How AI could compose a personalized soundtrack to your life | Pierre Barreau

169,507 views ใƒป 2018-10-01

TED


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

๋ฒˆ์—ญ: Chan-Hong Park ๊ฒ€ํ† : Jihyeon J. Kim
00:12
About two and a half years ago, I watched this movie called "Her."
0
12913
3428
ํ•œ 2๋…„ ๋ฐ˜ ์ „์—, ์ €๋Š” "๊ทธ๋…€"๋ผ๋Š” ์˜ํ™”๋ฅผ ๋ณด๊ฒŒ ๋˜์—ˆ์Šต๋‹ˆ๋‹ค.
00:16
And it features Samantha, a superintelligent form of AI
1
16365
5127
๊ทธ ์˜ํ™”์— ์‚ฌ๋งŒ์‚ฌ๊ฐ€ ๋“ฑ์žฅํ•˜๋Š”๋ฐ ๊ทธ๋…€๋Š” ๋ฌผ๋ฆฌ์  ํ˜•ํƒœ๋ฅผ ๋ ์ง€ ์•Š๋Š”
00:21
that cannot take physical form.
2
21516
1760
๋›ฐ์–ด๋‚œ ํ˜•ํƒœ์˜ ์ธ๊ณต์ง€๋Šฅ์ด์—ˆ์ฃ .
00:23
And because she can't appear in photographs,
3
23858
2230
์˜ํ™”์—์„œ ๊ทธ๋…€๋Š” ์‚ฌ์ง„์— ๋‚˜ํƒ€๋‚  ์ˆ˜ ์—†์—ˆ๊ธฐ ๋•Œ๋ฌธ์—
00:26
Samantha decides to write a piece of music
4
26112
2016
์‚ฌ๋งŒ์‚ฌ๋Š” ์ž์‹ ์˜ ์ธ์ƒ์˜ ํ•œ ์ˆœ๊ฐ„์„ ๋งˆ์น˜ ์‚ฌ์ง„์ฒ˜๋Ÿผ ํ‘œํ˜„ํ•  ์ˆ˜ ์žˆ๋„๋ก
00:28
that will capture a moment of her life just like a photograph would.
5
28152
3466
์Œ์•… ํ•œ ๊ณก์„ ์ž‘๊ณกํ•˜๊ธฐ๋กœ ํ•ฉ๋‹ˆ๋‹ค.
00:32
As a musician and an engineer, and someone raised in a family of artists,
6
32953
4408
์Œ์•…๊ฐ€์ด์ž ๊ณตํ•™์ž ๊ทธ๋ฆฌ๊ณ  ์˜ˆ์ˆ ๊ฐ€ ์ง‘์•ˆ์—์„œ ์ž๋ผ์˜จ ์ €๋กœ์„œ๋Š”
00:37
I thought that this idea of musical photographs was really powerful.
7
37385
4176
์Œ์•…์œผ๋กœ ํ‘œํ˜„๋œ ์‚ฌ์ง„์ด๋ผ๋Š” ์•„์ด๋””์–ด๊ฐ€ ๋งค์šฐ ์ธ์ƒ์ด ๊นŠ์—ˆ์Šต๋‹ˆ๋‹ค.
00:41
And I decided to create an AI composer.
8
41955
2868
๊ทธ๋ฆฌ๊ณ  ์ €๋Š” ์ธ๊ณต์ง€๋Šฅ ์ž‘๊ณก๊ฐ€๋ฅผ ๋งŒ๋“ค๊ธฐ๋กœ ํ•˜์˜€์Šต๋‹ˆ๋‹ค.
00:44
Her name is AIVA, and she's an artificial intelligence
9
44847
3488
๊ทธ๋…€์˜ ์ด๋ฆ„์€ AIVA์ด๊ณ , ์—ฌํƒœ๊นŒ์ง€ ๊ฐ€์žฅ ์œ„๋Œ€ํ–ˆ๋˜
00:48
that has learned the art of music composition
10
48359
2393
3๋งŒ ๊ฐœ์˜ ๋ช…๊ณก๋“ค์„ ๋“ค์œผ๋ฉด์„œ ์Œ์•… ์ž‘๊ณก์˜ ์˜ˆ์ˆ ์„ ๋ฐฐ์šด
00:50
by reading over 30,000 scores of history's greatest.
11
50776
2785
์ธ๊ณต์ง€๋Šฅ์ž…๋‹ˆ๋‹ค.
00:54
So here's what one score looks like to the algorithm
12
54165
2456
๊ทธ๋ž˜์„œ ์ด๊ฒƒ์€ ๋งคํŠธ๋ฆญ์Šค ํ˜•ํƒœ๋กœ ๋‚˜ํƒ€๋‚ธ
00:56
in a matrix-like representation.
13
56645
2202
์•Œ๊ณ ๋ฆฌ์ฆ˜ ๊ด€์ ์—์„œ ๋ณด์ด๋Š” ํ•˜๋‚˜์˜ ๊ณก์ž…๋‹ˆ๋‹ค.
00:58
And here's what 30,000 scores,
14
58871
2246
์—ฌ๊ธฐ 3๋งŒ ๊ฐœ์˜ ์•…๋ณด๊ฐ€ ์žˆ๋Š”๋ฐ
๋ชจ์งœ๋ฅดํŠธ์™€ ๋ฒ ํ† ๋ฒค ํ’์˜ ๊ณก๋“ค์ด ๋‹จ์ผ ํ”„๋ ˆ์ž„์— ์žˆ๋Š” ๊ฒƒ์ฒ˜๋Ÿผ ๋ณด์ด์ฃ .
01:01
written by the likes of Mozart and Beethoven,
15
61141
2096
01:03
look like in a single frame.
16
63261
2031
01:07
So, using deep neural networks, AIVA looks for patterns in the scores.
17
67609
4340
AIVA๋Š” ์‹ฌ์ธต์‹ ๊ฒฝ๋ง์„ ์ด์šฉํ•˜์—ฌ ๊ณก๋“ค์—์„œ์˜ ํŒจํ„ด๋“ค์„ ๋ถ„์„ํ•ฉ๋‹ˆ๋‹ค.
01:12
And from a couple of bars of existing music,
18
72260
3563
๊ทธ๋ฆฌ๊ณ  ํ˜„์กดํ•˜๋Š” ๊ณก๋“ค์—์„œ ๋ช‡๊ฐœ์˜ ๋ฐ”๋ฅผ ์›์ฒœ์œผ๋กœ ํ•˜์—ฌ
01:15
it actually tries to infer what notes should come next in those tracks.
19
75847
3708
ํŠธ๋ž™ ๋’ค์— ์–ด๋– ํ•œ ์Œ๋“ค์ด ๋‚˜์˜ค๋Š” ๊ฒƒ์ด ์ ์ ˆํ• ์ง€๋ฅผ ์ถ”๋ก ํ•ฉ๋‹ˆ๋‹ค.
01:19
And once AIVA gets good at those predictions,
20
79887
2498
๊ทธ๋ฆฌ๊ณ  AIVA๊ฐ€ ๊ทธ๋Ÿฌํ•œ ์ถ”๋ก ๋Šฅ๋ ฅ์— ๋›ฐ์–ด๋‚˜๊ฒŒ ๋˜๋ฉด
01:22
it can actually build a set of mathematical rules
21
82409
3613
ํŠน์ • ์Œ์•…์˜ ์Šคํƒ€์ผ์— ๋”ฐ๋ผ์„œ ์ˆ˜ํ•™์ ์ธ ๊ทœ์น™๋“ค,
01:26
for that style of music
22
86046
1166
์ˆ˜ํ•™์ ์ธ ๊ทœ์น™๋“ค์˜ ์ง‘ํ•ฉ์„ ๊ตฌ์„ฑํ•˜์–ด ์ž์‹  ๊ณ ์œ ์˜ ๊ณก๋“ค์„ ๋งŒ๋“ค์–ด๋ƒ…๋‹ˆ๋‹ค.
01:27
in order to create its own original compositions.
23
87236
2788
01:30
And in a way, this is kind of how we, humans, compose music, too.
24
90490
3709
๊ทธ๋Ÿฐ๋ฐ ์ด๋Ÿฌํ•œ ๋ฐฉ๋ฒ•์€ ์‹ค์ œ ์šฐ๋ฆฌ ์ธ๊ฐ„๋„ ์‚ฌ์šฉํ•˜๋Š” ๋ฐฉ๋ฒ•์ด์ฃ .
01:34
It's a trial-and-error process,
25
94561
1492
์‹œํ–‰์ฐฉ์˜ค์˜ ๊ณผ์ •์ธ ๊ฑฐ์ฃ .
01:36
during which we may not get the right notes all the time.
26
96077
3008
๊ณผ์ • ์†์—์„œ ์šฐ๋ฆฌ๋Š” ๋ชจ๋‘ ์˜ณ์€ ์Œ๋งŒ ๋‚ผ ์ˆ˜๋Š” ์—†์Šต๋‹ˆ๋‹ค.
01:39
But we can correct ourselves,
27
99109
1389
ํ•˜์ง€๋งŒ ์šฐ๋ฆฌ๋Š” ์ˆ˜์ •ํ•  ์ˆ˜ ์žˆ์Šต๋‹ˆ๋‹ค.
01:40
either with our musical ear or our musical knowledge.
28
100522
3293
์Œ์•…์  ๊ท€๋ฅผ ํ†ตํ•ด์„œ, ๋˜๋Š” ์Œ์•…์  ์ง€์‹์„ ํ†ตํ•ด์„œ์š”.
01:45
But for AIVA, this process is taken from years and years of learning,
29
105495
4143
ํ•˜์ง€๋งŒ AIVA์—๊ฒŒ๋Š” ์ด๋Ÿฌํ•œ ๋‹ค๋…„์˜ ํ•™์Šต์˜ ๊ณผ์ •์„
01:49
decades of learning as an artist, as a musician and a composer,
30
109662
3262
์˜ˆ์ˆ ๊ฐ€๋กœ์„œ, ์Œ์•…๊ฐ€์ด์ž ์ž‘๊ณก๊ฐ€๋กœ์„œ์˜ ์„ธ์›”์„
01:52
down to a couple of hours.
31
112948
1733
๋‹จ ๋ช‡์‹œ๊ฐ„์œผ๋กœ ์ค„์ผ ์ˆ˜ ์žˆ์Šต๋‹ˆ๋‹ค.
01:55
But music is also a supersubjective art.
32
115030
2880
ํ•˜์ง€๋งŒ ์Œ์•…์€ ๋งค์šฐ ์ฃผ๊ด€์ ์ธ ์˜ˆ์ˆ ์ด์ฃ .
01:57
And we needed to teach AIVA
33
117934
1564
๊ทธ๋ž˜์„œ ์ €ํฌ๋Š” AIVA์—๊ฒŒ
01:59
how to compose the right music for the right person,
34
119522
2445
์–ด๋–ป๊ฒŒ ํ•˜๋ฉด ํŠน์ • ์‚ฌ๋žŒ์—๊ฒŒ ๋งž๋Š” ๊ณก์„ ์ž‘๊ณกํ• ์ง€ ๊ฐ€๋ฅด์ณ์ค˜์•ผ ํ–ˆ์Šต๋‹ˆ๋‹ค.
02:01
because people have different preferences.
35
121991
2141
์™œ๋ƒํ•˜๋ฉด ์‚ฌ๋žŒ๋“ค์„ ๊ฐ์ž ์„ ํ˜ธํ•˜๋Š” ๊ฒƒ์ด ๋‹ค๋ฅด๊ธฐ ๋•Œ๋ฌธ์ด์ง€์š”.
02:04
And to do that, we show to the algorithm over 30 different category labels
36
124156
4190
๊ทธ๊ฒƒ์„ ์‹คํ˜„ํ•˜๊ธฐ ์œ„ํ•˜์—ฌ ์ €ํฌ๋Š” ์•Œ๊ณ ๋ฆฌ์ฆ˜์—์„œ
๋ฐ์ดํ„ฐ๋ฒ ์ด์Šค์˜ ๋ชจ๋“  ๊ณก๋“ค์— 30๊ฐœ๊ฐ€ ๋„˜๋Š” ์นดํ…Œ๊ณ ๋ฆฌ ๋ผ๋ฒจ์„ ์ •ํ•˜์˜€์Šต๋‹ˆ๋‹ค.
02:08
for each score in our database.
37
128370
1945
02:10
So those category labels are like mood
38
130339
2516
์ด๋Ÿฌํ•œ ๋ผ๋ฒจ๋“ค์„ ์‚ฌ๋žŒ์˜ ๊ธฐ๋ถ„์ด๋‚˜,
02:12
or note density or composer style of a piece
39
132879
2920
์Œ ๋ฐ€๋„, ๋˜๋Š” ์ž‘๊ณก๊ฐ€์˜ ์„ฑํ–ฅ
02:15
or the epoch during which it was written.
40
135823
2524
์•„๋‹ˆ๋ฉด ์ž‘๊ณก ์‹œ๊ธฐ๊ฐ€ ๋  ์ˆ˜ ์žˆ๋Š” ๊ฑฐ์ฃ .
02:18
And by seeing all this data,
41
138371
1935
์ด๋Ÿฌํ•œ ๋ชจ๋“  ๋ฐ์ดํ„ฐ๋ฅผ ๋ณด๊ณ 
02:20
AIVA can actually respond to very precise requirements.
42
140330
3056
AIVA๋Š” ๋งค์šฐ ์ž์„ธํ•œ ์š”๊ตฌ์‚ฌํ•ญ์— ๋Œ€์‘ํ•  ์ˆ˜ ์žˆ์Šต๋‹ˆ๋‹ค.
02:23
Like the ones, for example, we had for a project recently,
43
143966
3103
์ตœ๊ทผ ์ €ํฌ๊ฐ€ ํ–ˆ๋˜ ํ”„๋กœ์ ํŠธ์—์„œ๋„ ์ด๋Ÿฌํ•œ ํŠน์ง•์„ ๋ณผ ์ˆ˜ ์žˆ์—ˆ๋Š”๋ฐ
02:27
where we were commissioned to create a piece
44
147093
3035
SF์˜ํ™” ๋Š๋‚Œ์˜ OST๊ณก์„ ๋งŒ๋“œ๋Š” ๊ณผ์ œ๋ฅผ ๋ฐ›์•˜์ฃ .
02:30
that would be reminiscent of a science-fiction film soundtrack.
45
150152
3027
02:33
And the piece that was created is called "Among the Stars"
46
153839
4500
๋งŒ๋“ค์–ด์ง„ ๊ทธ ์ž‘ํ’ˆ์€ "๋ณ„๋“ค ๊ณ์—์„œ"๋ผ๊ณ  ๋ถˆ๋ฆฝ๋‹ˆ๋‹ค.
02:38
and it was recorded with CMG Orchestra in Hollywood,
47
158363
3317
๊ทธ ๊ณก์€ ํ• ๋ฆฌ์šฐ๋“œ์˜ CMG ์˜ค์ผ€์ŠคํŠธ๋ผ์™€ ํ•จ๊ป˜ ๋…น์Œ๋˜์—ˆ์ฃ .
02:41
under great conductor John Beal,
48
161704
1714
ํ›Œ๋ฅญํ•œ ์ง€ํœ˜์ž ์กด ๋นŒ ์•„๋ž˜์—์„œ ๋ง์ด์ฃ .
02:43
and this is what they recorded, made by AIVA.
49
163442
3067
์ด๊ฒƒ์ด AIVA๊ฐ€ ๋งŒ๋“  ๊ณก์ž…๋‹ˆ๋‹ค.
02:47
(Music)
50
167657
7000
(์Œ์•…)
03:30
(Music ends)
51
210196
2190
(์Œ์•… ๋)
03:34
What do you think?
52
214719
1207
์–ด๋–ป๊ฒŒ ์ƒ๊ฐํ•˜์‹ญ๋‹ˆ๊นŒ?
03:35
(Applause)
53
215950
4380
(๋ฐ•์ˆ˜)
03:40
Thank you.
54
220354
1150
๊ฐ์‚ฌํ•ฉ๋‹ˆ๋‹ค.
03:42
So, as you've seen, AI can create beautiful pieces of music,
55
222001
4055
๋ณด์‹œ๋‹ค์‹œํ”ผ ์ธ๊ณต์ง€๋Šฅ์€ ์•„๋ฆ„๋‹ค์šด ๊ณก์„ ๋งŒ๋“ค ์ˆ˜ ์žˆ๊ณ 
03:46
and the best part of it
56
226080
1803
์—ฌ๊ธฐ์„œ ๊ฐ€์žฅ ์ข‹์€ ์ ์€
03:47
is that humans can actually bring them to life.
57
227907
2581
์ธ๊ฐ„์ด ์ด ์Œ์•…์„ ์‹ค์ œ๋กœ ์—ฐ์ฃผํ•  ์ˆ˜ ์žˆ๋‹ค๋Š” ๊ฑฐ์ฃ .
03:51
And it's not the first time in history
58
231506
1838
์ด๊ฒƒ์€ ๊ธฐ์ˆ ์ด ์ธ๊ฐ„์˜ ์ฐฝ์˜์„ฑ์„ ์ฆ์ง„์‹œํ‚จ ์ฒซ ๋ฒˆ์งธ ๊ฒฝ์šฐ๊ฐ€ ์•„๋‹™๋‹ˆ๋‹ค.
03:53
that technology has augmented human creativity.
59
233368
3344
03:56
Live music was almost always used in silent films
60
236736
3072
์‹คํ™ฉ ์Œ์•…์€ ๋ฌด์„ฑ ์˜ํ™”์—์„œ
03:59
to augment the experience.
61
239832
1666
๊ฒฝํ—˜์„ ํ™•๋Œ€์‹œํ‚ค๋ ค๊ณ  ์‚ฌ์šฉ๋์Šต๋‹ˆ๋‹ค.
04:01
But the problem with live music is that it didn't scale.
62
241522
3182
ํ•˜์ง€๋งŒ ์‹คํ™ฉ ์Œ์•…์€ ๊ทœ๋ชจ ์กฐ์ •์ด ์–ด๋ ต์Šต๋‹ˆ๋‹ค.
04:04
It's really hard to cram a full symphony into a small theater,
63
244728
3429
๊ตํ–ฅ์•…๋‹จ์„ ์ž‘์€ ๊ทน์žฅ์— ๋„ฃ๋Š” ๊ฒƒ์ด๋ž€ ์–ด๋ ค์šด ์ผ์ด์ฃ .
04:08
and it's really hard to do that for every theater in the world.
64
248181
2991
์ „ ์„ธ๊ณ„์˜ ๋ชจ๋“  ๊ทน์žฅ์—์„œ ๊ทธ๋ ‡๊ฒŒ ํ•˜๋Š” ๊ฒƒ๋„ ๋งค์šฐ ์–ด๋ ต์ฃ .
04:11
So when music recording was actually invented,
65
251196
2849
๊ทธ๋ž˜์„œ ์Œ์•… ๋…น์Œ์ด ์‹ค์ œ๋กœ ๋ฐœ๋ช…๋˜์—ˆ์„ ๋•Œ,
04:14
it allowed content creators, like film creators,
66
254069
2349
๊ทธ๊ฒƒ์€ ์˜ํ™”์™€ ๊ฐ™์€ ์ฝ˜ํ…์ธ  ์ œ์ž‘์ž๋“ค์ด
04:16
to have prerecorded and original music
67
256442
2786
์ž์‹ ๋“ค์˜ ์Šคํ† ๋ฆฌ์˜ ๊ฐ๊ฐ์˜ ํ”„๋ ˆ์ž„์—
04:19
tailored to each and every frame of their stories.
68
259252
2873
๋ฏธ๋ฆฌ ๋…น์Œ๋œ ๊ณ ์œ ์˜ ์Œ์•…์ด ๋‚˜์˜ฌ ์ˆ˜ ์žˆ๊ฒŒ๋” ํ•ด์ฃผ์—ˆ์Šต๋‹ˆ๋‹ค.
04:22
And that was really an enhancer of creativity.
69
262149
2626
๊ทธ๊ฒƒ์ด ์‹ค์ œ๋กœ ์ฐฝ์˜์„ฑ์„ ํ–ฅ์ƒ์‹œ์ผฐ์ฃ .
04:26
Two and a half years ago, when I watched this movie "Her,"
70
266617
3286
2๋…„ ๋ฐ˜ ์ „, ์ œ๊ฐ€ "๊ทธ๋…€"๋ผ๋Š” ์˜ํ™”๋ฅผ ๋ณด์•˜์„ ๋•Œ,
04:29
I thought to myself that personalized music
71
269927
2907
์ €๋Š” ๋งž์ถคํ˜• ์Œ์•…์ด ์•ž์œผ๋กœ์˜ ์Œ์•… ์†Œ๋น„์™€ ์ฐฝ์ž‘์—์„œ
04:32
would be the next single biggest change in how we consume and create music.
72
272858
4417
๊ฐ€์žฅ ํฐ ๋ณ€ํ™”๊ฐ€ ๋  ๊ฒƒ์ด๋ผ๊ณ  ์ƒ๊ฐํ–ˆ์Šต๋‹ˆ๋‹ค.
04:38
Because nowadays, we have interactive content, like video games,
73
278187
4222
์™œ๋ƒํ•˜๋ฉด ์š”์ฆ˜์€, ๋ช‡ ๋ฐฑ ์‹œ๊ฐ„์˜ ์ƒํ˜ธ์ž‘์šฉ์˜ ๋‚ด์šฉ์œผ๋กœ ๊ตฌ์„ฑ๋œ
04:42
that have hundreds of hours of interactive game plays,
74
282433
3015
๋น„๋””์˜ค๊ฒŒ์ž„๊ณผ ๊ฐ™์€ ์ฝ˜ํ…์ธ ๋Š” ์กด์žฌํ•˜๋Š”๋ฐ ๋ฐ˜๋ฉด์—
04:45
but only two hours of music, on average.
75
285472
2113
์ƒํ˜ธ์ž‘์šฉ์ด ์ผ์–ด๋‚˜๋Š” ์Œ์•…์€ 2์‹œ๊ฐ„ ์ •๋„๋งŒ ์กด์žฌํ•˜๊ธฐ ๋•Œ๋ฌธ์ž…๋‹ˆ๋‹ค.
04:47
And it means that the music loops and loops and loops
76
287609
2492
๊ทธ๊ฒƒ์€ ๊ทธ๋ ‡๋‹ค๋ฉด ๊ทธ ์Œ์•…์„ ๊ณ„์† ๋Œ๋ ค์„œ ๋ฐ˜๋ณตํ•ด์„œ ๋“ฃ๋Š”๋ฐ
04:50
over and over again, and it's not very immersive.
77
290125
2332
์ž˜ ๋ชฐ์ž…๋˜์ง€ ์•Š์ฃ .
04:52
So what we're working on is to make sure that AI can compose
78
292467
3951
๊ทธ๋ž˜์„œ ์ €ํฌ๋Š” ์ธ๊ณต์ง€๋Šฅ์ด ์ˆ˜๋ฐฑ ์‹œ๊ฐ„์˜ ๋งž์ถคํ˜• ์Œ์•…์„
04:56
hundreds of hours of personalized music
79
296442
2302
๋งŒ๋“ค ์ˆ˜ ์žˆ๊ฒŒ ํ•˜๊ณ  ์žˆ์Šต๋‹ˆ๋‹ค.
04:58
for those use cases where human creativity doesn't scale.
80
298768
3866
์ธ๊ฐ„์˜ ์ฐฝ์˜์„ฑ์ด ์ธก์ •๋˜์ง€ ์•Š๋Š” ์ผ€์ด์Šค๋“ค์„ ์œ„ํ•ด์„œ ๋ง์ž…๋‹ˆ๋‹ค.
05:03
And we don't just want to do that for games.
81
303363
2206
์ €ํฌ๋Š” ๊ฒŒ์ž„์šฉ์œผ๋กœ๋งŒ ํ•˜์ง€ ์•Š์Šต๋‹ˆ๋‹ค.
05:06
Beethoven actually wrote a piece for his beloved, called "Fรผr Elise,"
82
306657
4428
๋ฒ ํ† ๋ฒค์€ ์‹ค์ œ๋กœ ์‚ฌ๋ž‘ํ•˜๋Š” ์‚ฌ๋žŒ์„ ์œ„ํ•ด "์—˜๋ฆฌ์ œ๋ฅผ ์œ„ํ•˜์—ฌ"๋ผ๋Š” ๊ณก์„ ์ผ์ฃ 
05:11
and imagine if we could bring back Beethoven to life.
83
311109
3651
์šฐ๋ฆฌ๊ฐ€ ๋ฒ ํ† ๋ฒค์„ ๋ถ€ํ™œ์‹œ์ผœ
05:14
And if he was sitting next to you, composing a music for your personality
84
314784
5230
์—ฌ๋Ÿฌ๋ถ„ ์˜†์ž๋ฆฌ์— ์•‰์•„ ์—ฌ๋Ÿฌ๋ถ„์˜ ๊ฐœ์„ฑ๊ณผ
05:20
and your life story.
85
320038
1333
์‚ถ์„ ๊ณก์œผ๋กœ ํ‘œํ˜„ํ•œ๋‹ค๋ฉด ์–ด๋–จ๊นŒํ•˜๊ณ  ๋ง์ž…๋‹ˆ๋‹ค.
05:22
Or imagine if someone like Martin Luther King, for example,
86
322632
2779
ํ˜น์€ ์˜ˆ๋ฅผ ๋“ค์–ด ๋งˆํ‹ด ๋ฃจํ„ฐ ํ‚น ๋ชฉ์‚ฌ ๊ฐ™์€ ๋ถ„์ด
05:25
had a personalized AI composer.
87
325435
2039
๋งž์ถคํ˜• ์ธ๊ณต์ง€๋Šฅ ์ž‘๊ณก๊ฐ€๊ฐ€ ์žˆ๋‹ค๋ฉด ์–ด๋–จ๊นŒ์š”.
05:27
Maybe then we would remember
88
327498
1373
๊ทธ๋ ‡๋‹ค๋ฉด ์šฐ๋ฆฌ๋Š”
05:28
"I Have a Dream" not only as a great speech,
89
328895
2056
๊ทธ๊ฐ€ ํ–ˆ๋˜ "๋‚˜์˜ ๊ฟˆ"์„ ์œ„๋Œ€ํ•œ ์—ฐ์„ค๋กœ์„œ๋ฟ ์•„๋‹ˆ๋ผ
05:30
but also as a great piece of music, part of our history,
90
330975
2626
์œ„๋Œ€ํ•œ ์Œ์•…์œผ๋กœ์„œ ์—ญ์‚ฌ๋ฅผ ์žฅ์‹ํ•  ์ˆ˜ ์žˆ์„ ๊ฒ๋‹ˆ๋‹ค.
05:33
and capturing Dr. King's ideals.
91
333625
2133
ํ‚น ๋ชฉ์‚ฌ์˜ ์ด์ƒ์„ ํ‘œํ˜„ํ•˜๋ฉด์„œ์š”.
05:36
And this is our vision at AIVA:
92
336069
1889
์ด๊ฒƒ์€ VIVA์— ๋‹ด์€ ์šฐ๋ฆฌ์˜ ๋ฏธ๋ž˜์˜ ๋ฐ”๋žŒ์ž…๋‹ˆ๋‹ค.
05:37
to personalize music so that each and every one of you
93
337982
2578
์Œ์•…์„ ๋งž์ถคํ™”ํ•ด์„œ ํ•œ์‚ฌ๋žŒ ํ•œ์‚ฌ๋žŒ
05:40
and every individual in the world
94
340584
1649
์„ธ์ƒ์˜ ๋ชจ๋‘๊ฐ€
05:42
can have access to a personalized live soundtrack,
95
342257
3074
์ž๊ธฐ๋งŒ์˜ ์Œ์•…์„ ๊ฐ€์งˆ ์ˆ˜ ์žˆ๋„๋ก ๋งŒ๋“œ๋Š” ๊ฟˆ์ž…๋‹ˆ๋‹ค.
05:45
based on their story and their personality.
96
345355
2505
์ž๊ธฐ ์ด์•ผ๊ธฐ์™€ ๊ฐœ์„ฑ์— ๊ธฐ๋ฐ˜ํ•œ ์Œ์•…์ด์ฃ .
05:49
So this moment here together at TED is now part of our life story.
97
349915
4079
TED์— ํ•จ๊ป˜ํ•œ ์ด ์ˆœ๊ฐ„์ด ์šฐ๋ฆฌ ์‚ถ์˜ ์ด์•ผ๊ธฐ๊ฒ ์ฃ .
05:54
So it only felt fitting that AIVA would compose music for this moment.
98
354018
4169
AIVA๊ฐ€ ์ด ์ˆœ๊ฐ„์„ ์œ„ํ•ด ์ž‘๊ณก์„ ํ•˜๋Š” ๊ฒƒ์ด ์ฉ ๊ดœ์ฐฎ๊ฒ ์ฃ .
05:58
And that's exactly what we did.
99
358674
2444
๊ทธ๋ž˜์„œ ๊ทธ๋ ‡๊ฒŒ ํ–ˆ์Šต๋‹ˆ๋‹ค.
06:01
So my team and I worked on biasing AIVA on the style of the TED jingle,
100
361436
5022
์ €ํฌ ํŒ€์€ AIVA๊ฐ€
TED ์†Œ๋ฆฌ ์Šคํƒ€์ผ๊ณผ ๊ฒฝ์ด์™€ ๋†€๋ผ์›€์˜ ๋Š๋‚Œ์ด ๋‚˜๋„๋ก ๋งŒ๋“ค๊ฒŒ ํ–ˆ์Šต๋‹ˆ๋‹ค.
06:06
and on music that makes us feel a sense of awe and wonder.
101
366482
3444
06:09
And the result is called "The Age of Amazement."
102
369950
3913
์ด ๊ฒฐ๊ณผ๋ฌผ์˜ ์ œ๋ชฉ์€ "๊ฒฝ์ด์˜ ์‹œ๋Œ€"๋ผ๊ณ  ๋ถ™์˜€์Šต๋‹ˆ๋‹ค.
06:13
Didn't take an AI to figure that one out.
103
373887
2396
๊ทธ๊ฑด ์ธ๊ณต์ง€๋Šฅ ์—†์ด๋„ ๋งŒ๋“ค ์ˆ˜ ์žˆ์—ˆ์–ด์š”.
06:16
(Laughter)
104
376307
1150
(์›ƒ์Œ)
06:18
And I couldn't be more proud to show it to you,
105
378152
2402
์—ฌ๋Ÿฌ๋ถ„๊ป˜ ๋ณด์—ฌ๋“œ๋ฆฌ๊ฒŒ ๋˜์–ด ๋„ˆ๋ฌด๋‚˜ ์ž๋ž‘์Šค๋Ÿฝ์Šต๋‹ˆ๋‹ค.
06:20
so if you can, close your eyes and enjoy the music.
106
380578
2428
๊ทธ๋Ÿฌ๋‹ˆ ๋ˆˆ์„ ๊ฐ๊ณ  ์Œ์•…์„ ๊ฐ์ƒํ•ด์ฃผ์„ธ์š”.
06:23
Thank you very much.
107
383030
1333
๊ฐ์‚ฌํ•ฉ๋‹ˆ๋‹ค.
06:25
(Music)
108
385537
4195
(์Œ์•…)
06:35
[The Age of Amazement Composed by AIVA]
109
395176
2667
[๊ฒฝ์ด์˜ ์‹œ๋Œ€, AIVA ์ž‘๊ณก]
08:19
(Music ends)
110
499649
1151
(์Œ์•… ๋)
08:20
This was for all of you.
111
500824
1373
์ค€๋น„ํ•œ ์Œ์•…์€ ์—ฌ๊ธฐ๊นŒ์ง€ ์ž…๋‹ˆ๋‹ค.
08:22
Thank you.
112
502221
1166
๊ฐ์‚ฌํ•ฉ๋‹ˆ๋‹ค.
08:23
(Applause)
113
503411
4573
(๋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