll need to collect millions,
85
258667
2392
ื ืขืฉื” ืืช ื–ื” ืขื ืจื•ื‘ื•ื˜ื™ื ืื•ื˜ื•ื ื•ืžื™ื ืœื ืคื•ืœืฉื ื™ื™ื ืฉืฉื•ื—ื™ื ื‘ื—ื•ืคืฉื™ื•ืช,
04:21
if not tens of millions
86
261083
1976
ืจื—ืคื ื™ื ืื•ื•ื™ืจื™ื™ื-ื™ืžื™ื™ื
04:23
of carefully annotated sperm whale vocalizations
87
263083
2893
ืžืขืจื›ื™ื ื”ื™ื“ืจื•ืคื•ื ื™ื ืžื•ืจื›ื‘ื™ื ื‘ืงืจืงืขื™ืช
ื•ืขื•ื“.
04:26
correlated with behaviors.
88
266000
1893
04:27
We'll do it with noninvasive, autonomous, free-swimming robots,
89
267917
3142
ื ืขื‘ื•ื“ ืขื ื”ืฉื•ืชืคื™ื ื”ืงืจื•ื‘ื™ื ืฉืœื ื• ื‘ืคืจื•ื™ื™ืงื˜ ื“ื•ืžื™ื ื™ืงื” ืœืœื•ื•ื™ืชื ื™ ื–ืจืข
ื›ื“ื™ ืœื›ืกื•ืช ืฉื˜ื— ืฉืœ 20 ืงื™ืœื•ืžื˜ืจ ืจื‘ื•ืขื™ื
04:31
aerial-aquatic drones,
90
271083
1685
04:32
bottom-mounted hydrophone arrays
91
272792
1601
ืฉืžื‘ืงืจื™ื ื‘ื• ื™ื•ืชืจ ืž 25 ืžืฉืคื—ื•ืช ืžื•ื›ืจื•ืช ืฉืœ ืœื•ื•ื™ืชื ื™ ื–ืจืข.
04:34
and more.
92
274417
1267
04:35
We'll work with our close partners at the Dominica Sperm Whale Project
93
275708
3351
ืื ื—ื ื• ืขื•ืžื“ื™ื ืœื”ืชืžืงื“ ื‘ืชืงืฉื•ืจืช ื‘ื™ืŸ ืืžื”ื•ืช ืœื’ื•ืจื™ื,
04:39
to cover a 20-square-kilometer area
94
279083
2101
04:41
that is frequented by over 25 well-known families of sperm whales.
95
281208
4560
ื›ื“ื™ ืœืืžืŸ ืืช ืืœื’ื•ืจื™ืชืžื™ ืœื™ืžื•ื“ ื”ืžื›ื•ื ื” ืฉืœื ื•
ืœืœืžื•ื“ ืืช ืฉืคืช ื”ืœื•ื•ื™ืชื ื™ื ืžืœืžื˜ื” ืœืžืขืœื”.
04:45
We're going to put specific focus on the interactions of mothers and calfs,
96
285792
4642
ื›ืœ ื”ืžื™ื“ืข ื”ื–ื” ืฉื™ื”ื™ื” ืœื ื• ื™ื™ืฉืœื— ื“ืจืš ื”ืžืขืจื›ืช
ื•ื™ื ื•ืชื— ืขืœ ื™ื“ื™ ืฆื•ื•ืช ื”ืชืจื’ื•ื ืฉืœ ืคืจื•ื™ื™ืงื˜ CETI.
04:50
training our machine learning algorithms
97
290458
2185
ื”ืื•ื“ื™ื• ื”ืœื ืžืขื•ื‘ื“ ื•ืžื™ื“ืข ื”ื”ืงืฉืจ ื™ืขื‘ืจื• ื“ืจืš ืžื ื•ืข ืœื™ืžื•ื“ ื”ืžื›ื•ื ื” ืฉืœื ื•
04:52
to learn whale language from the bottom up.
98
292667
2601
04:55
All this data we'll have sent through a pipeline
99
295292
2309
ืฉื ืงื•ื“ื ื”ื•ื ื™ืžื•ื™ืŸ ืœืคื™ ืžื‘ื ื”.
04:57
and analyzed by the Project CETI translation team.
100
297625
2434
ืฆื•ื•ืช ื”ืœืฉื•ื ืื•ืช ื™ื—ืคืฉ ืื– ื“ื‘ืจื™ื ื›ืžื• ืชื—ื‘ื™ืจ
05:00
The raw audio and context data will go through our machine learning engine
101
300083
3976
ื•ื”ื–ื—ืช ื–ืžื ื™ื.
ืœื“ื•ื’ืžื”,
ืื ื ืžืฆื ืืจื•ืข ื‘ื• ืœื•ื•ื™ืชืŸ ื“ื™ื‘ืจ ืขืœ ืžืฉื”ื• ืฉืงืจื” ืืชืžื•ืœ,
05:04
where it's going to be first sorted by structure.
102
304083
2351
05:06
The linguistics team will then search for things like syntax
103
306458
2893
ื–ื” ืœื‘ื“ื• ื™ื”ื™ื” ืžืžืฆื ืขื™ืงืจื™,
05:09
and time displacement.
104
309375
1268
ืžืฉื”ื• ืฉืขื“ ืขื›ืฉื™ื• ื ืจืื” ืจืง ื‘ื‘ื ื™ ืื“ื.
05:10
For example,
105
310667
1267
05:11
if we find an event where a whale was talking about something yesterday,
106
311958
3810
ื•ื‘ืจื’ืข ืฉื‘ืืžืช ื ืฉืœื•ื˜ ื‘ื”ืงืฉื‘ื”,
05:15
that alone would be a major finding,
107
315792
2142
ื ื ืกื” ื‘ืืžืช ื‘ื–ื”ื™ืจื•ืช ืœืชืงืฉืจ ื—ื–ืจื”
05:17
something that has thus far only been shown in humans.
108
317958
3268
ืืคื™ืœื• ื‘ืจืžื” ื”ื›ื™ ื‘ืกื™ืกื™ืช.
ืœื‘ืกื•ืฃ, ืคืจื•ื™ื™ืงื˜ CETI ื™ื‘ื ื” ืคืœื˜ืคื•ืจืžื” ืคืชื•ื—ื”
05:21
And once we've really mastered listening,
109
321250
2309
05:23
we're going to try really carefully to talk back
110
323583
3226
ืฉื ื ื ื’ื™ืฉ ืืช ืžืขืจื›ื™ ื”ืžื™ื“ืข ืฉืœื ื• ืœืฆื™ื‘ื•ืจ,
05:26
even on the most simplistic level.
111
326833
2185
ื•ื ืขื•ื“ื“ ืงื”ื™ืœื” ื’ืœื•ื‘ืœื™ืช
ืฉืชืฆื˜ืจืฃ ืœืžืกืข ืœื”ื‘ื ื”.
05:29
Finally, Project CETI will build an open-source platform
112
329042
2726
ื”ื—ื™ื•ืช ื”ืืœื• ื™ื›ื•ืœื•ืช ืœื”ื™ื•ืช ื”ื™ืฆื•ืจื™ื ื”ื›ื™ ืื™ื ื˜ื™ืœื’ื ื˜ื™ื ืขืœ ื”ืคืœื ื˜ื”.
05:31
where we will make our data sets available to the public,
113
331792
2809
05:34
encouraging the global community
114
334625
2059
ื™ืฉ ืœื”ืŸ ื ืื•-ืงื•ืจื˜ืงืก ื•ืชืื™ ื›ื™ืฉื•ืจ --
05:36
to come along on this journey for understanding.
115
336708
2393
ืžื‘ื ื™ื ืฉื‘ืื ืฉื™ื ืฉื•ืœื˜ื™ื ื‘ืžื—ืฉื‘ื•ืช ื”ื’ื‘ื•ื”ื•ืช ืฉืœื ื•,
05:39
These animals could be the most intelligent beings on this planet.
116
339125
4393
ื”ืจื’ืฉื•ืช, ื”ื–ื›ืจื•ืŸ, ื”ืฉืคื” ื•ื”ืื”ื‘ื”.
05:43
They have a neocortex and spindle cells --
117
343542
2851
ื•ื›ืœ ื”ืคืœื˜ืคื•ืจืžื•ืช ืฉืื ื—ื ื• ืžืคืชื—ื™ื ื™ื›ื•ืœื•ืช ืœื”ื™ื•ืช ืžื™ื•ืฉืžื•ืช ืขืœ ื—ื™ื•ืช ืื—ืจื•ืช:
05:46
structure that in humans control our higher thoughts,
118
346417
3101
ืœืคื™ืœื™ื, ืฆื™ืคื•ืจื™ื,
05:49
emotions, memory, language and love.
119
349542
3226
ืงื•ืคื™ ืื“ื, ื“ื•ืœืคื™ื ื™ื --
ื‘ืขื™ืงืจื•ืŸ ื›ืœ ื—ื™ื”.
05:52
And all the platforms that we develop can be cross-applied to other animals:
120
352792
3684
ื•ื‘ืกื•ืฃ ืฉื ื•ืช ื” 60 ืฉืœ ื”ืžืื” ื” 20,
ื—ื‘ืจ ื”ืฆื•ื•ืช ืฉืœื ื•, ืจื•ื’โ€™ืจ ืคื™ื™ืŸ ื’ื™ืœื” ืฉืœื•ื•ื™ืชื ื™ื ืฉืจื™ื.
05:56
to elephants, birds,
121
356500
1601
05:58
primates, dolphins --
122
358125
1643
(ื”ืงืœื˜ื”: ืฉื™ืจืช ืœื•ื•ื™ืชื ื™ื)
05:59
essentially any animal.
123
359792
1517
ืžืžืฆื ืฉื”ืฆื™ืช ืืช ืชื ื•ืขืช ื”ืฆืœืช ื”ืœื•ื•ื™ืชื ื™ื
06:01
In the late 1960s,
124
361333
1643
ืฉื”ื•ื‘ื™ืœื” ืœืกื•ืฃ ืฆื™ื™ื“ ื”ืœื•ื•ื™ืชื ื™ื ื”ืžืกื™ื‘ื™
06:03
our team member, Roger Payne, discovered that whales sing.
125
363000
3976
ื•ืžื ืข ื”ื›ื—ื“ื” ืฉืœ ืžืกืคืจ ืžื™ื ื™ ืœื•ื•ื™ืชื ื™ื
06:07
(Recording: whale singing)
126
367000
1268
06:08
A finding that sparked the Save the Whales movement
127
368292
2642
ืจืง ืขืœ ื™ื“ื™ ื›ืš ืฉื”ืจืื• ืฉืœื•ื•ื™ืชื ื™ื ืฉืจื™ื.
06:10
led to the end of large-scale whaling
128
370958
2643
ื“ืžื™ื™ื ื• ืื ื ื•ื›ืœ ืœื”ื‘ื™ืŸ ืžื” ืฉื”ื ืื•ืžืจื™ื.
06:13
and prevented several whale species from extinction
129
373625
3476
ืขื›ืฉื™ื• ื”ื–ืžืŸ ืœืคืชื•ื— ืืช ื”ื“ื™ืืœื•ื’ ื”ืจื—ื‘ ื™ื•ืชืจ.
06:17
just by showing that whales sing.
130
377125
3143
ืขื›ืฉื™ื• ื”ื–ืžืŸ ืœื”ืงืฉื™ื‘ ืœืขื•ืžืง
06:20
Imagine if we could understand what they're saying.
131
380292
2476
ื•ืœื”ืจืื•ืช ืœื—ื™ื•ืช ื”ืงืกื•ืžื•ืช ื”ืืœื•,
06:22
Now is the time to open this larger dialogue.
132
382792
3642
ื•ืื—ื“ ืœืฉื ื™,
ื›ื‘ื•ื“ ื—ื“ืฉ ืฉื”ืชื’ืœื”.
06:26
Now is the time to listen deeply
133
386458
2643
ืชื•ื“ื” ืœื›ื.
06:29
and show these magical animals,
134
389125
1893
06:31
and each other,
135
391042
1851
06:32
newfound respect.
136
392917
1375
06:35
Thank you.
137
395417
1250
ืขืœ ืืชืจ ื–ื”

ืืชืจ ื–ื” ื™ืฆื™ื’ ื‘ืคื ื™ื›ื ืกืจื˜ื•ื ื™ YouTube ื”ืžื•ืขื™ืœื™ื ืœืœื™ืžื•ื“ ืื ื’ืœื™ืช. ืชื•ื›ืœื• ืœืจืื•ืช ืฉื™ืขื•ืจื™ ืื ื’ืœื™ืช ื”ืžื•ืขื‘ืจื™ื ืขืœ ื™ื“ื™ ืžื•ืจื™ื ืžื”ืฉื•ืจื” ื”ืจืืฉื•ื ื” ืžืจื—ื‘ื™ ื”ืขื•ืœื. ืœื—ืฅ ืคืขืžื™ื™ื ืขืœ ื”ื›ืชื•ื‘ื™ื•ืช ื‘ืื ื’ืœื™ืช ื”ืžื•ืฆื’ื•ืช ื‘ื›ืœ ื“ืฃ ื•ื™ื“ืื• ื›ื“ื™ ืœื”ืคืขื™ืœ ืืช ื”ืกืจื˜ื•ืŸ ืžืฉื. ื”ื›ืชื•ื‘ื™ื•ืช ื’ื•ืœืœื•ืช ื‘ืกื ื›ืจื•ืŸ ืขื ื”ืคืขืœืช ื”ื•ื•ื™ื“ืื•. ืื ื™ืฉ ืœืš ื”ืขืจื•ืช ืื• ื‘ืงืฉื•ืช, ืื ื ืฆื•ืจ ืื™ืชื ื• ืงืฉืจ ื‘ืืžืฆืขื•ืช ื˜ื•ืคืก ื™ืฆื™ืจืช ืงืฉืจ ื–ื”.

https://forms.gle/WvT1wiN1qDtmnspy7