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

170,346 views ใƒป 2018-10-01

TED


ูŠุฑุฌู‰ ุงู„ู†ู‚ุฑ ู†ู‚ุฑู‹ุง ู…ุฒุฏูˆุฌู‹ุง ููˆู‚ ุงู„ุชุฑุฌู…ุฉ ุงู„ุฅู†ุฌู„ูŠุฒูŠุฉ ุฃุฏู†ุงู‡ ู„ุชุดุบูŠู„ ุงู„ููŠุฏูŠูˆ.

ุงู„ู…ุชุฑุฌู…: Mohamed Emad ุงู„ู…ุฏู‚ู‘ู‚: Hani Eldalees
00:12
About two and a half years ago, I watched this movie called "Her."
0
12913
3428
ู…ู†ุฐ ุญูˆุงู„ูŠ ุนุงู…ูŠู† ูˆู†ุตูุŒ ุดุงู‡ุฏุชู ููŠู„ู…ู‹ุง ูŠูุณู…ู‘ู‰ (ู‡ูŠ).
00:16
And it features Samantha, a superintelligent form of AI
1
16365
5127
ูŠูุธู‡ุฑ ู‡ุฐุง ุงู„ููŠู„ู… ุณุงู…ุงู†ุซุงุŒ ุดูƒู„ ู…ู† ุฃุดูƒุงู„ ุงู„ุฐูƒุงุก ุงู„ุงุตุทู†ุงุนูŠ ูุงุฆู‚ ุงู„ุฐูƒุงุก
00:21
that cannot take physical form.
2
21516
1760
ู„ุง ูŠุณุชุทูŠุน ุฃู†ู’ ูŠุฃุฎุฐ ุดูƒู„ู‹ุง ู…ุงุฏูŠู‹ุง.
00:23
And because she can't appear in photographs,
3
23858
2230
ูˆู„ุฃู†ู‘ู‡ุง ู„ุง ุชุณุชุทูŠุน ุฃู†ู’ ุชูŽุธู‡ุฑ ููŠ ุงู„ุตูˆุฑุŒ
00:26
Samantha decides to write a piece of music
4
26112
2016
ู‚ุฑู‘ุฑุช ุณุงู…ุงู†ุซุง ุฃู†ู’ ุชูƒุชุจ ู‚ุทุนุฉ ู…ูˆุณูŠู‚ูŠุฉ
00:28
that will capture a moment of her life just like a photograph would.
5
28152
3466
ุณุชุตูˆู‘ุฑ ู„ุญุธุฉ ู…ู† ุญูŠุงุชู‡ุงุŒ ูƒู…ุง ุชูุนู„ ุงู„ุตูˆุฑ ุงู„ููˆุชูˆุบุฑุงููŠุฉ.
00:32
As a musician and an engineer, and someone raised in a family of artists,
6
32953
4408
ูƒู…ูˆุณูŠู‚ูŠุŒ ูˆูƒู…ู‡ู†ุฏุณุŒ ูˆูƒุดุฎุต ุชุฑุนุฑุน ูˆุณุท ุนุงุฆู„ุฉ ู…ู† ุงู„ูู†ู‘ุงู†ูŠู†ุŒ
00:37
I thought that this idea of musical photographs was really powerful.
7
37385
4176
ุงุนุชู‚ุฏุชู ุจุฃู†ู‘ ููƒุฑุฉ ุงู„ุตูˆุฑ ุงู„ู…ูˆุณูŠู‚ูŠุฉ ู‚ูˆูŠุฉ ู„ู„ุบุงูŠุฉ.
00:41
And I decided to create an AI composer.
8
41955
2868
ูˆู‚ุฑู‘ุฑุชู ุฃู†ู’ ุฃุตู†ุน ุฐูƒุงุกู‹ ุงุตุทู†ุงุนูŠู‹ุง ู‚ุงุฏุฑู‹ุง ุนู„ู‰ ุชุฃู„ูŠู ุงู„ู…ูˆุณูŠู‚ู‰.
00:44
Her name is AIVA, and she's an artificial intelligence
9
44847
3488
ุงุณู…ู‡ุง (ุฃูŠูุง)ุŒ ูˆู‡ูŠ ุนุจุงุฑุฉ ุนู† ุฐูƒุงุก ุงุตุทู†ุงุนูŠ
00:48
that has learned the art of music composition
10
48359
2393
ู‚ุฏู‘ ุชุนู„ู‘ู… ูู† ุชุฃู„ูŠู ุงู„ู…ูˆุณูŠู‚ู‰
00:50
by reading over 30,000 scores of history's greatest.
11
50776
2785
ุนู† ุทุฑูŠู‚ ู‚ุฑุงุกุฉ ุฃูƒุซุฑ ู…ู† 30,000 ู‚ุทุนุฉ ู…ูˆุณูŠู‚ูŠุฉ ู…ู† ุฃุนุธู… ุงู„ู‚ุทุน ููŠ ุงู„ุชุงุฑูŠุฎ.
00:54
So here's what one score looks like to the algorithm
12
54165
2456
ู‡ุง ู‡ูˆ ู…ุซุงู„ ู„ูƒูŠููŠุฉ ุฑุคูŠุฉ ุงู„ุฎูˆุงุฑุฒู…ูŠุฉ ู„ู‚ุทุนุฉู ู…ูˆุณูŠู‚ูŠุฉ
00:56
in a matrix-like representation.
13
56645
2202
ุญูŠุซ ุชูŽุธู‡ุฑ ููŠ ุตูˆุฑุฉ ุชูุดุจู‡ ุงู„ู…ุตููˆูุงุช ุงู„ุฑูŠุงุถูŠุฉ.
00:58
And here's what 30,000 scores,
14
58871
2246
ูˆู‡ุง ู‡ูˆ ู…ุซุงู„ ู„ูƒูŠููŠุฉ ุฑุคูŠุฉ ุงู„ุฎูˆุงุฑุฒู…ูŠุฉ ู„ุนุฏุฏ 30,000 ู‚ุทุนุฉ ู…ูˆุณูŠู‚ูŠุฉุŒ
01:01
written by the likes of Mozart and Beethoven,
15
61141
2096
ู…ูƒุชูˆุจุฉ ุจูˆุงุณุทุฉ ุฃุดุฎุงุต ู…ุซู„ ู…ูˆุฒุงุฑุช ูˆุจูŠุชู‡ูˆฺคู†ุŒ
01:03
look like in a single frame.
16
63261
2031
ุธุงู‡ุฑุฉ ููŠ ุฅุทุงุฑู ูˆุงุญุฏ ุฃู…ุงู…ูƒู….
01:07
So, using deep neural networks, AIVA looks for patterns in the scores.
17
67609
4340
ุนู† ุทุฑูŠู‚ ุงุณุชุนู…ุงู„ ุดุจูƒุงุช ุนุตุจูŠุฉ ุนู…ูŠู‚ุฉุŒ ุฃูŠูุง ุชุจุญุซ ุนู† ุฃู†ู…ุงุท ุจุฏุงุฎู„ ุงู„ู‚ุทุน ุงู„ู…ูˆุณูŠู‚ูŠุฉ.
01:12
And from a couple of bars of existing music,
18
72260
3563
ูˆุจูˆุงุณุทุฉ ุจุถุน ู…ูˆุงุฒูŠู† ู…ูˆุณูŠู‚ูŠุฉ ู…ูˆุฌูˆุฏุฉุŒ
01:15
it actually tries to infer what notes should come next in those tracks.
19
75847
3708
ุชูุญุงูˆู„ ุฃูŠูุง ุฃู†ู’ ุชูุฎู…ู‘ู† ุงู„ุฏุฑุฌุฉ ุงู„ู…ูˆุณูŠู‚ูŠุฉ ุงู„ู‚ุงุฏู…ุฉ ููŠ ุงู„ู‚ุทุนุฉ ุงู„ู…ูˆุณูŠู‚ูŠุฉ.
01:19
And once AIVA gets good at those predictions,
20
79887
2498
ูˆุนู†ุฏู…ุง ุชูุตุจุญ ุฃูŠูุง ุฌูŠุฏุฉ ููŠ ู‡ุฐู‡ ุงู„ุชุฎู…ูŠู†ุงุชุŒ
01:22
it can actually build a set of mathematical rules
21
82409
3613
ุชูุตุจุญ ู‚ุงุฏุฑุฉู‹ ุนู„ู‰ ูˆูŽุถู’ุน ู…ุฌู…ูˆุนุฉ ู…ู† ุงู„ู‚ูˆุงุนุฏ ุงู„ุฑูŠุงุถูŠุฉ
01:26
for that style of music
22
86046
1166
ู„ู‡ุฐุง ุงู„ู†ูˆุน ู…ู† ุงู„ู…ูˆุณูŠู‚ู‰
01:27
in order to create its own original compositions.
23
87236
2788
ู…ู† ุฃุฌู„ ุชุฃู„ูŠู ุงู„ู…ูˆุณูŠู‚ู‰ ุงู„ู…ูุจุชูŽูƒุฑุฉ ุฎุงุตุชู‡ุง.
01:30
And in a way, this is kind of how we, humans, compose music, too.
24
90490
3709
ู…ู† ู†ุญูˆู ุขุฎุฑุŒ ู‡ุฐู‡ ู‡ูŠ ู†ูˆุนู‹ุง ู…ุง ู†ูุณ ุงู„ุทุฑูŠู‚ุฉ ุงู„ุชูŠ ูŠุคู„ู‘ู ุจู‡ุง ุงู„ุฅู†ุณุงู† ุงู„ู…ูˆุณูŠู‚ู‰.
01:34
It's a trial-and-error process,
25
94561
1492
ุฅู†ู‘ู‡ ุชุนู„ู‘ู… ุนู† ุทุฑูŠู‚ ุงู„ุชุฌุฑุจุฉ ูˆุงู„ุฎุทุฃุŒ
01:36
during which we may not get the right notes all the time.
26
96077
3008
ูู†ุญู†ู ู„ุง ู†ู†ุฌุญ ุฏุงุฆู…ู‹ุง ุฃุซู†ุงุก ุชุฃู„ูŠู ุงู„ุฃู„ุญุงู† ุงู„ู…ูˆุณูŠู‚ูŠุฉ.
01:39
But we can correct ourselves,
27
99109
1389
ูˆู„ูƒู†ู†ุง ู†ุณุชุทูŠุน ุชุตุญูŠุญ ู‡ุฐู‡ ุงู„ุฃุฎุทุงุกุŒ
01:40
either with our musical ear or our musical knowledge.
28
100522
3293
ุณูˆุงุกู‹ ุจูˆุงุณุทุฉ ุขุฐุงู†ู†ุง ุงู„ู…ูˆุณูŠู‚ูŠุฉ ุฃูˆ ู…ุนุฑูุชู†ุง ุงู„ู…ูˆุณูŠู‚ูŠุฉ.
01:45
But for AIVA, this process is taken from years and years of learning,
29
105495
4143
ูˆู„ูƒู† ุจุงู„ู†ุณุจุฉ ู„ุฃูŠูุงุŒ ู‡ุฐู‡ ุงู„ุนู…ู„ูŠุฉ ู…ุฃุฎูˆุฐุฉ ู…ู† ุณู†ูˆุงุช ู…ู† ุงู„ุชุนู„ู‘ู…ุŒ
01:49
decades of learning as an artist, as a musician and a composer,
30
109662
3262
ุจู„ ู‚ุฑูˆู†ู‹ุง ู…ู† ุงู„ุชุนู„ู‘ู… ูƒูู†ู‘ุงู†ุŒ ูˆู…ูˆุณูŠู‚ุงุฑุŒ ูˆู…ุคู„ู‘ูุŒ
01:52
down to a couple of hours.
31
112948
1733
ุชุฃุฎุฐู‡ุง ูˆุชูŽุชุนู„ู‘ู…ู‡ุง ููŠ ุจุถุน ุณุงุนุงุช.
01:55
But music is also a supersubjective art.
32
115030
2880
ู…ุน ุฐู„ูƒุŒ ุงู„ู…ูˆุณูŠู‚ู‰ ูู† ู…ูุชูŽุนู„ู‘ู‚ ุฌุฏู‹ุง ุจุฃุฑุงุก ุงู„ู†ุงุณ.
01:57
And we needed to teach AIVA
33
117934
1564
ูุงุญุชุฌู†ุง ู„ุชุนู„ูŠู… ุฃูŠูุง
01:59
how to compose the right music for the right person,
34
119522
2445
ูƒูŠููŠุฉ ุชุฃู„ูŠู ุงู„ู…ูˆุณูŠู‚ู‰ ุงู„ู…ู†ุงุณุจุฉ ู„ู„ุดุฎุต ุงู„ู…ู†ุงุณุจุŒ
02:01
because people have different preferences.
35
121991
2141
ู„ุฃู†ู‘ ุงู„ู†ุงุณ ู„ุฏูŠู‡ุง ุชูุถูŠู„ุงุช ู…ุฎุชู„ูุฉ.
02:04
And to do that, we show to the algorithm over 30 different category labels
36
124156
4190
ูˆู…ู† ุฃุฌู„ ูุนู„ ู‡ุฐุงุŒ ู†ูุธู‡ุฑ ู„ู„ุฎูˆุงุฑุฒู…ูŠุฉ ุฃูƒุซุฑ ู…ู† 30 ุชุตู†ูŠู ู…ุฎุชู„ู ู„ู„ูุฆุงุช
02:08
for each score in our database.
37
128370
1945
ู„ูƒู„ู‘ ู‚ุทุนุฉ ู…ูˆุณูŠู‚ูŠุฉ ููŠ ู‚ุงุนุฏุชู†ุง ุงู„ุจูŠุงู†ูŠุฉ.
02:10
So those category labels are like mood
38
130339
2516
ู„ุฐู„ูƒ ุชุตู†ูŠูุงุช ุงู„ูุฆุงุช ู‡ุฐู‡ ุชูƒูˆู† ู…ุซู„ ุงู„ู…ุฒุงุฌ
02:12
or note density or composer style of a piece
39
132879
2920
ุฃูˆ ูƒุซุงูุฉ ุงู„ู‚ุทุนุฉ ุงู„ู…ูˆุณูŠู‚ูŠุฉ ุฃูˆ ุฃูุณู„ูˆุจ ุงู„ู…ุคู„ู‘ู ู„ู‚ุทุนุฉู ู…ูˆุณูŠู‚ูŠุฉ ู…ุง
02:15
or the epoch during which it was written.
40
135823
2524
ุฃูˆ ุงู„ุนูŽุตู’ุฑ ุงู„ุฐูŠ ูƒูุชูุจูŽุช ุงู„ู‚ุทุนุฉ ุงู„ู…ูˆุณูŠู‚ูŠุฉ ููŠู‡.
02:18
And by seeing all this data,
41
138371
1935
ูˆุนู† ุทุฑูŠู‚ ุฑุคูŠุฉ ูƒู„ ู‡ุฐู‡ ุงู„ุจูŠุงู†ุงุชุŒ
02:20
AIVA can actually respond to very precise requirements.
42
140330
3056
ุฃูŠูุง ุชุณุชุทูŠุน ุงู„ุงุณุชุฌุงุจุฉ ู„ู…ูุชุทู„ู‘ุจูŽุงุช ุฏู‚ูŠู‚ุฉ ู„ู„ุบุงูŠุฉ.
02:23
Like the ones, for example, we had for a project recently,
43
143966
3103
ู…ุซู„ ุงู„ู…ูุชุทู„ู‘ุจูŽุงุช ุงู„ุชูŠ ูˆุถุนู†ุงู‡ุง ู„ู…ุดุฑูˆุนู ู…ุง ู…ุคุฎุฑู‹ุงุŒ
02:27
where we were commissioned to create a piece
44
147093
3035
ุฃูู…ูุฑู†ุง ููŠู‡ ุฃู†ู’ ู†ุคู„ู‘ู ู‚ุทุนุฉู‹ ู…ูˆุณูŠู‚ูŠุฉ
02:30
that would be reminiscent of a science-fiction film soundtrack.
45
150152
3027
ุณุชูƒูˆู† ุฐูƒุฑู‰ ู„ู…ูˆุณูŠู‚ู‰ ุชุตูˆูŠุฑูŠุฉ ู„ููŠู„ู… ุฎูŠุงู„ู ุนู„ู…ูŠู‘.
02:33
And the piece that was created is called "Among the Stars"
46
153839
4500
ูˆู‡ุฐู‡ ุงู„ู‚ุทุนุฉ ุงู„ุชูŠ ุฃูู„ูู‘ูุช ุงุณู…ู‡ุง (ูˆุณุท ุงู„ู†ุฌูˆู…)
02:38
and it was recorded with CMG Orchestra in Hollywood,
47
158363
3317
ูˆู‚ุฏ ุณูุฌู‘ู„ุช ุจูˆุงุณุทุฉ ุฃูˆุฑูƒุณุชุฑุง (CMG) ููŠ ู‡ูˆู„ูŠูˆูˆุฏุŒ
02:41
under great conductor John Beal,
48
161704
1714
ุชุญุช ู‚ูŠุงุฏุฉ ุฌูˆู† ุจูŠู„ุŒ
02:43
and this is what they recorded, made by AIVA.
49
163442
3067
ูˆู‡ุฐุง ู‡ูˆ ู…ุง ู‚ุฏ ุณุฌู‘ู„ูˆู‡. ู‡ุฐู‡ ุงู„ู…ูˆุณูŠู‚ู‰ ู…ู† ุชุฃู„ูŠู ุฃูŠูุง.
02:47
(Music)
50
167657
7000
(ู…ูˆุณูŠู‚ู‰)
03:30
(Music ends)
51
210196
2190
(ุงู„ู…ูˆุณูŠู‚ู‰ ุชู†ุชู‡ูŠ)
03:34
What do you think?
52
214719
1207
ู…ุง ุฑุฃูŠูƒู…ุŸ
03:35
(Applause)
53
215950
4380
(ุชุตููŠู‚)
03:40
Thank you.
54
220354
1150
ุดูƒุฑู‹ุง ู„ูƒู….
03:42
So, as you've seen, AI can create beautiful pieces of music,
55
222001
4055
ูƒู…ุง ุฑุฃูŠุชู…ุŒ ุงู„ุฐูƒุงุก ุงู„ุงุตุทู†ุงุนูŠ ูŠุณุชุทูŠุน ุฃู†ู’ ูŠุคู„ู‘ู ู‚ุทุนู‹ุง ู…ูˆุณูŠู‚ูŠุฉ ุฌู…ูŠู„ุฉุŒ
03:46
and the best part of it
56
226080
1803
ูˆุฃูุถู„ ุดูŠุก ููŠ ู‡ุฐุง
03:47
is that humans can actually bring them to life.
57
227907
2581
ู‡ูˆ ุฃู†ู‘ ุงู„ุจุดุฑ ูŠุณุชุทูŠุนูˆู† ุฃู†ู’ ูŠุนุทูˆุง ุงู„ุญูŠุงุฉ ู„ู‡ุฐู‡ ุงู„ู‚ุทุน.
03:51
And it's not the first time in history
58
231506
1838
ูˆู‡ุฐู‡ ู„ูŠุณุช ุฃูˆู„ ู…ุฑุฉ ููŠ ุงู„ุชุงุฑูŠุฎ
03:53
that technology has augmented human creativity.
59
233368
3344
ุฒุงุฏุช ุงู„ุชูƒู†ูˆู„ูˆุฌูŠุง ููŠู‡ุง ู…ู† ุฅุจุฏุงุน ุงู„ุฅู†ุณุงู†.
03:56
Live music was almost always used in silent films
60
236736
3072
ุงู„ู…ูˆุณูŠู‚ู‰ ุงู„ุญูŠู‘ุฉ ูƒุงู†ุช ุชูุณุชุฎุฏู‘ู… ุฏุงุฆู…ู‹ุง ุชู‚ุฑูŠุจู‹ุง ููŠ ุงู„ุฃูู„ุงู… ุงู„ุตุงู…ุชุฉ
03:59
to augment the experience.
61
239832
1666
ู…ู† ุฃุฌู„ ุชุนุฒูŠุฒ ุงู„ุชุฌุฑุจุฉ.
04:01
But the problem with live music is that it didn't scale.
62
241522
3182
ูˆู„ูƒู† ู…ุดูƒู„ุฉ ุงู„ู…ูˆุณูŠู‚ู‰ ุงู„ุญูŠุฉ ู‡ู‰ ุฃู†ู‘ู‡ุง ู„ู… ุชุชู†ุงุณุจ ู…ุน ุงู„ู…ูƒุงู†.
04:04
It's really hard to cram a full symphony into a small theater,
63
244728
3429
ุฅู†ู‘ู‡ ุดูŠุก ุตุนุจ ู„ู„ุบุงูŠุฉ ุฃู†ู’ ุชูŽุญุดุฑ ุณู…ููˆู†ูŠุฉ ูƒุงู…ู„ุฉ ููŠ ู…ูŽุณุฑุญ ุตุบูŠุฑุŒ
04:08
and it's really hard to do that for every theater in the world.
64
248181
2991
ูˆุฅู†ู‘ู‡ ุดูŠุก ุตุนุจ ู„ู„ุบุงูŠุฉ ุฃู†ู’ ุชูุนู„ ู‡ุฐุง ููŠ ูƒู„ ู…ุณุฑุญู ุจุงู„ุนุงู„ูŽู….
04:11
So when music recording was actually invented,
65
251196
2849
ู„ุฐู„ูƒ ุนู†ุฏู…ุง ุงูุจุชูƒูุฑ ุชุณุฌูŠู„ ุงู„ู…ูˆุณูŠู‚ู‰ุŒ
04:14
it allowed content creators, like film creators,
66
254069
2349
ุงุณุชุทุงุน ู…ู†ุดุฆูˆ ุงู„ู…ุญุชูˆู‰ ู…ุซู„ ุตูู†ู‘ุงุน ุงู„ุฃูู„ุงู…ุŒ
04:16
to have prerecorded and original music
67
256442
2786
ุฃู†ู’ ูŠุณุฌู‘ู„ูˆุง ุงู„ู…ูˆุณูŠู‚ู‰ ุงู„ุฃุตู„ูŠุฉ ู…ูู‚ุฏู‘ู…ู‹ุง
04:19
tailored to each and every frame of their stories.
68
259252
2873
ูˆูŠุฌุนู„ูˆู‡ุง ุชุชู†ุงุณุจ ู…ุน ูƒู„ ุฅุทุงุฑ ู…ู† ู‚ุตุตู‡ู….
04:22
And that was really an enhancer of creativity.
69
262149
2626
ูˆูƒุงู† ู‡ุฐุง ู…ูุนุฒูุฒู‹ุง ุญู‚ู‹ุง ู„ู„ุฅุจุฏุงุน.
04:26
Two and a half years ago, when I watched this movie "Her,"
70
266617
3286
ู…ู†ุฐ ุนุงู…ูŠู† ูˆู†ุตูุŒ ุนู†ุฏู…ุง ุฑุฃูŠุชู ู‡ุฐุง ุงู„ููŠู„ู… ุงู„ู…ูุณู…ู‘ู‰ (ู‡ูŠ)ุŒ
04:29
I thought to myself that personalized music
71
269927
2907
ุฃุฎุฐุชู ุฃูููƒู‘ุฑ ุจุฃู†ู‘ ุงู„ู…ูˆุณูŠู‚ู‰ ุงู„ู…ูุฎุตู‘ุตุฉ
04:32
would be the next single biggest change in how we consume and create music.
72
272858
4417
ุณุชูƒูˆู† ุฃูƒุจุฑ ุชุบูŠูŠุฑู ู‚ุงุฏู… ููŠ ูƒูŠููŠุฉ ุชุฃู„ูŠู ูˆุงุณุชู‡ู„ุงูƒู†ุง ู„ู„ู…ูˆุณูŠู‚ู‰.
04:38
Because nowadays, we have interactive content, like video games,
73
278187
4222
ู„ุฃู†ู‘ ููŠ ุงู„ูˆู‚ุช ุงู„ุญุงุถุฑุŒ ู„ุฏูŠู†ุง ู…ูุญุชูˆู‰ ุชูุงุนู„ูŠุŒ ู…ุซู„ ุฃู„ุนุงุจ ุงู„ฺคูŠุฏูŠูˆุŒ
04:42
that have hundreds of hours of interactive game plays,
74
282433
3015
ุงู„ุชูŠ ุชุญุชูˆู‰ ุนู„ู‰ ู…ุฆุงุช ุงู„ุณุงุนุงุช ู…ู† ุฃูุณู„ูˆุจ ุงู„ู„ุนุจ ุงู„ุชูุงุนู„ูŠุŒ
04:45
but only two hours of music, on average.
75
285472
2113
ูˆู„ูƒู† ุชุญุชูˆูŠ ุนู„ู‰ ุณุงุนุชูŠู† ูู‚ุท ู…ู† ุงู„ู…ูˆุณูŠู‚ู‰ุŒ ููŠ ุงู„ู…ุชูˆุณุท.
04:47
And it means that the music loops and loops and loops
76
287609
2492
ูˆู‡ุฐุง ูŠุนู†ูŠ ุจุฃู†ู‘ ุงู„ู…ูˆุณูŠู‚ู‰ ุชุชูƒุฑุฑ ูˆุชุชูƒุฑุฑ ูˆุชุชูƒุฑุฑ
04:50
over and over again, and it's not very immersive.
77
290125
2332
ู…ุฑุงุฑู‹ุง ูˆุชูƒุฑุงุฑู‹ุงุŒ ูˆู‡ุฐู‡ ู„ูŠุณุช ุชุฌุฑุจุฉ ุบุงู…ุฑุฉ ู„ู„ุบุงูŠุฉ.
04:52
So what we're working on is to make sure that AI can compose
78
292467
3951
ู„ุฐู„ูƒ ู†ุญู† ู†ุนู…ู„ ุงู„ุขู† ุนู„ู‰ ุชุฃูƒูŠุฏ ุฃู†ู‘ ุงู„ุฐูƒุงุก ุงู„ุงุตุทู†ุงุนูŠู‘ ู‚ุงุฏุฑูŒ ุนู„ู‰ ุชุฃู„ูŠู
04:56
hundreds of hours of personalized music
79
296442
2302
ู…ุฆุงุช ุงู„ุณุงุนุงุช ู…ู† ุงู„ู…ูˆุณูŠู‚ู‰ ุงู„ู…ูุฎุตู‘ุตุฉ
04:58
for those use cases where human creativity doesn't scale.
80
298768
3866
ู…ู† ุฃุฌู„ ู‡ุฐู‡ ุงู„ุญุงู„ุงุช ุงู„ุชูŠ ู„ุง ุชุตู„ุญ ุฃู†ู’ ุชุณุชุฎุฏู… ุฅุจุฏุงุน ุงู„ุฅู†ุณุงู† ููŠู‡ุง.
05:03
And we don't just want to do that for games.
81
303363
2206
ูˆู†ุญู† ู„ุง ู†ูุฑูŠุฏ ุฃู†ู’ ู†ูุนู„ ู‡ุฐุง ูู‚ุท ููŠ ุงู„ุฃู„ุนุงุจ.
05:06
Beethoven actually wrote a piece for his beloved, called "Fรผr Elise,"
82
306657
4428
ุจูŠุชู‡ูˆฺคู† ูƒูŽุชูŽุจ ู‚ุทุนุฉ ู…ูˆุณูŠู‚ูŠุฉ ู…ู† ุฃุฌู„ ุญุจูŠุจุชู‡ุŒ ุงุณู… ุงู„ู‚ุทุนุฉ (ู…ู† ุฃุฌู„ ุฅู„ูŠุฒู‡)ุŒ
05:11
and imagine if we could bring back Beethoven to life.
83
311109
3651
ูุชุฎูŠู‘ู„ ู„ูˆ ุงุณุชุทุนู†ุง ุฅุนุงุฏุฉ ุจูŠุชู‡ูˆฺคู† ู„ู„ุญูŠุงุฉ.
05:14
And if he was sitting next to you, composing a music for your personality
84
314784
5230
ูˆูƒุงู† ุจูŠุชู‡ูˆฺคู† ุฌุงู„ุณู‹ุง ุจุฌูˆุงุฑูƒุŒ ูŠุคู„ู‘ู ู‚ุทุนุฉ ู…ูˆุณูŠู‚ูŠุฉ ู…ูุฎุตู‘ุตุฉ ู„ุดุฎุตูŠุชูƒ
05:20
and your life story.
85
320038
1333
ูˆู‚ุตุฉ ุญูŠุงุชูƒ.
05:22
Or imagine if someone like Martin Luther King, for example,
86
322632
2779
ุฃูˆ ุชุฎูŠู‘ู„ ู„ูˆ ุฃู† ู‡ู†ุงูƒ ุดุฎุต ู…ุซู„ ู…ุงุฑุชู† ู„ูˆุซุฑ ูƒูŠู†ุบ
05:25
had a personalized AI composer.
87
325435
2039
ูƒุงู† ู„ุฏูŠู‡ ุฐูƒุงุก ุงุตุทู†ุงุนูŠู‘ ู…ุคู„ู‘ู ู„ู„ู…ูˆุณูŠู‚ู‰.
05:27
Maybe then we would remember
88
327498
1373
ููŠ ู‡ุฐู‡ ุงู„ุญุงู„ุฉ ุฑุจู…ุง ูƒูู†ู‘ุง ุณู†ุชุฐูƒู‘ุฑ
05:28
"I Have a Dream" not only as a great speech,
89
328895
2056
"ู„ุฏูŠ ุญู„ู…" ู„ูŠุณ ูู‚ุท ูƒุฎุทุงุจู ุฑุงุฆุนุŒ
05:30
but also as a great piece of music, part of our history,
90
330975
2626
ุจู„ ุฃูŠุถู‹ุง ูƒู‚ุทุนุฉู ู…ูˆุณูŠู‚ูŠุฉ ุฑุงุฆุนุฉุŒ ุฌุฒุก ู…ู† ุชุงุฑูŠุฎู†ุงุŒ
05:33
and capturing Dr. King's ideals.
91
333625
2133
ูˆุชูˆุถูŠุญ ุฃู‡ุฏุงู ุงู„ุฏูƒุชูˆุฑ ูƒูŠู†ุบ.
05:36
And this is our vision at AIVA:
92
336069
1889
ูˆู‡ุฐู‡ ู‡ูŠ ู†ุธุฑุชู†ุง ู„ุฃูŠูุง:
05:37
to personalize music so that each and every one of you
93
337982
2578
ุชุฎุตูŠุต ุงู„ู…ูˆุณูŠู‚ู‰ ุญุชู‰ ูŠุณุชุทูŠุน ูƒู„ ูˆุงุญุฏู ู…ู†ูƒู…
05:40
and every individual in the world
94
340584
1649
ูˆูƒู„ ูุฑุฏ ููŠ ุงู„ุนุงู„ู…
05:42
can have access to a personalized live soundtrack,
95
342257
3074
ุฃู†ู’ ูŠุชู…ูƒู† ู…ู† ุณู…ุงุน ู…ูˆุณูŠู‚ู‰ ุชุตูˆูŠุฑูŠุฉ ุญูŠู‘ุฉุŒ
05:45
based on their story and their personality.
96
345355
2505
ู…ุจู†ูŠู‘ุฉ ุนู„ู‰ ู‚ุตุชู‡ ูˆุดุฎุตูŠุชู‡.
05:49
So this moment here together at TED is now part of our life story.
97
349915
4079
ู„ุฐู„ูƒ ู‡ุฐู‡ ุงู„ู„ุญุธุฉ ู‡ู†ุง ู…ุนู‹ุง ููŠ TED ุงู„ุขู† ุฌุฒุก ู…ู† ู‚ุตุฉ ุญูŠุงุชู†ุง.
05:54
So it only felt fitting that AIVA would compose music for this moment.
98
354018
4169
ู„ุฐู„ูƒ ุณูŠูƒูˆู† ู…ู„ุงุฆู…ู‹ุง ุฃู†ู’ ุชุคู„ู‘ู ุฃูŠูุง ู‚ุทุนุฉู‹ ู…ูˆุณูŠู‚ูŠุฉ ู„ู‡ุฐู‡ ุงู„ู„ุญุธุฉ.
05:58
And that's exactly what we did.
99
358674
2444
ูˆู‡ุฐุง ู‡ูˆ ุจุงู„ุถุจุท ู…ุง ูุนู„ู†ุงู‡.
06:01
So my team and I worked on biasing AIVA on the style of the TED jingle,
100
361436
5022
ุฃู†ุง ูˆูุฑูŠู‚ูŠ ุนู…ู„ู†ุง ุนู„ู‰ ุฌุนู„ ุฃูŠูุง ุชู†ุญุงุฒ ุฅู„ู‰ ุฃุณู„ูˆุจ ุฌู„ุฌู„ุฉ TED
06:06
and on music that makes us feel a sense of awe and wonder.
101
366482
3444
ูˆุฅู„ู‰ ู…ูˆุณูŠู‚ู‰ ุชุฌุนู„ู†ุง ู†ุญุณู‘ ุจุดุนูˆุฑ ู…ู† ุงู„ุฑูˆุนุฉ ูˆุงู„ุงู†ุฏู‡ุงุด
06:09
And the result is called "The Age of Amazement."
102
369950
3913
ูˆุงู„ู†ุชูŠุฌุฉ ู‚ุทุนุฉ ู…ูˆุณูŠู‚ูŠุฉ ุชูุณู…ู‘ู‰ (ุนุตุฑ ุงู„ุงู†ุฏู‡ุงุด).
06:13
Didn't take an AI to figure that one out.
103
373887
2396
ู†ุญู† ู…ู† ุณู…ู‘ูŠู†ุงู‡ุงุŒ ู„ูŠุณ ุงู„ุฐูƒุงุก ุงู„ุงุตุทู†ุงุนูŠ.
06:16
(Laughter)
104
376307
1150
(ุถุญูƒ)
06:18
And I couldn't be more proud to show it to you,
105
378152
2402
ูˆุฃู†ุง ุฃุดุนุฑ ุจุฅุญุณุงุณ ุดุฏูŠุฏ ุจุงู„ูุฎุฑ ู„ุฃูุฑูŠูƒู… ู‡ุฐู‡ุŒ
06:20
so if you can, close your eyes and enjoy the music.
106
380578
2428
ู„ุฐู„ูƒ ุฅุฐุง ุฃุฑุฏุชู…ุŒ ุงุบู„ู‚ูˆุง ุนูŠูˆู†ูƒู… ูˆุงุณุชู…ุชุนูˆุง ุจุงู„ู…ูˆุณูŠู‚ู‰.
06:23
Thank you very much.
107
383030
1333
ุดูƒุฑู‹ุง ุฌุฒูŠู„ู‹ุง ู„ูƒู….
06:25
(Music)
108
385537
4195
(ู…ูˆุณูŠู‚ู‰)
06:35
[The Age of Amazement Composed by AIVA]
109
395176
2667
[ุนุตุฑ ุงู„ุงู†ุฏู‡ุงุดุŒ ู…ู† ุชุฃู„ูŠู ุฃูŠูุง]
08:19
(Music ends)
110
499649
1151
(ุงู„ู…ูˆุณูŠู‚ู‰ ุชู†ุชู‡ูŠ)
08:20
This was for all of you.
111
500824
1373
ูƒุงู† ู‡ุฐุง ู…ู† ุฃุฌู„ูƒู… ุฌู…ูŠุนู‹ุง.
08:22
Thank you.
112
502221
1166
ุดูƒุฑู‹ุง ู„ูƒู….
08:23
(Applause)
113
503411
4573
(ุชุตููŠู‚)
ุญูˆู„ ู‡ุฐุง ุงู„ู…ูˆู‚ุน

ุณูŠู‚ุฏู… ู„ูƒ ู‡ุฐุง ุงู„ู…ูˆู‚ุน ู…ู‚ุงุทุน ููŠุฏูŠูˆ YouTube ุงู„ู…ููŠุฏุฉ ู„ุชุนู„ู… ุงู„ู„ุบุฉ ุงู„ุฅู†ุฌู„ูŠุฒูŠุฉ. ุณุชุฑู‰ ุฏุฑูˆุณ ุงู„ู„ุบุฉ ุงู„ุฅู†ุฌู„ูŠุฒูŠุฉ ุงู„ุชูŠ ูŠุชู… ุชุฏุฑูŠุณู‡ุง ู…ู† ู‚ุจู„ ู…ุฏุฑุณูŠู† ู…ู† ุงู„ุฏุฑุฌุฉ ุงู„ุฃูˆู„ู‰ ู…ู† ุฌู…ูŠุน ุฃู†ุญุงุก ุงู„ุนุงู„ู…. ุงู†ู‚ุฑ ู†ู‚ุฑู‹ุง ู…ุฒุฏูˆุฌู‹ุง ููˆู‚ ุงู„ุชุฑุฌู…ุฉ ุงู„ุฅู†ุฌู„ูŠุฒูŠุฉ ุงู„ู…ุนุฑูˆุถุฉ ุนู„ู‰ ูƒู„ ุตูุญุฉ ููŠุฏูŠูˆ ู„ุชุดุบูŠู„ ุงู„ููŠุฏูŠูˆ ู…ู† ู‡ู†ุงูƒ. ูŠุชู… ุชู…ุฑูŠุฑ ุงู„ุชุฑุฌู…ุงุช ุจุงู„ุชุฒุงู…ู† ู…ุน ุชุดุบูŠู„ ุงู„ููŠุฏูŠูˆ. ุฅุฐุง ูƒุงู† ู„ุฏูŠูƒ ุฃูŠ ุชุนู„ูŠู‚ุงุช ุฃูˆ ุทู„ุจุงุช ุŒ ูŠุฑุฌู‰ ุงู„ุงุชุตุงู„ ุจู†ุง ุจุงุณุชุฎุฏุงู… ู†ู…ูˆุฐุฌ ุงู„ุงุชุตุงู„ ู‡ุฐุง.

https://forms.gle/WvT1wiN1qDtmnspy7