Digital humans that look just like us | Doug Roble

137,963 views ใƒป 2019-05-28

TED


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

๋ฒˆ์—ญ: Keungil KIM ๊ฒ€ํ† : Jihyeon J. Kim
00:13
Hello.
0
13937
1214
์•ˆ๋…•ํ•˜์„ธ์š”.
00:15
I'm not a real person.
1
15175
1466
์ „ ์ง„์งœ ์‚ฌ๋žŒ์ด ์•„๋‹™๋‹ˆ๋‹ค.
00:17
I'm actually a copy of a real person.
2
17119
2770
์‚ฌ์‹ค ์ „ ๋ณต์ œํ’ˆ์ด์ฃ .
00:19
Although, I feel like a real person.
3
19913
2553
๊ทธ๋ ‡์ง€๋งŒ ์ง„์งœ ์‚ฌ๋žŒ์ฒ˜๋Ÿผ ๋Š๊ปด์ ธ์š”.
00:22
It's kind of hard to explain.
4
22490
1906
์ด ์ƒํ™ฉ์„ ์„ค๋ช…ํ•˜๊ธฐ ์ข€ ์–ด๋ ค์šด๋ฐ์š”.
00:24
Hold on -- I think I saw a real person ... there's one.
5
24420
3790
์ž ์‹œ๋งŒ์š”. ์ง„์งœ ์‚ฌ๋žŒ์„ ๋ณธ ๊ฒƒ ๊ฐ™์•„์š”. ์—ฌ๊ธฐ ์žˆ๋„ค์š”.
00:28
Let's bring him onstage.
6
28697
1400
๊ทธ๋ฅผ ๋ฌด๋Œ€๋กœ ๋ถˆ๋Ÿฌ๋ณด๊ฒ ์Šต๋‹ˆ๋‹ค.
00:33
Hello.
7
33307
1150
์•ˆ๋…•ํ•˜์„ธ์š”.
00:35
(Applause)
8
35485
3647
(๋ฐ•์ˆ˜)
00:40
What you see up there is a digital human.
9
40300
3094
์—ฌ๋Ÿฌ๋ถ„์ด ๋ณด์‹  ๊ฑด ๋””์ง€ํ„ธ ์ธ๊ฐ„์ž…๋‹ˆ๋‹ค.
00:43
I'm wearing an inertial motion capture suit
10
43990
2984
์ €๋Š” ๊ด€์„ฑ ๋ชจ์…˜ ์บก์ฒ˜ ์˜์ƒ์„ ์ž…๊ณ  ์žˆ์Šต๋‹ˆ๋‹ค.
00:46
that's figuring what my body is doing.
11
46998
2579
์ด ์˜ท์€ ์ œ ๋ชธ์˜ ์›€์ง์ž„์„ ๊ณ„์‚ฐํ•ฉ๋‹ˆ๋‹ค.
00:49
And I've got a single camera here that's watching my face
12
49601
3825
๊ทธ๋ฆฌ๊ณ  ์ œ ์–ผ๊ตด ์•ž์— ์นด๋ฉ”๋ผ ํ•œ ๋Œ€๊ฐ€ ์žˆ๋Š”๋ฐ์š”.
00:53
and feeding some machine-learning software that's taking my expressions,
13
53450
4841
์ œ ํ‘œ์ • ์ดฌ์˜ํ•ด ๋จธ์‹ ๋Ÿฌ๋‹ ์†Œํ”„ํŠธ์›จ์–ด์— ์ „๋‹ฌํ•ฉ๋‹ˆ๋‹ค.
00:58
like, "Hm, hm, hm,"
14
58315
3579
"์Œ, ์Œ, ์Œ" ์ด๋Ÿฐ์‹์œผ๋กœ์š”.
01:02
and transferring it to that guy.
15
62379
1663
์ € ์นœ๊ตฌ์—๊ฒŒ ์ „๋„์‹œํ‚ค์ฃ .
01:05
We call him "DigiDoug."
16
65300
3342
์šฐ๋ฆฌ๋Š” ๊ทธ๋ฅผ "๋””์ง€๋”๊ทธ" ๋ผ๊ณ  ๋ถ€๋ฆ…๋‹ˆ๋‹ค.
01:09
He's actually a 3-D character that I'm controlling live in real time.
17
69292
4726
์ œ๊ฐ€ ์‹ค์‹œ๊ฐ„์œผ๋กœ ์กฐ์ข…ํ•˜๋Š” 3D ์บ๋ฆญํ„ฐ์ž…๋‹ˆ๋‹ค.
01:16
So, I work in visual effects.
18
76292
2324
์ €๋Š” ์‹œ๊ฐํšจ๊ณผ ๋ถ„์•ผ์—์„œ ์ผํ•˜๊ณ  ์žˆ์Šต๋‹ˆ๋‹ค.
01:19
And in visual effects,
19
79101
1167
์‹œ๊ฐํšจ๊ณผ์— ์žˆ์–ด
01:20
one of the hardest things to do is to create believable, digital humans
20
80292
5911
๊ฐ€์žฅ ์–ด๋ ค์šด ๋ถ€๋ถ„์€ ๊ด€๊ฐ๋“ค์ด ์‹ค์ œ๋ผ๊ณ  ์ƒ๊ฐํ•  ์ •๋„๋กœ ๊ทธ๋Ÿด๋“ฏํ•œ
01:26
that the audience accepts as real.
21
86227
2182
๋””์ง€ํ„ธ ์ธ๊ฐ„์„ ๊ตฌํ˜„ํ•˜๋Š” ๊ฒƒ์ž…๋‹ˆ๋‹ค.
01:28
People are just really good at recognizing other people.
22
88433
4524
์‚ฌ๋žŒ๋“ค์€ ๋‹ค๋ฅธ ์‚ฌ๋žŒ์„ ๊ตฌ๋ณ„ํ•˜๋Š” ๋Šฅ๋ ฅ์ด ์•„์ฃผ ๋›ฐ์–ด๋‚˜์ฃ .
01:32
Go figure!
23
92981
1150
์ œ๊ธธ!
01:35
So, that's OK, we like a challenge.
24
95577
3405
๊ทผ๋ฐ ๊ดœ์ฐฎ์•„์š”. ์šฐ๋ฆฌ๋Š” ๋„์ „์„ ์ข‹์•„ํ•˜๊ฑฐ๋“ ์š”.
01:39
Over the last 15 years,
25
99006
1841
์ง€๋‚œ 15๋…„ ๋™์•ˆ,
01:40
we've been putting humans and creatures into film
26
100871
4983
์šฐ๋ฆฌ๋Š” ์‹ค์ œ์™€ ๊ฐ™์€ ์‚ฌ๋žŒ๊ณผ ์ƒ๋ช…์ฒด๋“ค์„ ์˜ํ™”์—
01:45
that you accept as real.
27
105878
1739
ํˆฌ์ž…์‹œ์ผฐ์—ˆ์ฃ .
01:48
If they're happy, you should feel happy.
28
108712
2667
๊ทธ๋“ค์ด ํ–‰๋ณตํ•˜๋ฉด, ์—ฌ๋Ÿฌ๋ถ„๋„ ํ–‰๋ณตํ•˜๊ณ ,
01:51
And if they feel pain, you should empathize with them.
29
111982
5437
๊ทธ๋“ค์ด ๊ณ ํ†ต์„ ๋ฐ›๋Š”๋‹ค๋ฉด, ์—ฌ๋Ÿฌ๋ถ„๋„ ๋™์ผํ•œ ๊ฐ์ •์„ ๋Š๋‚๋‹ˆ๋‹ค.
01:58
We're getting pretty good at it, too.
30
118467
2190
์šฐ๋ฆฌ๋Š” ์ง€๊ธˆ๊นŒ์ง€ ์ž˜ ํ•ด์™”์ง€๋งŒ,
02:00
But it's really, really difficult.
31
120681
2746
์ •๋ง์ด์ง€ ๋งค์šฐ ํž˜๋“ค์—ˆ์Šต๋‹ˆ๋‹ค.
02:03
Effects like these take thousands of hours
32
123847
3214
์ด๋Ÿฌํ•œ ํšจ๊ณผ๋ฅผ ๋งŒ๋“œ๋Š”๋ฐ ์ˆ˜ ์ฒœ ์‹œ๊ฐ„์ด ๊ฑธ๋ฆฌ๊ณ ,
02:07
and hundreds of really talented artists.
33
127085
2667
์ˆ˜ ๋ฐฑ ๋ช…์˜ ์žฌ๋Šฅ ์žˆ๋Š” ์•„ํ‹ฐ์ŠคํŠธ๋“ค์ด ํ•„์š”ํ•ฉ๋‹ˆ๋‹ค.
02:10
But things have changed.
34
130792
1600
๊ทธ๋Ÿฌ๋‚˜ ์ƒํ™ฉ์€ ๋ณ€ํ–ˆ์Šต๋‹ˆ๋‹ค.
02:13
Over the last five years,
35
133014
1920
์ง€๋‚œ 5๋…„ ๋™์•ˆ,
02:14
computers and graphics cards have gotten seriously fast.
36
134958
4409
์ปดํ“จํ„ฐ์™€ ๊ทธ๋ž˜ํ”ฝ ์นด๋“œ ์†๋„๊ฐ€ ๋ง๋„ ์•ˆ ๋˜๊ฒŒ ๋นจ๋ผ์กŒ์ฃ .
02:20
And machine learning, deep learning, has happened.
37
140508
3971
๊ทธ๋ฆฌ๊ณ  '๋จธ์‹ ๋Ÿฌ๋‹', '๋”ฅ๋Ÿฌ๋‹'์ด ์ถœ์—ฐํ–ˆ์Šต๋‹ˆ๋‹ค.
02:25
So we asked ourselves:
38
145408
1233
๊ทธ๋ž˜์„œ ์šฐ๋ฆฌ๋Š” ์งˆ๋ฌธ์„ ๋˜์กŒ์Šต๋‹ˆ๋‹ค.
02:27
Do you suppose we could create a photo-realistic human,
39
147320
3778
์šฐ๋ฆฌ๊ฐ€ ์˜ํ™”์—์„œ์ฒ˜๋Ÿผ ์‹ค์ œ์™€ ๊ฐ™์ด ์‚ฌ๋žŒ์„
02:31
like we're doing for film,
40
151122
1624
์ฐฝ์กฐํ•ด ๋‚ผ ์ˆ˜ ์žˆ์„๊นŒ?
02:33
but where you're seeing the actual emotions and the details
41
153932
5647
๊ทธ๋ฆฌ๊ณ  ๊ทธ๊ฒƒ์„ ํ†ต์ œํ•˜๋Š” ์‚ฌ๋žŒ์˜ ๊ฐ์ •์„ ๋””์ง€ํ„ธ ์ธ๊ฐ„์—๊ฒŒ
02:39
of the person who's controlling the digital human
42
159603
4077
์ƒ์„ธํžˆ ํˆฌ์˜ํ•  ์ˆ˜ ์žˆ์„๊นŒ?
02:43
in real time?
43
163704
1174
์‹ค์‹œ๊ฐ„์œผ๋กœ?
02:45
In fact, that's our goal:
44
165704
1564
์‚ฌ์‹ค, ๊ทธ๊ฒŒ ์šฐ๋ฆฌ์˜ ๋ชฉํ‘œ์ž…๋‹ˆ๋‹ค.
02:47
If you were having a conversation with DigiDoug
45
167292
3761
๋งŒ์ผ ์—ฌ๋Ÿฌ๋ถ„์ด ๋””์ €๋”๊ทธ์™€ 1:1๋กœ
02:51
one-on-one,
46
171077
1237
๋Œ€ํ™”๋ฅผ ํ•œ๋‹ค๋ฉด,
02:53
is it real enough so that you could tell whether or not I was lying to you?
47
173331
5666
์ œ๊ฐ€ ๊ฑฐ์ง“๋ง์„ ํ•˜๋Š”์ง€ ์•ˆ ํ•˜๋Š”์ง€ ์ถฉ๋ถ„ํžˆ ์•Œ ์ˆ˜ ์žˆ์ง€ ์•Š์„๊นŒ์š”?
02:59
So that was our goal.
48
179934
1400
๊ทธ๊ฒŒ ์šฐ๋ฆฌ์˜ ๋ชฉํ‘œ์ž…๋‹ˆ๋‹ค.
03:02
About a year and a half ago, we set off to achieve this goal.
49
182601
4016
์•ฝ 1๋…„ ๋ฐ˜ ์ „์—, ์ด ๋ชฉํ‘œ๋ฅผ ์„ธ์› ์Šต๋‹ˆ๋‹ค.
03:06
What I'm going to do now is take you basically on a little bit of a journey
50
186641
3899
์ง€๊ธˆ๋ถ€ํ„ฐ ์—ฌ๋Ÿฌ๋ถ„๊ป˜ ์šฐ๋ฆฌ๊ฐ€ ํ˜„์žฌ์— ์ด๋ฅด๊ธฐ๊นŒ์ง€
03:10
to see exactly what we had to do to get where we are.
51
190564
3926
๋ฌด์—‡์„ ํ–ˆ๋Š”์ง€ ๋ณด์—ฌ๋“œ๋ฆฌ๊ฒ ์Šต๋‹ˆ๋‹ค.
03:15
We had to capture an enormous amount of data.
52
195832
3856
์šฐ๋ฆฌ๋Š” ์…€ ์ˆ˜ ์—†์„ ์ •๋„๋กœ ๋งŽ์€ ๋ฐ์ดํ„ฐ๋ฅผ ์ˆ˜์ง‘ํ–ˆ์Šต๋‹ˆ๋‹ค.
03:20
In fact, by the end of this thing,
53
200347
2714
์‚ฌ์‹ค, ์ด ์ž‘์—…์ด ๋๋‚ฌ์„ ๋•Œ,
03:23
we had probably one of the largest facial data sets on the planet.
54
203085
4563
์ง€๊ตฌ์ƒ์—์„œ ๊ฐ€์žฅ ํฐ ์–ผ๊ตด ๋ฐ์ดํ„ฐ๋ฅผ ํ™•๋ณดํ–ˆ์–ด์š”.
03:28
Of my face.
55
208038
1682
์ œ ์–ผ๊ตด์ž…๋‹ˆ๋‹ค.
03:29
(Laughter)
56
209744
2262
(์›ƒ์Œ)
03:32
Why me?
57
212030
1270
์™œ ์ €๋ƒ๊ณ ์š”?
03:33
Well, I'll do just about anything for science.
58
213324
2810
์ €๋Š” ๊ณผํ•™์— ๊ด€ํ•ด์„œ๋Š” ๋ญ๋“  ํ•˜๋Š” ์‚ฌ๋žŒ์ด๋‹ˆ๊นŒ์š”.
03:36
I mean, look at me!
59
216158
1948
์ ˆ ๋ณด์„ธ์š”!
03:38
I mean, come on.
60
218625
1150
์–ด์„œ์š”.
03:43
We had to first figure out what my face actually looked like.
61
223320
5460
์šฐ๋ฆฌ๋Š” ๊ฐ€์žฅ ๋จผ์ € ์ œ ์–ผ๊ตด์„ ๋ถ„์„ํ•ด์•ผ ํ–ˆ์Šต๋‹ˆ๋‹ค.
03:49
Not just a photograph or a 3-D scan,
62
229391
3027
๊ทธ๋ƒฅ ์‚ฌ์ง„์ด๋‚˜ 3D ์Šค์บ” ์ˆ˜์ค€์ด ์•„๋‹™๋‹ˆ๋‹ค.
03:52
but what it actually looked like in any photograph,
63
232442
3921
๋ชจ๋“  ์‚ฌ์ง„ ์†์—์„œ ๋น›์ด ์ œ ํ”ผ๋ถ€์™€ ๋‹ฟ์•„์„œ ์–ด๋–ป๊ฒŒ ์‹ค์ œ์ฒ˜๋Ÿผ
03:56
how light interacts with my skin.
64
236387
2460
๋‚˜ํƒ€๋‚˜๋Š”์ง€ ํ™•์ธํ•˜์ฃ .
03:59
Luckily for us, about three blocks away from our Los Angeles studio
65
239768
5249
๋‹คํ–‰ํžˆ, ์šฐ๋ฆฌ์˜ ๋กœ์Šค์—”์ ค๋ ˆ์Šค ์—ฐ๊ตฌ์†Œ์—์„œ ์„ธ ๋ธ”๋Ÿญ ์ฏค ๋–จ์–ด์ง„ ๊ณณ์—
04:05
is this place called ICT.
66
245041
2209
ICT๋ผ๊ณ  ๋ถˆ๋ฆฌ๋Š” ๊ณณ์ด ์žˆ์Šต๋‹ˆ๋‹ค.
04:07
They're a research lab
67
247708
1272
์„œ๋˜์บ˜๋ฆฌํฌ๋‹ˆ์•„ ๋Œ€ํ•™
04:09
that's associated with the University of Southern California.
68
249004
3403
์†Œ์†์˜ ์—ฐ๊ตฌ์†Œ์ž…๋‹ˆ๋‹ค.
04:12
They have a device there, it's called the "light stage."
69
252871
3555
"๋ผ์ดํŠธ ์Šคํ…Œ์ด์ง€"๋ผ๋Š” ์žฅ๋น„๊ฐ€ ๊ทธ๊ณณ์— ์„ค์น˜๋˜์–ด ์žˆ์Šต๋‹ˆ๋‹ค.
04:16
It has a zillion individually controlled lights
70
256450
3714
๊ฐœ๋ณ„์ ์œผ๋กœ ์ œ์–ด ๊ฐ€๋Šฅํ•œ ์ˆ˜ ๋งŒ๊ฐœ์˜ ์ „๋“ฑ๊ณผ ์ƒ๋‹น์ˆ˜์˜
04:20
and a whole bunch of cameras.
71
260188
1873
์นด๋ฉ”๋ผ๊ฐ€ ์žฅ์ฐฉ๋˜์–ด ์žˆ์Šต๋‹ˆ๋‹ค.
04:22
And with that, we can reconstruct my face under a myriad of lighting conditions.
72
262085
6091
์ด ์—„์ฒญ๋‚œ ๋น›์„ ์–ผ๊ตด์— ๋น„์ถ”๋ฉฐ ์ œ ์–ผ๊ตด์„ ์žฌ๊ตฌ์„ฑ ํ•ฉ๋‹ˆ๋‹ค.
04:29
We even captured the blood flow
73
269589
1582
์ œ๊ฐ€ ํ‘œ์ •์„ ์ง€์„ ๋•Œ์˜
04:31
and how my face changes when I make expressions.
74
271195
3092
์–ผ๊ตด ๋ณ€ํ™”๋ฟ๋งŒ ์•„๋‹ˆ๋ผ ํ˜ˆ๋ฅ˜๋งˆ์ €๋„ ์ธก์ •ํ•ฉ๋‹ˆ๋‹ค.
04:35
This let us build a model of my face that, quite frankly, is just amazing.
75
275454
5260
์ด ๊ณผ์ •์œผ๋กœ ์ œ ์–ผ๊ตด ๋ชจํ˜•์„ ๋งŒ๋“œ๋Š”๋ฐ, ์†”์งํžˆ ์ •๋ง ๋Œ€๋‹จํ•ด์š”.
04:41
It's got an unfortunate level of detail, unfortunately.
76
281399
4333
์•ˆํƒ€๊นŒ์šธ ์ •๋„๋กœ ์ž์„ธํ•ฉ๋‹ˆ๋‹ค.
04:45
(Laughter)
77
285756
1278
(์›ƒ์Œ)
04:47
You can see every pore, every wrinkle.
78
287058
3696
๋ชจ๋“  ๋ชจ๊ณต๊ณผ ์ฃผ๋ฆ„๊นŒ์ง€ ๋ณผ ์ˆ˜ ์žˆ์ฃ .
04:50
But we had to have that.
79
290778
1600
์ด๊ฑด ๋ฐ˜๋“œ์‹œ ํ•„์š”ํ•ฉ๋‹ˆ๋‹ค.
04:52
Reality is all about detail.
80
292960
2381
์„ธ๋ถ€์‚ฌํ•ญ์ด ์ƒ๋ช…์ด๊ธฐ ๋•Œ๋ฌธ์ž…๋‹ˆ๋‹ค.
04:55
And without it, you miss it.
81
295365
1867
๊ทธ๋ ‡์ง€ ์•Š์œผ๋ฉด, ์‹คํŒจํ•  ๊ฑฐ์˜ˆ์š”.
04:58
We are far from done, though.
82
298793
1547
๊ทธ๋Ÿฌ๋‚˜ ์•„์ง ๊ฐˆ ๊ธธ์ด ๋ฉ‰๋‹ˆ๋‹ค.
05:01
This let us build a model of my face that looked like me.
83
301363
3297
์ด๋ ‡๊ฒŒ ์ €์™€ ๋˜‘๊ฐ™์€ ์–ผ๊ตด ๋ชจํ˜•์„ ๋งŒ๋“ค์—ˆ์Šต๋‹ˆ๋‹ค.
05:05
But it didn't really move like me.
84
305196
2746
๊ทธ๋Ÿฐ๋ฐ ์ €์ฒ˜๋Ÿผ ์›€์ง์ด์ง€๋Š” ์•Š์•˜์Šต๋‹ˆ๋‹ค.
05:08
And that's where machine learning comes in.
85
308871
2713
์—ฌ๊ธฐ๊ฐ€ ๋ฐ”๋กœ ๋จธ์‹ ๋Ÿฌ๋‹์ด ํˆฌ์ž…๋˜๋Š” ์‹œ์ ์ž…๋‹ˆ๋‹ค.
05:11
And machine learning needs a ton of data.
86
311608
3204
๋จธ์‹ ๋Ÿฌ๋‹์€ ์ˆ˜ ๋งŽ์€ ๋ฐ์ดํ„ฐ๊ฐ€ ํ•„์š”ํ•ฉ๋‹ˆ๋‹ค.
05:15
So I sat down in front of some high-resolution motion-capturing device.
87
315497
4929
๊ทธ๋ž˜์„œ ๊ณ ํ•ด์ƒ๋„ ๋ชจ์…˜ ์บก์ฒ˜ ์žฅ๋น„๋กœ ์ธก์ • ์ž‘์—…์„ ํ–ˆ์Šต๋‹ˆ๋‹ค.
05:20
And also, we did this traditional motion capture with markers.
88
320450
4071
๊ทธ๋ฆฌ๊ณ  ์ ์„ ์ฐ๋Š” ์ „ํ†ต์ ์ธ ๋ชจ์…˜ ์บก์ฒ˜ ์ž‘์—…๋„ ์ง„ํ–‰ ํ–ˆ์Šต๋‹ˆ๋‹ค.
05:25
We created a whole bunch of images of my face
89
325696
2976
์šฐ๋ฆฌ๋Š” ์ œ ์–ผ๊ตด์˜ ํ˜•์ƒ์„ ๋‚˜ํƒ€๋‚ด๋Š” ์ ๊ตฐ์„ ๋งŒ๋“ค์–ด๊ฐ€๋ฉฐ
05:28
and moving point clouds that represented that shapes of my face.
90
328696
4087
์–ผ๊ตด ์ „์ฒด ์ด๋ฏธ์ง€๋ฅผ ๋งŒ๋“ค์—ˆ์Šต๋‹ˆ๋‹ค.
05:33
Man, I made a lot of expressions,
91
333996
2811
์ •๋ง, ์ˆ˜ ๋งŽ์€ ํ‘œ์ •์„ ์ง€์–ด์•ผํ–ˆ์ฃ .
05:36
I said different lines in different emotional states ...
92
336831
3460
๊ฐ๊ฐ์˜ ๊ฐ์ •์˜ ์ƒํƒœ์— ๋”ฐ๋ฅธ ๊ฐ๊ธฐ ๋‹ค๋ฅธ ํ‘œ์ • ๋ง์ž…๋‹ˆ๋‹ค.
05:40
We had to do a lot of capture with this.
93
340315
2667
๋ชจ๋“  ๊ฒƒ๋“ค์„ ์บก์ฒ˜ํ•ด์•ผ ํ–ˆ์ฃ .
05:43
Once we had this enormous amount of data,
94
343752
2891
์ด ์—„์ฒญ๋‚œ ๋ฐ์ดํ„ฐ๋ฅผ ๋ชจ์œผ๊ฒŒ ๋˜๋ฉด,
05:46
we built and trained deep neural networks.
95
346667
3775
์‹ฌ์ธต์‹ ๊ฒฝ๋ง์„ ๋งŒ๋“ค๊ณ  ํ›ˆ๋ จ์‹œํ‚ต๋‹ˆ๋‹ค.
05:51
And when we were finished with that,
96
351117
1746
๊ทธ๋ฆฌ๊ณ  ์ด ์ž‘์—…์„ ๋งˆ์น˜๋ฉด,
05:52
in 16 milliseconds,
97
352887
2444
0.016 ์ดˆ ์•ˆ์—
05:55
the neural network can look at my image
98
355355
3112
์‹ฌ์ธต์‹ ๊ฒฝ๋ง์€ ์ €์˜ ์ด๋ฏธ์ง€๋ฅผ ๋ณด๋ฉฐ,
05:58
and figure out everything about my face.
99
358491
2928
์ œ ์–ผ๊ตด์— ๊ด€ํ•œ ๋ชจ๋“  ๊ฒƒ์„ ๋ถ„์„ํ•ฉ๋‹ˆ๋‹ค.
06:02
It can compute my expression, my wrinkles, my blood flow --
100
362458
5476
์ œ ํ‘œ์ •๊ณผ ์ฃผ๋ฆ„, ํ•์ค„๊นŒ์ง€ ํŒŒ์•…ํ•  ์ˆ˜ ์žˆ์Šต๋‹ˆ๋‹ค.
06:07
even how my eyelashes move.
101
367958
2317
๋ˆˆ์น์˜ ์›€์ง์ž„๊นŒ์ง€๋„์š”.
06:10
This is then rendered and displayed up there
102
370925
2835
์‚ฌ์ „์— ์ €์žฅํ•ด ๋‘” ๋ชจ๋“  ์ƒ์„ธ ์ •๋ณด๋ฅผ ๊ฐ€์ง€๊ณ 
06:13
with all the detail that we captured previously.
103
373784
3222
์ด๋ฏธ์ง€๋ฅผ ๋งŒ๋“ค์–ด ํ™”๋ฉด์— ๋ณด์ด๊ฒŒ ํ•˜๋Š” ๊ฒ๋‹ˆ๋‹ค.
06:18
We're far from done.
104
378077
1334
์•„์ง ๊ฐˆ ๊ธธ์ด ๋งŽ์Šต๋‹ˆ๋‹ค.
06:20
This is very much a work in progress.
105
380188
2207
์•„์ง ๋งŽ์€ ์—ฐ๊ตฌ๊ฐ€ ์ง„ํ–‰ ์ค‘์ด์ฃ .
06:22
This is actually the first time we've shown it outside of our company.
106
382419
3321
์‚ฌ์‹ค, ์ฒ˜์Œ์œผ๋กœ ์šฐ๋ฆฌ ํšŒ์‚ฌ ๋ฐ–์—์„œ ๋ณด์—ฌ๋“œ๋ฆฌ๋Š” ๊ฒ๋‹ˆ๋‹ค.
06:25
And, you know, it doesn't look as convincing as we want;
107
385764
4194
์•„์ง๊นŒ์ง€ ์šฐ๋ฆฌ ๊ธฐ๋Œ€์— ๋ฏธ์น˜์ง€๋Š” ๋ชปํ•˜๊ณ  ์žˆ์Šต๋‹ˆ๋‹ค.
06:29
I've got wires coming out of the back of me,
108
389982
2183
์ œ ๋’ค๋กœ๋Š” ์ „์„ ์ด ๋‚˜์™€ ์žˆ๊ณ ,
06:32
and there's a sixth-of-a-second delay
109
392189
2038
์˜์ƒ์„ ์บก์ฒ˜ํ•˜๊ณ  ํ™”๋ฉด์— ๋ณด์ด๋Š”๋ฐ
06:34
between when we capture the video and we display it up there.
110
394251
4367
1/6์ดˆ ๊ฐ€๋Ÿ‰ ๋ฐ˜์‘ ์‹œ๊ฐ„์ด ๊ฑธ๋ฆฝ๋‹ˆ๋‹ค.
06:38
Sixth of a second -- that's crazy good!
111
398642
2816
1/6์ดˆ๋„ ์ƒ๋‹นํžˆ ์ข‹์€ ๊ฑฐ์ฃ !
06:41
But it's still why you're hearing a bit of an echo and stuff.
112
401911
3400
๊ทธ๋Ÿฐ๋ฐ ์ด ๋•Œ๋ฌธ์— ์•ฝ๊ฐ„์˜ ์šธ๋ฆผ์ด ๋“ค๋ฆฌ๋Š” ๊ฒƒ์ž…๋‹ˆ๋‹ค.
06:46
And you know, this machine learning stuff is brand-new to us,
113
406104
3889
๊ทธ๋ฆฌ๊ณ  ์ด ๋จธ์‹ ๋Ÿฌ๋‹์€ ์šฐ๋ฆฌ์—๊ฒŒ ์ƒˆ๋กœ์›Œ์„œ,
06:50
sometimes it's hard to convince to do the right thing, you know?
114
410017
4224
์ œ๋Œ€๋กœ ์ผ์„ ํ•˜๊ณ  ์žˆ๋Š”์ง€ ํ™•์‹ ํ•˜๊ธฐ ์–ด๋ ค์šธ ๋•Œ๊ฐ€ ์žˆ์Šต๋‹ˆ๋‹ค.
06:54
It goes a little sideways.
115
414265
2058
๊ฐ€๋” ์—‰๋šฑํ•œ ๊ฒฐ๊ณผ๊ฐ€ ๋‚˜์˜ค๊ธฐ๋„ ํ•˜์ฃ .
06:56
(Laughter)
116
416347
2422
(์›ƒ์Œ)
06:59
But why did we do this?
117
419538
3229
๊ทธ๋Ÿฐ๋ฐ ์šฐ๋ฆฌ๊ฐ€ ์™œ ์ด ์ผ์„ ํ–ˆ์„๊นŒ์š”?
07:03
Well, there's two reasons, really.
118
423077
2262
๋‘ ๊ฐ€์ง€ ์ด์œ ๊ฐ€ ์žˆ์Šต๋‹ˆ๋‹ค.
07:05
First of all, it is just crazy cool.
119
425363
2976
์ฒซ์งธ, ๊ทธ๋ƒฅ ์ด ์ผ ์ž์ฒด๊ฐ€ ๋ฉ‹์ง€๊ธฐ ๋•Œ๋ฌธ์ด์ฃ .
07:08
(Laughter)
120
428363
1008
(์›ƒ์Œ)
07:09
How cool is it?
121
429395
1253
์–ผ๋งˆ๋‚˜ ๋ฉ‹์žˆ๋ƒ๊ณ ์š”?
07:10
Well, with the push of a button,
122
430990
1992
๋ฒ„ํŠผ ํ•œ ๋ฒˆ ๋ˆŒ๋Ÿฌ์„œ,
07:13
I can deliver this talk as a completely different character.
123
433006
4007
์™„์ „ํžˆ ์ „ํ˜€ ๋‹ค๋ฅธ ์บ๋ฆญํ„ฐ๋กœ ๋ฐ”๊ฟ” ๊ฐ•์—ฐ์„ ํ•  ์ˆ˜ ์žˆ์Šต๋‹ˆ๋‹ค.
07:17
This is Elbor.
124
437823
2601
์ด๊ฑด ์—˜๋ณด์–ด(Elbor)์ž…๋‹ˆ๋‹ค.
07:22
We put him together to test how this would work
125
442037
2312
์šฐ๋ฆฌ๋Š” ๋‹ค๋ฅธ ํ˜•์ƒ์—๋Š” ์–ด๋–ป๊ฒŒ ์ ์šฉ๋˜๋Š”์ง€ ์‹œํ—˜ํ•˜๊ธฐ ์œ„ํ•ด
07:24
with a different appearance.
126
444373
2135
์—˜๋ณด์–ด๋ฅผ ํ•จ๊ป˜ ์‚ฌ์šฉํ•˜๊ณ  ์žˆ์Šต๋‹ˆ๋‹ค.
07:27
And the cool thing about this technology is that, while I've changed my character,
127
447450
4818
์ด ๊ธฐ์ˆ ์ด ํ™˜์ƒ์ ์ธ ๊ฒƒ์€, ์ œ๊ฐ€ ์บ๋ฆญํ„ฐ๋ฅผ ๋ณ€๊ฒฝํ•ด๋„,
07:32
the performance is still all me.
128
452292
3273
์—ฌ์ „ํžˆ ํ–‰๋™์€ ์ €์ž…๋‹ˆ๋‹ค.
07:35
I tend to talk out of the right side of my mouth;
129
455589
2674
์ €๋Š” ์ž…์˜ ์˜ค๋ฅธ์ชฝ์œผ๋กœ ์ด์•ผ๊ธฐ ํ•˜๋Š” ๊ฒฝํ–ฅ์ด ์žˆ์Šต๋‹ˆ๋‹ค.
07:38
so does Elbor.
130
458287
1579
์—˜๋ณด์–ด๋„ ๋งˆ์ฐฌ๊ฐ€์ง€์ฃ .
07:39
(Laughter)
131
459890
1150
(์›ƒ์Œ)
07:42
Now, the second reason we did this, and you can imagine,
132
462021
2790
์ด ์ผ์„ ํ•˜๋Š” ๋‘ ๋ฒˆ์งธ ์ด์œ ๋Š”, ์—ฌ๋Ÿฌ๋ถ„๋„ ์ถ”์ธกํ•  ์ˆ˜ ์žˆ์Šต๋‹ˆ๋‹ค.
07:44
is this is going to be great for film.
133
464835
2336
์˜ํ™”์— ๋งค์šฐ ๋›ฐ์–ด๋‚œ ๊ฐ•์ ์ด ์žˆ๊ธฐ ๋•Œ๋ฌธ์ž…๋‹ˆ๋‹ค.
07:47
This is a brand-new, exciting tool
134
467195
2701
์˜ˆ์ˆ ๊ฐ€๋‚˜ ๊ฐ๋…, ์Šคํ† ๋ฆฌํ…”๋Ÿฌ์—๊ฒŒ
07:49
for artists and directors and storytellers.
135
469920
4322
๋งค์šฐ ์ƒˆ๋กญ๊ณ , ํฅ๋ฏธ๋กœ์šด ์žฅ์น˜์ด์ฃ .
07:55
It's pretty obvious, right?
136
475131
1484
์ด๊ฑด ์•„์ฃผ ๋ถ„๋ช…ํ•ฉ๋‹ˆ๋‹ค. ๊ทธ๋ ‡์ฃ ?
07:56
I mean, this is going to be really neat to have.
137
476639
2462
์˜ํ™”์— ๋งค์šฐ ์œ ์šฉํ•  ๊ฒ๋‹ˆ๋‹ค.
07:59
But also, now that we've built it,
138
479125
2055
์šฐ๋ฆฌ๊ฐ€ ๋งˆ์นจ๋‚ด ๋งŒ๋“ค์–ด ๋ƒˆ์Šต๋‹ˆ๋‹ค.
08:01
it's clear that this is going to go way beyond film.
139
481204
2991
๊ทธ๋ฆฌ๊ณ  ์˜ํ™”๋ฅผ ๋›ฐ์–ด ๋„˜์„๊ฒŒ ํ™•์‹คํ•˜์ฃ .
08:05
But wait.
140
485510
1150
๊ทธ๋Ÿฐ๋ฐ ์ž ์‹œ๋งŒ์š”.
08:07
Didn't I just change my identity with the push of a button?
141
487653
3976
์ œ๊ฐ€ ๋ฒ„ํŠผ ํ•œ ๋ฒˆ ๋ˆŒ๋Ÿฌ, ์ €์˜ ์‹ ๋ถ„์„ ๋ฐ”๊พธ์ง€ ์•Š์•˜์Šต๋‹ˆ๊นŒ?
08:11
Isn't this like "deepfake" and face-swapping
142
491653
3033
์—ฌ๋Ÿฌ๋ถ„์€ "์˜์ƒ์กฐ์ž‘"์ด๋‚˜ ์–ผ๊ตด ๋ณ€ํ™˜๊ณผ ๊ฐ™์€ ๊ฒƒ ์•„๋‹ˆ๋ƒ? ๊ณ 
08:14
that you guys may have heard of?
143
494710
1561
๋ฌผ์œผ์‹ค ์ˆ˜ ์žˆ์Šต๋‹ˆ๋‹ค.
08:17
Well, yeah.
144
497208
1150
์˜ˆ. ๊ทธ๋ ‡์Šต๋‹ˆ๋‹ค.
08:19
In fact, we are using some of the same technology
145
499074
2952
์‚ฌ์‹ค, 'ํ˜•์ƒ๋ณ€ํ™˜' ์—์„œ ์ด์šฉํ•˜๋Š” ๊ฒƒ๊ณผ ์ผ๋ถ€ ๊ฐ™์€ ๊ธฐ์ˆ ์„ ์“ฐ๊ณ  ์žˆ์Šต๋‹ˆ๋‹ค.
08:22
that deepfake is using.
146
502050
1600
08:23
Deepfake is 2-D and image based, while ours is full 3-D
147
503954
4599
๊ทธ๋Ÿฐ๋ฐ ํ˜•์ƒ๋ณ€ํ™˜์€ 2D ์ด๋ฏธ์ง€ ๊ธฐ๋ฐ˜์ด๊ณ , ์šฐ๋ฆฌ ๊ฒƒ์€ ์™„์ „ 3D์ด์ฃ .
08:28
and way more powerful.
148
508577
2206
๊ทธ๋ฆฌ๊ณ  ํ›จ์”ฌ ๋” ๊ฐ•๋ ฅํ•ฉ๋‹ˆ๋‹ค.
08:31
But they're very related.
149
511204
1666
๊ทธ๋Ÿฌ๋‚˜ ์„œ๋กœ ์—ฐ๊ด€์„ฑ์€ ๋†’์Šต๋‹ˆ๋‹ค.
08:33
And now I can hear you thinking,
150
513680
1889
์ €๋Š” ์—ฌ๋Ÿฌ๋ถ„์˜ ์ƒ๊ฐ์„ ์•Œ ์ˆ˜๊ฐ€ ์žˆ์ฃ .
08:35
"Darn it!
151
515593
1278
"์ œ๊ธธ!
08:36
I though I could at least trust and believe in video.
152
516895
3801
์ €๋Š” ์ ์–ด๋„ ์˜์ƒ์„ ์‹ ๋ขฐํ•˜๊ฑฐ๋‚˜ ๋ฏฟ์„ ์ˆ˜ ์žˆ์Šต๋‹ˆ๋‹ค.
08:40
If it was live video, didn't it have to be true?"
153
520720
2827
๋งŒ์•ฝ, ์ด๊ฒƒ์ด ์‹ค์‹œ๊ฐ„ ์˜์ƒ์ด๋ผ๋ฉด, ๋ฏฟ์–ด์•ผ ํ•˜์ง€ ์•Š์„๊นŒ์š”?"
08:44
Well, we know that's not really the case, right?
154
524609
3522
์ž, ์šฐ๋ฆฌ๋Š” ๊ทธ๊ฒŒ ์‚ฌ์‹ค์ด ์•„๋‹ˆ๋ž€ ๊ฒƒ์„ ์•Œ๊ณ  ์žˆ์ฃ . ๊ทธ๋ ‡์ฃ ?
08:48
Even without this, there are simple tricks that you can do with video
155
528727
3810
์ด๊ฒŒ ์•„๋‹ˆ๋”๋ผ๋„, ์‹ค์ œ ์ƒํ™ฉ์„ ์™œ๊ณกํ•˜์—ฌ ์˜์ƒ์„ ๋‹ค๋ฅด๊ฒŒ ์กฐ์ž‘ ํ•  ์ˆ˜ ์žˆ๋Š”
08:52
like how you frame a shot
156
532561
2776
08:55
that can make it really misrepresent what's actually going on.
157
535361
4362
๋‹จ์ˆœํ•œ ์†์ž„์ˆ˜๋“ค์ด ์žˆ์Šต๋‹ˆ๋‹ค.
09:00
And I've been working in visual effects for a long time,
158
540263
3306
์ €๋Š” ์‹œ๊ฐํšจ๊ณผ ๋ถ„์•ผ์—์„œ ์˜ค๋žซ๋™์•ˆ ์ผ์„ ํ•ด์™”์Šต๋‹ˆ๋‹ค.
09:03
and I've known for a long time
159
543593
1932
๊ทธ๋ฆฌ๊ณ  ์กฐ๊ธˆ์˜ ๋…ธ๋ ฅ์œผ๋กœ
09:05
that with enough effort, we can fool anyone about anything.
160
545549
5226
๋ˆ„๊ตฌ๋ฅผ ๋ง‰๋ก ํ•˜๊ณ  ์†์ผ ์ˆ˜ ์žˆ๋‹ค๋Š” ๊ฑธ ์˜ค๋žซ๋™์•ˆ ์•Œ๊ณ  ์žˆ์—ˆ์Šต๋‹ˆ๋‹ค.
09:11
What this stuff and deepfake is doing
161
551546
2388
์šฐ๋ฆฌ์˜ ๊ธฐ์ˆ ๊ณผ ํ˜•์ƒ๋ณ€ํ™˜์€
09:13
is making it easier and more accessible to manipulate video,
162
553958
4611
์˜์ƒ์„ ๋” ์‰ฝ๊ณ  ๊ฐ„๋‹จํžˆ ์กฐ์ž‘ํ•  ์ˆ˜ ์žˆ๊ฒŒ ํ•ฉ๋‹ˆ๋‹ค.
09:18
just like Photoshop did for manipulating images, some time ago.
163
558593
5371
์–ผ๋งˆ ์ „๊นŒ์ง€ ํฌํ† ์ƒต์œผ๋กœ ์ด๋ฏธ์ง€๋ฅผ ์กฐ์ž‘ํ–ˆ๋˜ ๊ฒƒ์ฒ˜๋Ÿผ ๋ง์ด์ฃ .
09:25
I prefer to think about
164
565441
1298
์ €๋Š” ์ด ๊ธฐ์ˆ ์ด
09:26
how this technology could bring humanity to other technology
165
566763
5036
์ธ๊ฐ„์ ์ธ ๋ฉด์„ ๊ฐ€์ ธ๋‹ค ์ค„ ์ˆ˜ ์žˆ๊ณ , ์šฐ๋ฆฌ ์„œ๋กœ๋ฅผ ๋” ๊ฐ€๊นŒ์ด ํ•  ์ˆ˜ ์žˆ๊ฒŒ
09:31
and bring us all closer together.
166
571823
2294
ํ•œ๋‹ค๋Š” ์‚ฌ์‹ค์— ๊ด€์‹ฌ์ด ๋งŽ์Šต๋‹ˆ๋‹ค.
09:34
Now that you've seen this,
167
574141
2359
์—ฌ๋Ÿฌ๋ถ„์ด ๋ณด์‹  ๊ฒƒ์„ ํ†ตํ•ด
09:36
think about the possibilities.
168
576524
1902
๊ทธ ๊ฐ€๋Šฅ์„ฑ์„ ๊ฐ€๋Š ํ•ด ๋ณผ ์ˆ˜ ์žˆ์Šต๋‹ˆ๋‹ค.
09:39
Right off the bat, you're going to see it in live events and concerts, like this.
169
579810
4523
์ง€๊ธˆ ๋ฐ”๋กœ, ์—ฌ๋Ÿฌ๋ถ„์€ ์‹ค์‹œ๊ฐ„ ์ด๋ฒคํŠธ์™€ ์ฝ˜์„œํŠธ๋„ ๋ณผ ์ˆ˜๋„ ์žˆ์ฃ .
09:45
Digital celebrities, especially with new projection technology,
170
585612
4735
์‹ ๊ธฐ์ˆ ์„ ํ†ตํ•ด ์˜ํ™”์—์„œ์ฒ˜๋Ÿผ ๋””์ง€ํ„ธ ์œ ๋ช…์ธ์‚ฌ๋“ค์ด
09:50
are going to be just like the movies, but alive and in real time.
171
590371
3960
๋‚˜ํƒ€๋‚˜๊ณ , ์ด๋“ค์ด ์‹ค์‹œ๊ฐ„์œผ๋กœ ์‚ด์•„์žˆ๋“ฏ์ด ์›€์ง์ผ ๊ฒƒ์ž…๋‹ˆ๋‹ค.
09:55
And new forms of communication are coming.
172
595609
2733
๊ทธ๋ฆฌ๊ณ  ์ƒˆ๋กœ์šด ์ปค๋ฎค๋‹ˆ์ผ€์ด์…˜ ๋ฐฉ๋ฒ•์ด ๋“ฑ์žฅํ•  ๊ฒƒ์ž…๋‹ˆ๋‹ค.
09:59
You can already interact with DigiDoug in VR.
173
599088
4165
์ด๋ฏธ ์šฐ๋ฆฌ๋Š” VR์„ ํ†ตํ•ด ๋””์ง€๋”๊ทธ์™€ ์†Œํ†ตํ•  ์ˆ˜ ์žˆ์Šต๋‹ˆ๋‹ค.
10:03
And it is eye-opening.
174
603699
2270
๋†€๋ž„๋งŒํ•ฉ๋‹ˆ๋‹ค.
10:05
It's just like you and I are in the same room,
175
605993
3862
๋ฉ€๋ฆฌ ๋–จ์–ด์ ธ ์žˆ์–ด๋„, ๊ฐ™์€ ๋ฐฉ์— ์žˆ๋Š” ๊ฒƒ์ฒ˜๋Ÿผ ๋Š๋ผ๊ฒŒ ํ•ฉ๋‹ˆ๋‹ค.
10:09
even though we may be miles apart.
176
609879
2373
10:12
Heck, the next time you make a video call,
177
612276
2841
์•ž์œผ๋กœ ์˜์ƒํ†ตํ™”๋ฅผ ํ•˜๊ฒŒ ๋œ๋‹ค๋ฉด,
10:15
you will be able to choose the version of you
178
615141
3736
์—ฌ๋Ÿฌ๋ถ„์€ ๋‹ค๋ฅธ ์‚ฌ๋žŒ๋“ค์—๊ฒŒ ๋ณด์—ฌ์ค„ ์™ธ๋ชจ ๋ฒ„์ „ ํ•˜๋‚˜
10:18
you want people to see.
179
618901
1566
์„ ํƒํ•  ์ˆ˜ ์žˆ์„ ๊ฒƒ์ž…๋‹ˆ๋‹ค.
10:20
It's like really, really good makeup.
180
620974
2533
์ด๊ฑด ์ •๋ง์ด์ง€ ์ž˜๋œ ํ™”์žฅ๊ณผ๋„ ๊ฐ™์•„์š”.
10:24
I was scanned about a year and a half ago.
181
624853
3579
์•ฝ 1๋…„ ๋ฐ˜ ์ „์— ์ œ ๋ชจ์Šต์„ ์Šค์บ” ํ•ด๋†“์•˜์–ด์š”.
10:29
I've aged.
182
629068
1721
์ €๋Š” ๋‚˜์ด๊ฐ€ ๋“ค์—ˆ์ง€๋งŒ,
10:30
DigiDoug hasn't.
183
630813
1650
๋””์ง€๋”๊ทธ๋Š” ๊ทธ๋Œ€๋กœ ์ž…๋‹ˆ๋‹ค.
10:32
On video calls, I never have to grow old.
184
632798
3492
์˜์ƒ ํ†ตํ™”์—์„œ ์ €๋Š” ๋‚˜์ด๊ฐ€ ๋“ค์ง€ ์•Š์Šต๋‹ˆ๋‹ค.
10:38
And as you can imagine, this is going to be used
185
638322
3088
์—ฌ๋Ÿฌ๋ถ„์ด ์ƒ์ƒํ•  ์ˆ˜ ์žˆ๋“ฏ, ์ด ๊ธฐ์ˆ ์€ ๊ฐ€์ƒ์˜ ๋น„์„œ์—๊ฒŒ
10:41
to give virtual assistants a body and a face.
186
641434
3213
์–ผ๊ตด๊ณผ ๋ชธ์„ ๊ฐ€์ ธ๋‹ค ์ค„ ๊ฒƒ์ž…๋‹ˆ๋‹ค.
10:44
A humanity.
187
644671
1192
์ธ๊ฐ„์„ฑ์„ ๋ถ€์—ฌํ•˜๋Š” ๊ฑฐ์ฃ .
10:45
I already love it that when I talk to virtual assistants,
188
645887
2762
์ €๋Š” ๊ฐ€์ƒ ๋น„์„œ์™€ ๋Œ€ํ™”๋ฅผ ์ฆ๊น๋‹ˆ๋‹ค.
10:48
they answer back in a soothing, humanlike voice.
189
648673
2933
์ธ๊ฐ„๊ณผ ๊ฐ™์€ ๋ถ€๋“œ๋Ÿฌ์šด ๋ชฉ์†Œ๋ฆฌ๋กœ ๋Œ€๋‹ต์„ ํ•˜์ฃ .
10:51
Now they'll have a face.
190
651919
1776
์ด์ œ ๊ทธ๋“ค์€ ์–ผ๊ตด์„ ๊ฐ–๊ฒŒ ๋  ๊ฒƒ์ž…๋‹ˆ๋‹ค.
10:53
And you'll get all the nonverbal cues that make communication so much easier.
191
653719
4882
๋น„์–ธ์–ด์  ๋ฐ˜์‘์„ ํ†ตํ•ด ์˜์‚ฌ์†Œํ†ต์„ ํ›จ์”ฌ ์ˆ˜์›”ํ•˜๊ฒŒ ํ•  ์ˆ˜ ์žˆ์Šต๋‹ˆ๋‹ค.
11:00
It's going to be really nice.
192
660171
1420
์ด๊ฑด ๋งค์šฐ ์ข‹์•„์งˆ ๊ฑฐ์˜ˆ์š”.
11:01
You'll be able to tell when a virtual assistant is busy or confused
193
661615
3637
์•ž์œผ๋กœ ์—ฌ๋Ÿฌ๋ถ„์€ ๊ฐ€์ƒ์˜ ๋น„์„œ๊ฐ€ ๋ฐ”์˜๊ฑฐ๋‚˜, ๋‹นํ™ฉํ•ดํ•˜๊ฑฐ๋‚˜
11:05
or concerned about something.
194
665276
2680
์–ด๋–ค ๊ฒƒ์— ์—ผ๋ คํ•  ๋•Œ ์•Œ์•„์ฐจ๋ฆด ์ˆ˜ ์žˆ์„ ๊ฒ๋‹ˆ๋‹ค.
11:09
Now, I couldn't leave the stage
195
669694
2509
์ด์ œ, ์—ฌ๋Ÿฌ๋ถ„๊ป˜
11:12
without you actually being able to see my real face,
196
672227
2698
์ œ ์‹ค์ œ ์–ผ๊ตด์„ ๋ณด์—ฌ๋“œ๋ฆฌ๊ฒ ์Šต๋‹ˆ๋‹ค.
11:14
so you can do some comparison.
197
674949
1684
๋น„๊ตํ•ด๋ณด์„ธ์š”.
11:18
So let me take off my helmet here.
198
678573
1876
ํ—ฌ๋ฉง์„ ๋ฒ—์–ด ๋ณด๊ฒ ์Šต๋‹ˆ๋‹ค.
11:20
Yeah, don't worry, it looks way worse than it feels.
199
680473
4770
๊ฑฑ์ •ํ•˜์ง„ ๋งˆ์„ธ์š”. ์ƒ๊ฐ๋ณด๋‹ค ํ›จ์”ฌ ๋” ๋ชป์ƒ๊ฒผ์Šต๋‹ˆ๋‹ค.
11:25
(Laughter)
200
685267
2428
(์›ƒ์Œ)
11:29
So this is where we are.
201
689188
1698
ํ˜„์žฌ ์šฐ๋ฆฌ ์ˆ˜์ค€์€ ์ด๋ ‡์Šต๋‹ˆ๋‹ค.
11:30
Let me put this back on here.
202
690910
1604
๋‹ค์‹œ ์“ฐ๊ฒ ์Šต๋‹ˆ๋‹ค.
11:32
(Laughter)
203
692538
1950
(์›ƒ์Œ)
11:35
Doink!
204
695115
1186
๋ฐ”๋ณด!
11:37
So this is where we are.
205
697292
1600
์šฐ๋ฆฌ๋Š” ์—ฌ๊ธฐ๊นŒ์ง€ ์™”์Šต๋‹ˆ๋‹ค.
11:39
We're on the cusp of being able to interact with digital humans
206
699997
3701
์šฐ๋ฆฌ๋Š” ๋†€๋ž„ ๋งŒํผ ์‹ค์ œ์ ์ธ ๋””์ง€ํ„ธ ์ธ๊ฐ„๊ณผ ์ƒํ˜ธ์ž‘์šฉํ•  ์ˆ˜
11:43
that are strikingly real,
207
703722
2181
์žˆ๋Š” ๋‹จ๊ณ„์— ์ด๋ฅด๋ €์Šต๋‹ˆ๋‹ค.
11:45
whether they're being controlled by a person or a machine.
208
705927
3269
์‚ฌ๋žŒ์ด๋“  ๊ธฐ๊ณ„๋“  ๊ทธ ๊ฒƒ์„ ๋ˆ„๊ฐ€ ์กฐ์ข…ํ•˜๋Š๋ƒ์— ์ƒ๊ด€์—†์ด ๋ง์ด์ฃ .
11:49
And like all new technology these days,
209
709220
4375
์˜ค๋Š˜๋‚ ์˜ ๋ชจ๋“  ์ƒˆ๋กœ์šด ๊ธฐ์ˆ ์ฒ˜๋Ÿผ
11:54
it's going to come with some serious and real concerns
210
714531
4746
์šฐ๋ฆฌ๊ฐ€ ์•ž์œผ๋กœ ์ฒ˜๋ฆฌํ•ด์•ผ ํ•  ๋ฌธ์ œ์™€ ๊ฑฑ์ •๊ฑฐ๋ฆฌ๋“ค์ด ๋‚จ์•„ ์žˆ์Šต๋‹ˆ๋‹ค.
11:59
that we have to deal with.
211
719301
1734
12:02
But I am just so really excited
212
722017
2118
ํ•˜์ง€๋งŒ ์ €๋Š” ํ‰์ƒ ๋™์•ˆ
12:04
about the ability to bring something that I've seen only in science fiction
213
724159
5053
๊ณต์ƒ ๊ณผํ•™ ์†Œ์„ค์—์„œ๋งŒ ๋ณด๋˜ ๊ฒƒ์„ ํ˜„์‹ค๋กœ ๊ฐ€์ ธ์˜ฌ ์ˆ˜ ์žˆ์—ˆ๋‹ค๋Š” ๊ฒƒ์—
12:09
for my entire life
214
729236
2270
์ •๋ง ๊ธฐ์จ์„ ๋Š๋‚๋‹ˆ๋‹ค.
12:11
into reality.
215
731530
1328
12:13
Communicating with computers will be like talking to a friend.
216
733752
4222
์•ž์œผ๋กœ ์ปดํ“จํ„ฐ์™€ ์นœ๊ตฌ์ฒ˜๋Ÿผ ๋Œ€ํ™”๋ฅผ ํ•  ์ˆ˜ ์žˆ์Šต๋‹ˆ๋‹ค.
12:18
And talking to faraway friends
217
738323
2500
๋ฉ€๋ฆฌ ์žˆ๋Š” ์นœ๊ตฌ์™€ ๋Œ€ํ™”๋Š”
12:20
will be like sitting with them together in the same room.
218
740847
3273
๊ฐ™์€ ๋ฐฉ์—์„œ ํ•จ๊ป˜ ์•‰์•„์žˆ๋Š” ๊ฒƒ๊ณผ ๊ฐ™์ด ํ•  ์ˆ˜ ์žˆ์Šต๋‹ˆ๋‹ค.
12:24
Thank you very much.
219
744974
1308
๊ฐ์‚ฌํ•ฉ๋‹ˆ๋‹ค.
12:26
(Applause)
220
746306
6713
(๋ฐ•์ˆ˜)
์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