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

76,718 views ใƒป 2021-04-28

TED


์•„๋ž˜ ์˜๋ฌธ์ž๋ง‰์„ ๋”๋ธ”ํด๋ฆญํ•˜์‹œ๋ฉด ์˜์ƒ์ด ์žฌ์ƒ๋ฉ๋‹ˆ๋‹ค.

๋ฒˆ์—ญ: riddler edward ๊ฒ€ํ† : JY Kang
00:12
You are about to hear the sounds of the largest-toothed predator
0
12375
3309
์ด์ œ ์—ฌ๋Ÿฌ๋ถ„๊ป˜ ๋“ค๋ ค๋“œ๋ฆด ์†Œ๋ฆฌ๋Š”
์ง€๊ตฌ ์ƒ ๊ฐ€์žฅ ํฐ ์ด๋นจ์„ ๊ฐ€์ง„ ํฌ์‹์ž๊ฐ€ ๋‚ด๋Š” ์†Œ๋ฆฌ์ž…๋‹ˆ๋‹ค.
00:15
on the planet:
1
15708
1268
์ด ๋™๋ฌผ์€ ํ•™๊ต ๋ฒ„์Šค๋ณด๋‹ค ํฌ๋ฉฐ
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
์•„๋งˆ๋„ ํ˜„์กดํ•˜๋Š” ๋ชจ๋“  ์˜์‚ฌ์†Œํ†ต ๋ฐฉ๋ฒ• ์ค‘
00:22
that has ever existed.
4
22458
2310
๊ฐ€์žฅ ๋ณต์žกํ•œ ํ˜•ํƒœ๋ฅผ ์‚ฌ์šฉํ•˜๋Š” ๋™๋ฌผ์ผ ๊ฒ๋‹ˆ๋‹ค.
00:24
(Video: whale clicking)
5
24792
6000
(์˜์ƒ: ๊ณ ๋ž˜ ์šธ์Œ ์†Œ๋ฆฌ)
(์˜์ƒ: ๊ณ ๋ž˜ ์šธ์Œ ์†Œ๋ฆฌ)
(์˜์ƒ: ๊ณ ๋ž˜ ์šธ์Œ ์†Œ๋ฆฌ)
00:43
These are the sounds of the mighty sperm whale,
6
43833
2518
์ด ์†Œ๋ฆฌ๋Š” ๊ฑฐ๋Œ€ํ•œ ํ–ฅ์œ ๊ณ ๋ž˜๊ฐ€ ๋‚ด๋Š” ์†Œ๋ฆฌ์ž…๋‹ˆ๋‹ค.
00:46
a fellow mammal that can dive almost a mile,
7
46375
2893
์ด ํฌ์œ ๋ฅ˜ ์นœ๊ตฌ๋“ค์€ ์•ฝ 1 ๋งˆ์ผ ์ •๋„๊นŒ์ง€ ์ž ์ˆ˜ํ•  ์ˆ˜ ์žˆ๊ณ ,
00:49
hold its breath for more than an hour
8
49292
2267
ํ•œ ์‹œ๊ฐ„ ์ด์ƒ ์ˆจ์„ ์ฐธ์„ ์ˆ˜ ์žˆ์ฃ .
00:51
and lives in these amazingly complex, matriarchal societies.
9
51583
3851
๊ทธ๋ฆฌ๊ณ  ๋งค์šฐ ๋ณต์žกํ•œ ๋ชจ๊ณ„ ์‚ฌํšŒ๋ฅผ ์ด๋ฃจ๋ฉฐ ์‚ด๊ณ  ์žˆ์Šต๋‹ˆ๋‹ค.
00:55
These clicks you heard,
10
55458
1310
๋ฐฉ๊ธˆ ๋“ค์œผ์‹  ๋”ธ๊น๊ฑฐ๋ฆฌ๋Š” ์†Œ๋ฆฌ๋Š”
00:56
called codas,
11
56792
1267
์ฝ”๋‹ค(coda)๋ผ๊ณ  ๋ถ€๋ฅด๋Š” ๊ฒƒ์œผ๋กœ,
00:58
are just a facet of what we know of their communication.
12
58083
3101
์šฐ๋ฆฌ๊ฐ€ ์•„๋Š” ๊ทธ๋“ค์˜ ์˜์‚ฌ์†Œํ†ต ๋ฐฉ์‹ ์ค‘ ์ผ๋ถ€์— ๋ถˆ๊ณผํ•ฉ๋‹ˆ๋‹ค.
01:01
We know these animals are communicating,
13
61208
2393
์šฐ๋ฆฌ๋Š” ์ด ๋™๋ฌผ๋“ค์ด ๋Œ€ํ™”๋ฅผ ํ•œ๋‹ค๋Š” ๊ฑด ์•Œ์ง€๋งŒ,
01:03
we just don't yet know what they're saying.
14
63625
2976
๋ญ๋ผ๊ณ  ๋งํ•˜๋Š”์ง€๋Š” ์•Œ์ง€ ๋ชปํ•ฉ๋‹ˆ๋‹ค.
01:06
Project CETI aims to find out.
15
66625
2268
CETI ํ”„๋กœ์ ํŠธ์˜ ๋ชฉํ‘œ๋Š” ๊ทธ๊ฑธ ์•Œ์•„๋‚ด๋Š” ๋ฐ ์žˆ์Šต๋‹ˆ๋‹ค.
01:08
Over the next five years,
16
68917
1559
ํ–ฅํ›„ 5๋…„๊ฐ„,
01:10
our team of AI specialists,
17
70500
1684
์ธ๊ณต์ง€๋Šฅ ์ „๋ฌธ๊ฐ€, ๋กœ๋ด‡ ๊ณตํ•™์ž,
01:12
roboticists, linguists
18
72208
1768
์–ธ์–ดํ•™์ž, ํ•ด์–‘ ์ƒ๋ฌผํ•™์ž๋กœ ๊ตฌ์„ฑ๋œ ์ €ํฌ ํŒ€์€
01:14
and marine biologists
19
74000
1434
01:15
aim to use the most cutting-edge technologies
20
75458
2310
์ตœ์ฒจ๋‹จ ๊ธฐ์ˆ ๋“ค์„ ์‚ฌ์šฉํ•˜์—ฌ
01:17
to make contact with another species,
21
77792
1892
๋‹ค๋ฅธ ์ข…๊ณผ ์ ‘์ด‰ํ•˜์—ฌ ์‹ ํ˜ธ๋ฅผ ๋ณด๋‚ด๊ณ 
01:19
and hopefully communicate back.
22
79708
3476
๊ฐ€๋Šฅํ•˜๋‹ค๋ฉด ๊ทธ๋“ค๊ณผ ๋Œ€ํ™”๋ฅผ ํ•ด๋ณด๋ ค๊ณ  ํ•ฉ๋‹ˆ๋‹ค.
01:23
We believe that by listening deeply to nature,
23
83208
2518
์šฐ๋ฆฌ๊ฐ€ ์ž์—ฐ์˜ ์†Œ๋ฆฌ์— ๊ท€ ๊ธฐ์šธ์ธ๋‹ค๋ฉด,
01:25
we can change our perspective of ourselves
24
85750
2476
์šฐ๋ฆฌ ์ž์‹ ์— ๋Œ€ํ•œ ๊ด€์ ์„ ๋ณ€ํ™”์‹œํ‚ค๊ณ 
01:28
and reshape our relationship with all life on this planet.
25
88250
5059
์ด ์ง€๊ตฌ ์ƒ ๋ชจ๋“  ์ƒ๋ฌผ๋“ค๊ณผ์˜ ๊ด€๊ณ„๋ฅผ ๊ฐœ์„ ํ•  ์ˆ˜ ์žˆ์„ ๊ฑฐ๋ผ ๋ฏฟ์Šต๋‹ˆ๋‹ค.
01:33
This of course seems like an impossible goal.
26
93333
3393
๊ทธ ๊ณผ์ •์ด ๋ถˆ๊ฐ€๋Šฅํ•œ ๋ชฉํ‘œ๋กœ ๋ณด์ผ ์ˆ˜๋„ ์žˆ์Šต๋‹ˆ๋‹ค.
01:36
People have been trying to make contact with other animals
27
96750
2768
์ง€๋‚œ ์ˆ˜๋ฐฑ ๋…„ ๊ฐ„ ์—ฌ๋Ÿฌ ์‚ฌ๋žŒ๋“ค์ด ๋‹ค๋ฅธ ๋™๋ฌผ๊ณผ์˜ ์†Œํ†ต์„ ์‹œ๋„ํ•ด์™”์Šต๋‹ˆ๋‹ค.
01:39
for hundreds of years.
28
99542
1309
01:40
How could we do what others could not,
29
100875
2393
๋‹ค๋ฅธ ์ด๋“ค์€ ๋ชปํ•œ ์ผ๋“ค์„ ์ €ํฌ๊ฐ€ ์–ด๋–ป๊ฒŒ ํ•  ์ˆ˜ ์žˆ๋Š”์ง€,
01:43
especially given that I'm sitting here on my couch in New York City
30
103292
4142
๊ทธ๊ฒƒ๋„ ๋‰ด์š•์˜ ์ œ ๋ฐฉ ์†ŒํŒŒ์— ์•‰์•„์„œ ์–ด๋–ป๊ฒŒ ๊ทธ๊ฒŒ ๊ฐ€๋Šฅํ•œ์ง€ ๊ถ๊ธˆํ•˜์‹œ๊ฒ ์ฃ ?
01:47
in the middle of a pandemic and protests?
31
107458
2476
์ฝ”๋กœ๋‚˜ ๋Œ€์œ ํ–‰๊ณผ ์‹œ์œ„ ํ˜„์žฅ ํ•œ๋ณตํŒ์—์„œ์š”.
01:49
I've spent the last 20 years as a marine biologist and oceanographer,
32
109958
3810
์ €๋Š” ์ง€๋‚œ 20๋…„๊ฐ„ ํ•ด์–‘ ์ƒ๋ฌผํ•™์ž์ด์ž ํ•ด์–‘ํ•™์ž๋กœ ์ผํ–ˆ์œผ๋ฉฐ,
01:53
studying the ocean from all different perspectives,
33
113792
3059
๋ฏธ์ƒ๋ฌผ์—์„œ ์ƒ์–ด๊นŒ์ง€ ๋‹ค์–‘ํ•œ ์‹œ๊ฐ์œผ๋กœ
01:56
from microbes to sharks.
34
116875
1851
๋ฐ”๋‹ค๋ฅผ ์—ฐ๊ตฌํ•ด์™”์Šต๋‹ˆ๋‹ค.
01:58
I've assembled interdisciplinary teams
35
118750
1893
์ €๋Š” ๋‹ค๋ถ„์•ผ ์—ฐ๊ตฌํŒ€์„ ์กฐ์งํ–ˆ๊ณ 
02:00
that have built the first shark-eye camera
36
120667
2142
์ƒ์–ด ๋ˆˆ ์นด๋ฉ”๋ผ๋ฅผ ์ตœ์ดˆ๋กœ ์ œ์ž‘ํ•˜์—ฌ
02:02
to see the world from a shark's perspective,
37
122833
2226
์ƒ์–ด์˜ ๊ด€์ ์—์„œ ๋ฐ”๋‹ท์† ์„ธ์ƒ์„ ๊ด€์ฐฐํ•˜๊ธฐ๋„ ํ–ˆ์Šต๋‹ˆ๋‹ค.
02:05
and have collaborated with engineers
38
125083
1851
๊ณตํ•™์ž๋“ค๊ณผ ํ˜‘๋ ฅํ•˜์—ฌ
02:06
to design robots so gentle that they don't even stress a jellyfish.
39
126958
4893
ํ•ดํŒŒ๋ฆฌ์กฐ์ฐจ ์ŠคํŠธ๋ ˆ์Šค๋ฅผ ๋ฐ›์ง€ ์•Š์„ ์ •๋„๋กœ ์‹ ์‚ฌ์ ์ธ ๋กœ๋ด‡์„ ๋””์ž์ธํ–ˆ์Šต๋‹ˆ๋‹ค.
02:11
But it wasn't until 2018
40
131875
2143
ํ•˜์ง€๋งŒ 2018๋…„๊นŒ์ง€
02:14
when I was on fellowship
41
134042
1309
๋ž˜๋“œํด๋ฆฌํ”„ ๊ณ ๋“ฑ์—ฐ๊ตฌ์†Œ์—์„œ ๋ฐ•์‚ฌํ›„ ๊ณผ์ •์„ ๋ณด๋‚ด๊ณ  ์žˆ์œผ๋ฉด์„œ
02:15
at the Radcliffe Institute for Advanced Study
42
135375
2434
02:17
that I realized that perhaps the best way to understand the ocean
43
137833
3060
๋ฐ”๋‹ค์™€ ํ•ด์–‘ ์ƒ๋ฌผ๋“ค์„ ์ดํ•ดํ•˜๋Š” ๊ฐ€์žฅ ์ข‹์€ ๋ฐฉ๋ฒ•์€
02:20
and its inhabitants
44
140917
1267
๊ทธ๋“ค์˜ ๋ˆˆ์œผ๋กœ ์„ธ์ƒ์„ ๋ณด๊ธฐ๋งŒ ํ•˜๋Š” ๊ฒƒ์ด ์•„๋‹ˆ๋ผ
02:22
wasn't just by seeing the world through their eyes,
45
142208
3101
02:25
but by listening --
46
145333
1310
๊ทธ๋“ค์˜ ์†Œ๋ฆฌ๋ฅผ ๋“ฃ๋Š”,
02:26
by really, deeply listening.
47
146667
2142
๊ท€ ๊ธฐ์šธ์—ฌ ๋“ฃ๋Š” ๊ฑฐ๋ผ๋Š” ๊ฑธ ๊นจ๋‹ฌ์•˜์Šต๋‹ˆ๋‹ค.
02:28
I became interested in sperm whales when I heard their sounds.
48
148833
3060
ํ–ฅ์œ ๊ณ ๋ž˜๊ฐ€ ๋‚ด๋Š” ์†Œ๋ฆฌ๋ฅผ ๋“ค์—ˆ์„ ๋•Œ ๊ทธ๋“ค์— ๋Œ€ํ•œ ๊ด€์‹ฌ์ด ์ƒ๊ฒผ์Šต๋‹ˆ๋‹ค.
02:31
They sounded like they were coming from another universe;
49
151917
2726
๋งˆ์น˜ ๋‹ค๋ฅธ ์„ธ๊ณ„์—์„œ ๋‚˜๋Š” ์†Œ๋ฆฌ ๊ฐ™์•˜์ฃ .
02:34
a siren song being broadcast from the darkest reaches of the sea.
50
154667
4434
๋ฐ”๋‹ค ๊นŠ์ˆ™ํ•œ ๊ณณ ์„ธ์ด๋ Œ์˜ ๋…ธ๋žซ์†Œ๋ฆฌ๋ฅผ ๋ฐฉ์†กํ•˜๊ณ  ์žˆ๋Š” ๊ฒƒ ๊ฐ™์•˜์Šต๋‹ˆ๋‹ค.
02:39
These weren't the typical harmonious whale songs
51
159125
3393
์ œ๊ฐ€ ์ง€๊ธˆ๊นŒ์ง€ ๋“ค์–ด์™”๋˜ ์—ฌ๋Ÿฌ ๊ณ ๋ž˜๋“ค์˜ ๋“ฃ๊ธฐ ์ข‹์€ ๋…ธ๋ž˜๋“ค๊ณผ๋Š”
02:42
that I had been accustomed to.
52
162542
1559
์ „ํ˜€ ๋‹ค๋ฅธ ์†Œ๋ฆฌ์˜€์Šต๋‹ˆ๋‹ค.
02:44
These sounded more like digital data transfer.
53
164125
3268
๊ทธ ์†Œ๋ฆฌ๋Š” ๋งˆ์น˜ ๋””์ง€ํ„ธ ์ •๋ณด๋ฅผ ์ „์†กํ•˜๋Š” ๊ฒƒ ๊ฐ™์•˜์Šต๋‹ˆ๋‹ค.
02:47
We assembled the future Project CETI team
54
167417
2434
์šฐ๋ฆฌ๋Š” ๋ฏธ๋ž˜ ํ”„๋กœ์ ํŠธ CETI ํŒ€์„ ๊ตฌ์„ฑํ–ˆ๊ณ 
02:49
and began discussing how to use the most advanced technologies
55
169875
3351
์ตœ์‹  ๊ธฐ์ˆ ์„ ํ™œ์šฉํ•ด์„œ ๊ณ ๋ž˜์™€ ์†Œํ†ตํ•  ์ˆ˜ ์žˆ๋Š” ๋ฐฉ๋ฒ•์„
02:53
to communicate with whales.
56
173250
2101
๋…ผ์˜ํ•˜๊ธฐ ์‹œ์ž‘ํ–ˆ์ฃ .
02:55
One of the principal conclusions
57
175375
1559
์ฃผ์š” ๊ฒฐ๋ก  ์ค‘ ํ•˜๋‚˜๋Š”
02:56
was that machine learning had a really good chance
58
176958
2685
ํ–ฅ์œ  ๊ณ ๋ž˜์˜ ์˜์‚ฌ์†Œํ†ต ํŒจํ„ด์„ ์ดํ•ดํ•˜๋Š” ๋ฐ์—
02:59
of understanding the patterns of sperm whale communication.
59
179667
2934
๋จธ์‹ ๋Ÿฌ๋‹์ด ํ™œ์šฉ ๊ฐ€๋Šฅ์„ฑ์ด ๋†’๋‹ค๋Š” ๊ฒƒ์ด์—ˆ์Šต๋‹ˆ๋‹ค.
03:02
And the time to apply these technologies was now.
60
182625
3684
์ด๋Ÿฐ ๊ธฐ์ˆ ์„ ์‚ฌ์šฉํ•  ์‹œ๊ธฐ๊ฐ€ ๋ฐ”๋กœ ์ง€๊ธˆ์ด์—ˆ์Šต๋‹ˆ๋‹ค.
03:06
Cracking the interspecies communication code
61
186333
2726
๋‘ ์ข… ์‚ฌ์ด์˜ ํ†ต์‹  ์•”ํ˜ธ ํ•ด๋… ์ž‘์—…์€
03:09
didn't just seem possible,
62
189083
3018
์ง€๊ธˆ๊นŒ์ง„ ๋ถˆ๊ฐ€๋Šฅํ•ด ๋ณด์˜€์ง€๋งŒ
03:12
it almost seemed inevitable.
63
192125
2268
๊ผญ ํ•ด์•ผ ํ•˜๋Š” ์ผ์ฒ˜๋Ÿผ ๋˜์–ด๊ฐ€๊ณ  ์žˆ์—ˆ์Šต๋‹ˆ๋‹ค.
03:14
But how can analyzing patterns help us converse with whales
64
194417
2851
ํ•˜์ง€๋งŒ ํŒจํ„ด์„ ๋ถ„์„ํ•˜๋Š” ๊ฒƒ์œผ๋กœ
์–ด๋–ป๊ฒŒ ๊ณ ๋ž˜๋‚˜ ๋‹ค๋ฅธ ์ƒ๋ฌผ๊ณผ ์˜์‚ฌ์†Œํ†ต์„ ํ•  ์ˆ˜ ์žˆ์„๊นŒ์š”?
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
์šฐ์„ , ์ฒซ ๋‹จ๊ณ„๋Š”
ํ–ฅ์œ  ๊ณ ๋ž˜ ์†Œํ†ต๋ฐฉ์‹์˜ ๊ตฌ์„ฑ ์š”์†Œ๋ฅผ ์ดํ•ดํ•˜๋Š” ๊ฒƒ์ž…๋‹ˆ๋‹ค.
๋“ค๋ ค๋“œ๋ฆฐ ์ฝ”๋‹ค๋Š” ์•Œ ์ˆ˜ ์—†๋Š” ๋ฌธ์žฅ์ฒ˜๋Ÿผ ๋ณด์ด์ง€๋งŒ,
03:23
These codas you heard don't appear to be sentences as we know them,
67
203000
4059
03:27
but there's clear structure in how these animals communicate.
68
207083
2935
๋™๋ฌผ๋“ค์ด ์†Œํ†ตํ•˜๋Š” ๋ฐฉ์‹์—๋Š” ๋ถ„๋ช…ํžˆ ์–ด๋–ค ๊ตฌ์กฐ๊ฐ€ ์กด์žฌํ•ฉ๋‹ˆ๋‹ค.
03:30
Sperm whales send codas back and forth to each other
69
210042
2934
ํ–ฅ์œ  ๊ณ ๋ž˜๋Š” ์ผ์ • ์ˆœ์„œ์˜ ์ฝ”๋‹ค๋ฅผ ์„œ๋กœ ์ฃผ๊ณ  ๋ฐ›๊ธฐ๋„ ํ•˜๊ณ ,
03:33
in sequences,
70
213000
1309
03:34
and there are regional dialects like British and Australian accents.
71
214333
3976
์˜๊ตญ์ด๋‚˜ ํ˜ธ์ฃผ ๋ฐœ์Œ ๊ฐ™์€ ์ง€์—ญ ์‚ฌํˆฌ๋ฆฌ๋„ ์กด์žฌํ•ฉ๋‹ˆ๋‹ค.
03:38
This is exactly why machine learning is such a powerful tool.
72
218333
3768
๋จธ์‹  ๋Ÿฌ๋‹์ด ์ค‘์š”ํ•œ ๋„๊ตฌ์ธ ์ด์œ ๊ฐ€ ๋ฐ”๋กœ ์ด๊ฒƒ ๋•Œ๋ฌธ์ž…๋‹ˆ๋‹ค.
03:42
These approaches analyze patterns in relationship and map meaning to them.
73
222125
4018
์ด๋Ÿฐ ์ ‘๊ทผ๋ฒ•์€ ๋Œ€ํ™” ํŒจํ„ด์„ ๋ถ„์„ํ•˜๊ณ  ๊ฐ ํŒจํ„ด์ด ์–ด๋–ค ์˜๋ฏธ์ธ์ง€ ๋งคํ•‘ํ•ด์ค๋‹ˆ๋‹ค.
03:46
Just a few years ago, scientists used machine learning
74
226167
2767
๋ช‡ ๋…„ ์ „์—๋Š”,
๋ฏธ์ง€์˜ ์–ธ์–ด ๋‘ ๊ฐœ๋ฅผ ๋ฒˆ์—ญํ•˜๊ธฐ ์œ„ํ•ด ๋จธ์‹  ๋Ÿฌ๋‹์ด ์‚ฌ์šฉ๋œ ์—ฐ๊ตฌ๋„ ์žˆ์—ˆ์Šต๋‹ˆ๋‹ค.
03:48
to translate between two totally unknown human languages.
75
228958
3810
03:52
Not by using a Rosetta Stone or a dictionary,
76
232792
2767
๋กœ์ œํƒ€ ์Šคํ†ค์ด๋‚˜ ์‚ฌ์ „์„ ์‚ฌ์šฉํ•˜์ง€ ์•Š๊ณ ,
03:55
but by mapping them on patterns in higher-dimensional space.
77
235583
4435
๊ณ ์ฐจ์› ๊ณต๊ฐ„์—์„œ ํŒจํ„ด ๋ณ„๋กœ 1๋Œ€1 ๋งคํ•‘์„ ํ•ด์„œ ๋ฒˆ์—ญ์„ ์‹œ๋„ํ–ˆ์ฃ .
04:00
But for machine learning to work effectively,
78
240042
2267
ํ•˜์ง€๋งŒ ๋จธ์‹  ๋Ÿฌ๋‹์„ ํšจ์œจ์ ์œผ๋กœ ์‚ฌ์šฉํ•˜๊ธฐ ์œ„ํ•ด์„ 
04:02
it needs data --
79
242333
1310
๋ฐ์ดํ„ฐ๊ฐ€ ํ•„์š”ํ•ฉ๋‹ˆ๋‹ค.
04:03
it needs lots and lots of data.
80
243667
2767
์ •๋ง ๋งŽ์€ ๋ฐ์ดํ„ฐ๊ฐ€ ํ•„์š”ํ•˜์ฃ .
04:06
In the past half-century,
81
246458
1726
์ง€๋‚œ ๋ฐ˜ ์„ธ๊ธฐ๋™์•ˆ,
04:08
marine researchers have painstakingly collected
82
248208
3476
ํ•ด์–‘ ์กฐ์‚ฌ์›๋“ค์ด ๊ฐ–์€ ๋…ธ๋ ฅ์„ ๊ธฐ์šธ์—ฌ
04:11
and hand annotated just a few thousand sperm whale vocalizations,
83
251708
4601
ํ–ฅ์œ  ๊ณ ๋ž˜์˜ ์šธ์Œ ์†Œ๋ฆฌ ์ˆ˜์ฒœ ๊ฐœ๋ฅผ ๋ชจ์•„ ์ฃผ์„์„ ๋‹ฌ์•˜์ง€๋งŒ
04:16
but in order to learn sperm whale communication,
84
256333
2310
ํ–ฅ์œ  ๊ณ ๋ž˜์˜ ๋Œ€ํ™” ๋ฐฉ์‹์„ ๋ฐฐ์šฐ๋ ค๋ฉด ์ˆ˜๋ฐฑ๋งŒ ๊ฐœ์˜ ๋ฐ์ดํ„ฐ๊ฐ€ ํ•„์š”ํ•ฉ๋‹ˆ๋‹ค.
04:18
we'll need to collect millions,
85
258667
2392
04:21
if not tens of millions
86
261083
1976
ํ–ฅ์œ  ๊ณ ๋ž˜์˜ ํ–‰๋™๊ณผ ์—ฐ๊ณ„ํ•˜์—ฌ
04:23
of carefully annotated sperm whale vocalizations
87
263083
2893
์„ธ์‹ฌํ•˜๊ฒŒ ์ฃผ์„์„ ๋‹จ
๋ช‡ ์ฒœ ๋งŒ๊ฐœ์˜ ํ–ฅ์œ  ๊ณ ๋ž˜ ์šธ์Œ์†Œ๋ฆฌ๊นŒ์ง€๋Š” ์•„๋‹ˆ๋”๋ผ๋„์š”.
04:26
correlated with behaviors.
88
266000
1893
04:27
We'll do it with noninvasive, autonomous, free-swimming robots,
89
267917
3142
์šฐ๋ฆฌ๋Š” ๋ฐ์ดํ„ฐ๋ฅผ ์–ป๊ธฐ ์œ„ํ•ด ๋น„์นจํˆฌ์„ฑ, ์ž์œจํ˜• ์ž ์ˆ˜๋กœ๋ด‡๊ณผ
04:31
aerial-aquatic drones,
90
271083
1685
์ˆ˜๊ณต์–‘์šฉ ๋“œ๋ก ,
04:32
bottom-mounted hydrophone arrays
91
272792
1601
ํ•ด์ € ์ˆ˜์ค‘ ์ฒญ์Œ๊ธฐ,
04:34
and more.
92
274417
1267
๊ทธ๋ฆฌ๊ณ  ๊ธฐํƒ€ ๋“ฑ๋“ฑ์„ ์ด์šฉํ•  ๊ฒƒ์ž…๋‹ˆ๋‹ค.
04:35
We'll work with our close partners at the Dominica Sperm Whale Project
93
275708
3351
์šฐ๋ฆฌ๋Š” ๋„๋ฏธ๋‹ˆ์นด ํ–ฅ์œ  ๊ณ ๋ž˜ ํ”„๋กœ์ ํŠธ์— ์ฐธ์—ฌํ•˜๋Š” ๊ฐ€๊นŒ์šด ํŒŒํŠธ๋„ˆ์™€ ํ•จ๊ป˜
20 ํ‰๋ฐฉ ํ‚ฌ๋กœ๋ฏธํ„ฐ ๋ฉด์ ์— ๋‹ฌํ•˜๋Š”
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
25 ๋งˆ๋ฆฌ ์ด์ƒ์˜ ํ–ฅ์œ  ๊ณ ๋ž˜ ๊ฐ€์กฑ์ด ์ถœ๋ชฐํ•˜๋Š” ์ง€์—ญ์„ ์กฐ์‚ฌํ•  ์˜ˆ์ •์ž…๋‹ˆ๋‹ค.
04:45
We're going to put specific focus on the interactions of mothers and calfs,
96
285792
4642
์ €ํฌ๋Š” ํŠนํžˆ ์–ด๋ฏธ์™€ ์ž์‹๊ฐ„์˜ ๋Œ€ํ™”์— ์ดˆ์ ์„ ๋งž์ถœ ๊ณ„ํš์ด๋ฉฐ
04:50
training our machine learning algorithms
97
290458
2185
๋จธ์‹  ๋Ÿฌ๋‹ ์•Œ๊ณ ๋ฆฌ์ฆ˜์„ ํ›ˆ๋ จ์‹œ์ผœ
04:52
to learn whale language from the bottom up.
98
292667
2601
๊ณ ๋ž˜์˜ ์–ธ์–ด๋ฅผ ๊ธฐ์ดˆ๋ถ€ํ„ฐ ๋ฐฐ์›Œ๊ฐˆ ์ˆ˜ ์žˆ๋„๋ก ํ•  ์—์ •์ž…๋‹ˆ๋‹ค.
04:55
All this data we'll have sent through a pipeline
99
295292
2309
๋ชจ๋“  ์ •๋ณด๋Š” ์ „์šฉ ํ†ต์‹ ๋ง์œผ๋กœ ์ „๋‹ฌ๋˜์–ด
04:57
and analyzed by the Project CETI translation team.
100
297625
2434
CETI ํ”„๋กœ์ ํŠธ์˜ ๋ฒˆ์—ญ ํŒ€์ด ๋ถ„์„ํ•  ๊ฒƒ์ž…๋‹ˆ๋‹ค.
05:00
The raw audio and context data will go through our machine learning engine
101
300083
3976
๋…นํ™”๋œ ์Œ์„ฑ๊ณผ ์ฃผ๋ณ€ ํ™˜๊ฒฝ ๋ฐ์ดํ„ฐ๊ฐ€ ๋จธ์‹  ๋Ÿฌ๋‹ ์—”์ง„์— ์ž…๋ ฅ๋˜๋ฉด
05:04
where it's going to be first sorted by structure.
102
304083
2351
๋ถ„์„ ์—”์ง„์€ ์šฐ์„  ๊ทธ๊ฑธ ๊ตฌ์กฐ ๋ณ„๋กœ ๋ถ„๋ฅ˜ํ•˜๊ฒŒ ๋ฉ๋‹ˆ๋‹ค.
05:06
The linguistics team will then search for things like syntax
103
306458
2893
๊ทธ๋Ÿฌ๋ฉด ์–ธ์–ดํ•™์ž ํŒ€์€ ๊ตฌ๋ฌธ์ด๋‚˜ ์ „์œ„ ๋“ฑ์„ ํ™•์ธํ•˜์ฃ .
05:09
and time displacement.
104
309375
1268
05:10
For example,
105
310667
1267
์˜ˆ๋ฅผ ๋“ค์–ด,
05:11
if we find an event where a whale was talking about something yesterday,
106
311958
3810
๋งŒ์•ฝ ์šฐ๋ฆฌ๊ฐ€ ๊ณ ๋ž˜๊ฐ€ ์–ด์ œ ํ–ˆ๋˜ ๋ฌด์–ธ๊ฐ€์— ๋Œ€ํ•ด ์–˜๊ธฐํ•˜๋Š” ๊ฑธ ๋ฐœ๊ฒฌํ–ˆ๋‹ค๋ฉด,
05:15
that alone would be a major finding,
107
315792
2142
๊ทธ๊ฒƒ ์ž์ฒด๋งŒ์œผ๋กœ๋„ ํฐ ๋ฐœ๊ฒฌ์ด๋ฉฐ,
05:17
something that has thus far only been shown in humans.
108
317958
3268
์ง€๊ธˆ๊นŒ์ง€๋Š” ์ธ๋ฅ˜๋งŒ ๋ณด์ด๋˜ ํ–‰๋™์— ํ•ด๋‹นํ•ฉ๋‹ˆ๋‹ค.
05:21
And once we've really mastered listening,
109
321250
2309
๊ทธ๋ฆฌ๊ณ  ์ €ํฌ๊ฐ€ ์ •๋ง๋กœ ๋“ฃ๊ธฐ๋ฅผ ์™„๋ฃŒํ–ˆ๋‹ค๋ฉด,
05:23
we're going to try really carefully to talk back
110
323583
3226
์šฐ๋ฆฌ๋Š” ๋งค์šฐ ์กฐ์‹ฌ์Šค๋Ÿฝ๊ฒŒ ๋ง์„ ๊ฑฐ๋Š” ๊ฑธ ์‹œ์ž‘ํ•  ๊ฒƒ์ด๋ฉฐ
05:26
even on the most simplistic level.
111
326833
2185
๋งค์šฐ ๊ฐ„๋‹จํ•œ ๋‹จ์–ด๋ถ€ํ„ฐ ์–˜๊ธฐํ•  ๊ฒƒ์ž…๋‹ˆ๋‹ค.
05:29
Finally, Project CETI will build an open-source platform
112
329042
2726
์ตœ์ข… ๋‹จ๊ณ„๋กœ ํ”„๋กœ์ ํŠธ CETI๋Š” ์˜คํ”ˆ์†Œ์Šค ํ”Œ๋žซํผ์„ ๋งŒ๋“ค์–ด
05:31
where we will make our data sets available to the public,
113
331792
2809
๊ฑฐ๊ธฐ์— ์ˆ˜์ง‘๋œ ๋ฐ์ดํ„ฐ ์ž๋ฃŒ๋ฅผ ์˜ฌ๋ ค ๋Œ€์ค‘์—๊ฒŒ ๊ณต๊ฐœํ•  ๊ฒƒ์ด๋ฉฐ,
05:34
encouraging the global community
114
334625
2059
์ „ ์„ธ๊ณ„ ์ปค๋ฎค๋‹ˆํ‹ฐ๋“ค์ด
05:36
to come along on this journey for understanding.
115
336708
2393
์–ธ์–ด ์ดํ•ด๋ฅผ ์œ„ํ•œ ์—ฌ์ •์— ๋™์ฐธํ•˜๋„๋ก ์œ ๋„ํ•  ๊ฒƒ์ž…๋‹ˆ๋‹ค.
05:39
These animals could be the most intelligent beings on this planet.
116
339125
4393
์ด ๋™๋ฌผ๋“ค์€ ์ง€๊ตฌ ์ƒ์—์„œ ๊ฐ€์žฅ ๋˜‘๋˜‘ํ•œ ๋™๋ฌผ์ผ ์ˆ˜๋„ ์žˆ์Šต๋‹ˆ๋‹ค.
05:43
They have a neocortex and spindle cells --
117
343542
2851
๊ทธ๋“ค์€ ์‹ ํ”ผ์งˆ๊ณผ ๋ฐฉ์ถ”์„ธํฌ๋ฅผ ๊ฐ€์ง€๊ณ  ์žˆ์œผ๋ฉฐ --
05:46
structure that in humans control our higher thoughts,
118
346417
3101
์ด๊ฒƒ๋“ค์€ ์‚ฌ๋žŒ์˜ ๋ชธ์—์„œ ๊ณ ์ฐจ์›์ ์ธ ์‚ฌ๊ณ ๋ฅผ ๋‹ด๋‹นํ•˜์ฃ .
05:49
emotions, memory, language and love.
119
349542
3226
๊ฐ์ •, ๊ธฐ์–ต, ์–ธ์–ด ๊ทธ๋ฆฌ๊ณ  ์‚ฌ๋ž‘ ๊ฐ™์€ ๊ฒƒ์„์š”.
05:52
And all the platforms that we develop can be cross-applied to other animals:
120
352792
3684
์šฐ๋ฆฌ๊ฐ€ ๋งŒ๋“ค ๋ชจ๋“  ํ”Œ๋žซํผ์€ ๋‹ค๋ฅธ ๋™๋ฌผ๋“ค์—๊ฒŒ๋„ ์ ์šฉํ•  ์ˆ˜ ์žˆ์Šต๋‹ˆ๋‹ค:
05:56
to elephants, birds,
121
356500
1601
์ฝ”๋ผ๋ฆฌ๋‚˜, ์ƒˆ๋“ค,
05:58
primates, dolphins --
122
358125
1643
์˜์žฅ๋ฅ˜, ๋Œ๊ณ ๋ž˜ --
05:59
essentially any animal.
123
359792
1517
๊ธฐ๋ณธ์ ์œผ๋กœ ๋ชจ๋“  ๋™๋ฌผ์ด ๊ฐ€๋Šฅํ•˜์ฃ .
06:01
In the late 1960s,
124
361333
1643
1960๋…„ ํ›„๋ฐ˜,
์ €ํฌ ํŒ€์›์ธ ๋กœ์ € ํŽ˜์ธ์€ ๊ณ ๋ž˜์˜ ๋…ธ๋ž˜ ์†Œ๋ฆฌ๋ฅผ ๋ฐœ๊ฒฌํ–ˆ์Šต๋‹ˆ๋‹ค.
06:03
our team member, Roger Payne, discovered that whales sing.
125
363000
3976
(๋…น์Œ ํŒŒ์ผ:๊ณ ๋ž˜์˜ ๋…ธ๋žซ์†Œ๋ฆฌ)
06:07
(Recording: whale singing)
126
367000
1268
06:08
A finding that sparked the Save the Whales movement
127
368292
2642
๊ทธ ๋ฐœ๊ฒฌ์€ โ€˜๊ณ ๋ž˜ ์‚ด๋ฆฌ๊ธฐโ€™ ์šด๋™์— ๋ถˆ์„ ๋ถ™์˜€๊ณ 
06:10
led to the end of large-scale whaling
128
370958
2643
๋Œ€๊ทœ๋ชจ ํฌ๊ฒฝ์ด ์—†์–ด์ง€๋„๋ก ์ด๋Œ์—ˆ์œผ๋ฉฐ
06:13
and prevented several whale species from extinction
129
373625
3476
๋ช‡๋ช‡ ๊ณ ๋ž˜ ์ข…๋“ค์ด ๋ฉธ์ข… ๋˜๋Š” ๊ฑธ ๋ง‰์•„๋ƒˆ๋Š”๋ฐ
06:17
just by showing that whales sing.
130
377125
3143
์ด๋Š” ๋‹จ์ง€ ๊ณ ๋ž˜๊ฐ€ ๋…ธ๋ž˜๋ฅผ ๋ถ€๋ฅธ๋‹ค๋Š” ์‚ฌ์‹ค๋งŒ ๋ณด์—ฌ์ฃผ์—ˆ์„ ๋ฟ์ž…๋‹ˆ๋‹ค.
06:20
Imagine if we could understand what they're saying.
131
380292
2476
๋งŒ์•ฝ ๊ทธ๋“ค์ด ์–ธ์–ด๋ฅผ ์‚ฌ์šฉํ•œ๋‹ค๋Š” ์‚ฌ์‹ค์„ ์•Œ์•˜๋‹ค๊ณ  ์ƒ์ƒํ•ด๋ณด์„ธ์š”.
06:22
Now is the time to open this larger dialogue.
132
382792
3642
์ด์ œ๋Š” ๋” ํฐ ๋Œ€ํ™”์˜ ์žฅ์„ ์—ด์–ด์•ผ ํ•  ์‹œ๊ฐ„์ž…๋‹ˆ๋‹ค.
06:26
Now is the time to listen deeply
133
386458
2643
๊ทธ๋“ค์˜ ๋ชฉ์†Œ๋ฆฌ๋ฅผ ๊ท€ ๊ธฐ์šธ์—ฌ ๋“ฃ๋Š”๋‹ค๋ฉด
06:29
and show these magical animals,
134
389125
1893
์ด ๋†€๋ผ์šด ๋™๋ฌผ๋“ค์—๊ฒŒ,
06:31
and each other,
135
391042
1851
๊ทธ๋ฆฌ๊ณ  ์„œ๋กœ์—๊ฒŒ,
06:32
newfound respect.
136
392917
1375
์ƒˆ๋กœ์šด ์กด๊ฒฝ์‹ฌ์„ ๊ฐ–๊ฒŒ ๋  ๊ฒ๋‹ˆ๋‹ค.
06:35
Thank you.
137
395417
1250
๊ฐ์‚ฌํ•ฉ๋‹ˆ๋‹ค.
์ด ์›น์‚ฌ์ดํŠธ ์ •๋ณด

์ด ์‚ฌ์ดํŠธ๋Š” ์˜์–ด ํ•™์Šต์— ์œ ์šฉํ•œ YouTube ๋™์˜์ƒ์„ ์†Œ๊ฐœํ•ฉ๋‹ˆ๋‹ค. ์ „ ์„ธ๊ณ„ ์ตœ๊ณ ์˜ ์„ ์ƒ๋‹˜๋“ค์ด ๊ฐ€๋ฅด์น˜๋Š” ์˜์–ด ์ˆ˜์—…์„ ๋ณด๊ฒŒ ๋  ๊ฒƒ์ž…๋‹ˆ๋‹ค. ๊ฐ ๋™์˜์ƒ ํŽ˜์ด์ง€์— ํ‘œ์‹œ๋˜๋Š” ์˜์–ด ์ž๋ง‰์„ ๋”๋ธ” ํด๋ฆญํ•˜๋ฉด ๊ทธ๊ณณ์—์„œ ๋™์˜์ƒ์ด ์žฌ์ƒ๋ฉ๋‹ˆ๋‹ค. ๋น„๋””์˜ค ์žฌ์ƒ์— ๋งž์ถฐ ์ž๋ง‰์ด ์Šคํฌ๋กค๋ฉ๋‹ˆ๋‹ค. ์˜๊ฒฌ์ด๋‚˜ ์š”์ฒญ์ด ์žˆ๋Š” ๊ฒฝ์šฐ ์ด ๋ฌธ์˜ ์–‘์‹์„ ์‚ฌ์šฉํ•˜์—ฌ ๋ฌธ์˜ํ•˜์‹ญ์‹œ์˜ค.

https://forms.gle/WvT1wiN1qDtmnspy7