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

169,507 views ใƒป 2018-10-01

TED


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

ืชืจื’ื•ื: Yarden Dover ืขืจื™ื›ื”: Talia Breuer
00:12
About two and a half years ago, I watched this movie called "Her."
0
12913
3428
ืœืคื ื™ ื›ืฉื ืชื™ื™ื ื•ื—ืฆื™, ืฆืคื™ืชื™ ื‘ืกืจื˜ ื‘ืฉื "ื”ื™ื".
00:16
And it features Samantha, a superintelligent form of AI
1
16365
5127
ื”ื•ื ืžืกืคืจ ืขืœ ืกืžื ืชื”, ืžืขืจื›ืช ื‘ื™ื ื” ืžืœืื›ื•ืชื™ืช ืกื•ืคืจ-ื—ื›ืžื”,
00:21
that cannot take physical form.
2
21516
1760
ืฉืœื ื™ื›ื•ืœื” ืœืœื‘ื•ืฉ ืฆื•ืจื” ืคื™ื–ื™ืช.
00:23
And because she can't appear in photographs,
3
23858
2230
ืžืื—ืจ ื•ื”ื™ื ืœื ื™ื›ื•ืœื” ืœื”ื•ืคื™ืข ื‘ืชืžื•ื ื•ืช,
00:26
Samantha decides to write a piece of music
4
26112
2016
ืกืžื ืชื” ืžื—ืœื™ื˜ื” ืœื”ืœื—ื™ืŸ ื™ืฆื™ืจื” ืžื•ื–ื™ืงืœื™ืช
00:28
that will capture a moment of her life just like a photograph would.
5
28152
3466
ืฉืชืชืขื“ ืจื’ืข ื‘ื—ื™ื™ื” ื‘ื“ื™ื•ืง ื›ืคื™ ืฉืชืžื•ื ื” ื”ื™ื™ืชื” ืขื•ืฉื”.
00:32
As a musician and an engineer, and someone raised in a family of artists,
6
32953
4408
ื›ืžื•ื–ื™ืงืื™ ื•ืžื”ื ื“ืก, ื•ื›ืื“ื ืฉื’ื“ืœ ื‘ืžืฉืคื—ื” ืฉืœ ืืžื ื™ื,
00:37
I thought that this idea of musical photographs was really powerful.
7
37385
4176
ื—ืฉื‘ืชื™ ืฉื”ืจืขื™ื•ืŸ ื”ื–ื” ืฉืœ ืชืžื•ื ื•ืช ืžื•ื–ื™ืงืœื™ื•ืช ื”ื•ื ืขื•ืฆืžืชื™ ืžืื•ื“.
00:41
And I decided to create an AI composer.
8
41955
2868
ื•ื”ื—ืœื˜ืชื™ ืœื™ืฆื•ืจ ืžืœื—ื™ืŸ ื‘ื™ื ื” ืžืœืื›ื•ืชื™ืช.
00:44
Her name is AIVA, and she's an artificial intelligence
9
44847
3488
ื”ืฉื ืฉืœื” ื”ื•ื ืื™ื•"ื”, ื•ื”ื™ื ื‘ื™ื ื” ืžืœืื›ื•ืชื™ืช
00:48
that has learned the art of music composition
10
48359
2393
ืฉืœืžื“ื” ืืช ืื•ืžื ื•ืช ื”ืœื—ื ืช ื”ืžื•ื–ื™ืงื”
00:50
by reading over 30,000 scores of history's greatest.
11
50776
2785
ืข"ื™ ืงืจื™ืื” ืฉืœ ื™ื•ืชืจ ืž-30 ืืœืฃ ืคืจื˜ื™ื˜ื•ืจื•ืช ืฉืœ ื”ื™ืฆื™ืจื•ืช ื”ื’ื“ื•ืœื•ืช ื‘ื”ื™ืกื˜ื•ืจื™ื”.
00:54
So here's what one score looks like to the algorithm
12
54165
2456
ืื– ื›ื›ื” ื”ืืœื’ื•ืจื™ืชื ืจื•ืื” ืคืจื˜ื™ื˜ื•ืจื” ืื—ืช
00:56
in a matrix-like representation.
13
56645
2202
ื‘ืชืฆื•ื’ื” ื“ืžื•ื™ืช ืžื˜ืจื™ืฆื”.
00:58
And here's what 30,000 scores,
14
58871
2246
ื•ื›ืš 30 ืืœืฃ ืคืจื˜ื™ื˜ื•ืจื•ืช,
01:01
written by the likes of Mozart and Beethoven,
15
61141
2096
ืฉื ื›ืชื‘ื• ืขืœ ื™ื“ื™ ืžื•ืฆืจื˜, ื‘ื˜ื”ื•ื‘ืŸ ื•ื“ื•ืžื™ื”ื,
01:03
look like in a single frame.
16
63261
2031
ื ืจืื•ืช ื‘ืชื•ืš ืชืžื•ื ื” ืื—ืช.
01:07
So, using deep neural networks, AIVA looks for patterns in the scores.
17
67609
4340
ื›ืš, ืขืœ ื™ื“ื™ ืฉื™ืžื•ืฉ ื‘ืจืฉืชื•ืช ืขืฆื‘ื™ื•ืช ืขืžื•ืงื•ืช, ืื™ื•"ื” ืžื—ืคืฉืช ืชื‘ื ื™ื•ืช ื‘ืคืจื˜ื™ื˜ื•ืจื•ืช.
01:12
And from a couple of bars of existing music,
18
72260
3563
ื•ืžืžืกืคืจ ืชื™ื‘ื•ืช ืฉืœ ืžื•ื–ื™ืงื” ืงื™ื™ืžืช,
01:15
it actually tries to infer what notes should come next in those tracks.
19
75847
3708
ื”ื™ื ืœืžืขืฉื” ืžื ืกื” ืœื”ืกื™ืง ืื™ืœื• ืชื•ื•ื™ื ืฆืจื™ื›ื™ื ืœื‘ื•ื ื‘ื”ืžืฉืš ื”ืงื˜ืขื™ื ื”ืืœื•.
01:19
And once AIVA gets good at those predictions,
20
79887
2498
ื‘ืจื’ืข ืฉืื™ื•"ื” ื ืขืฉื™ืช ื˜ื•ื‘ื” ื‘ื—ื™ื–ื•ื™ื™ื ื”ืืœื”,
01:22
it can actually build a set of mathematical rules
21
82409
3613
ื”ื™ื ื™ื›ื•ืœื”, ืœืžืขืฉื”, ืœื‘ื ื•ืช ืกื“ืจื” ืฉืœ ื—ื•ืงื™ื ืžืชืžื˜ื™ื™ื
01:26
for that style of music
22
86046
1166
ืขื‘ื•ืจ ืื•ืชื• ืกื’ื ื•ืŸ ืžื•ื–ื™ืงืœื™
01:27
in order to create its own original compositions.
23
87236
2788
ืขืœ ืžื ืช ืœื™ืฆื•ืจ ืœื—ื ื™ื ืžืงื•ืจื™ื™ื ืžืฉืœื”.
01:30
And in a way, this is kind of how we, humans, compose music, too.
24
90490
3709
ื‘ืžื™ื“ื” ืžืกื•ื™ืžืช, ื–ื”ื• ื”ืื•ืคืŸ ืฉื‘ื• ื’ื ืื ื—ื ื•, ื‘ื ื™ ื”ืื“ื, ืžืœื—ื™ื ื™ื ืžื•ื–ื™ืงื”.
01:34
It's a trial-and-error process,
25
94561
1492
ื–ื”ื• ืชื”ืœื™ืš ืฉืœ ื ื™ืกื•ื™ ื•ื˜ืขื™ื”,
01:36
during which we may not get the right notes all the time.
26
96077
3008
ืฉื‘ื• ืื ื—ื ื• ืขืฉื•ื™ื™ื ืœื ืœื‘ื—ื•ืจ ืชืžื™ื“ ืืช ื”ืชื•ื•ื™ื ื”ื ื›ื•ื ื™ื.
ืื‘ืœ ืื ื—ื ื• ื™ื›ื•ืœื™ื ืœืชืงืŸ ืืช ืขืฆืžื ื•,
01:39
But we can correct ourselves,
27
99109
1389
01:40
either with our musical ear or our musical knowledge.
28
100522
3293
ืื• ื‘ืืžืฆืขื•ืช ื”ืื•ื–ืŸ ื”ืžื•ื–ื™ืงืœื™ืช ืฉืœื ื• ืื• ื‘ืืžืฆืขื•ืช ื”ื™ื“ืข ื”ืžื•ื–ื™ืงืœื™ ืฉืœื ื•.
01:45
But for AIVA, this process is taken from years and years of learning,
29
105495
4143
ืื‘ืœ ื‘ืฉื‘ื™ืœ ืื™ื•"ื”, ืžื“ื•ื‘ืจ ื‘ืชื”ืœื™ืš ื”ืžื•ืฉืชืช ืขืœ ืฉื ื™ื ืขืœ ื’ื‘ื™ ืฉื ื™ื ืฉืœ ืœืžื™ื“ื”,
01:49
decades of learning as an artist, as a musician and a composer,
30
109662
3262
ืขืฉืจื•ืช ืฉื ื™ื ืฉืœ ืœืžื™ื“ื” ื›ืื•ืžืŸ, ื›ืžื•ื–ื™ืงืื™ ื•ื›ืžืœื—ื™ืŸ,
01:52
down to a couple of hours.
31
112948
1733
ืžืกืชื›ืžื•ืช ืœืฉืขื•ืช ื‘ื•ื“ื“ื•ืช.
01:55
But music is also a supersubjective art.
32
115030
2880
ืื‘ืœ ืžื•ื–ื™ืงื” ื”ื™ื ื’ื ืื•ืžื ื•ืช ืกื•ื‘ื™ื™ืงื˜ื™ื‘ื™ืช ื‘ื™ื•ืชืจ.
01:57
And we needed to teach AIVA
33
117934
1564
ื•ื”ื™ื” ืขืœื™ื ื• ืœืœืžื“ ืืช ืื™ื•"ื”
01:59
how to compose the right music for the right person,
34
119522
2445
ื›ื™ืฆื“ ืœื”ืœื—ื™ืŸ ืืช ื”ืžื•ื–ื™ืงื” ื”ื ื›ื•ื ื” ืขื‘ื•ืจ ื”ืื“ื ื”ื ื›ื•ืŸ,
02:01
because people have different preferences.
35
121991
2141
ื›ื™ื•ื•ืŸ ืฉืœืื ืฉื™ื ื™ืฉ ื”ืขื“ืคื•ืช ืฉื•ื ื•ืช.
02:04
And to do that, we show to the algorithm over 30 different category labels
36
124156
4190
ืขืœ ืžื ืช ืœืขืฉื•ืช ื–ืืช, ืื ื• ืžืฆื™ื’ื™ื ืœืืœื’ื•ืจื™ืชื ืžืขืœ 30 ืงื˜ื’ื•ืจื™ื•ืช
02:08
for each score in our database.
37
128370
1945
ืขื‘ื•ืจ ื›ืœ ืคืจื˜ื™ื˜ื•ืจื” ื‘ืžืกื“ ื”ื ืชื•ื ื™ื ืฉืœื ื•.
02:10
So those category labels are like mood
38
130339
2516
ืงื˜ื’ื•ืจื™ื•ืช ื›ืžื• ืื•ื•ื™ืจื”,
02:12
or note density or composer style of a piece
39
132879
2920
ืฆืคื™ืคื•ืช ืชื•ื•ื™ื, ื”ืกื’ื ื•ืŸ ืฉืœ ืžืœื—ื™ืŸ ื”ื™ืฆื™ืจื”
02:15
or the epoch during which it was written.
40
135823
2524
ืื• ื”ืชืงื•ืคื” ื‘ื” ื”ื™ื ื ื›ืชื‘ื”.
02:18
And by seeing all this data,
41
138371
1935
ื•ื‘ืืžืฆืขื•ืช ื›ืœ ื”ื ืชื•ื ื™ื ื”ืืœื”,
02:20
AIVA can actually respond to very precise requirements.
42
140330
3056
ืื™ื•"ื” ื™ื›ื•ืœื” ืœืขื ื•ืช ืขืœ ื“ืจื™ืฉื•ืช ืžื“ื•ื™ืงื•ืช ื‘ื™ื•ืชืจ.
02:23
Like the ones, for example, we had for a project recently,
43
143966
3103
ื“ืจื™ืฉื•ืช ื›ืžื• ืฉืงื™ื‘ืœื ื•, ืœื“ื•ื’ืžื”, ื‘ืคืจื•ื™ืงื˜ ืฉืœืงื—ื ื• ืœืื—ืจื•ื ื”,
02:27
where we were commissioned to create a piece
44
147093
3035
ื‘ื• ื”ืชื‘ืงืฉื ื• ืœื”ืœื—ื™ืŸ ื™ืฆื™ืจื”
02:30
that would be reminiscent of a science-fiction film soundtrack.
45
150152
3027
ืฉืชื–ื›ื™ืจ ืคืกืงื•ืœ ืฉืœ ืกืจื˜ ืžื“ืข ื‘ื“ื™ื•ื ื™.
02:33
And the piece that was created is called "Among the Stars"
46
153839
4500
ื”ื™ืฆื™ืจื” ืฉื”ืชืงื‘ืœื” ื ืงืจืืช "ื‘ื™ืŸ ื”ื›ื•ื›ื‘ื™ื"
02:38
and it was recorded with CMG Orchestra in Hollywood,
47
158363
3317
ื•ื”ื™ื ื”ื•ืงืœื˜ื” ื‘ืฉื™ืชื•ืฃ ืขื ืชื–ืžื•ืจืช CMG ื‘ื”ื•ืœื™ื•ื•ื“,
02:41
under great conductor John Beal,
48
161704
1714
ื‘ื ื™ืฆื•ื—ื• ืฉืœ ื’'ื•ืŸ ื‘ื™ืœ ื”ื’ื“ื•ืœ,
02:43
and this is what they recorded, made by AIVA.
49
163442
3067
ื•ื–ื” ืžื” ืฉื”ื ื”ืงืœื™ื˜ื•, ื™ืฆื™ืจื” ืฉืœ ืื™ื•"ื”.
02:47
(Music)
50
167657
7000
03:30
(Music ends)
51
210196
2190
03:34
What do you think?
52
214719
1207
ืžื” ื“ืขืชื›ื?
03:35
(Applause)
53
215950
4380
03:40
Thank you.
54
220354
1150
ืชื•ื“ื”.
03:42
So, as you've seen, AI can create beautiful pieces of music,
55
222001
4055
ื•ื‘ื›ืŸ, ื›ืคื™ ืฉืจืื™ืชื, ื‘ื™ื ื” ืžืœืื›ื•ืชื™ืช ื™ื›ื•ืœื” ืœื”ืœื—ื™ืŸ ื™ืฆื™ืจื•ืช ืžื•ื–ื™ืงืœื™ื•ืช ื™ืคื”ืคื™ื•ืช,
03:46
and the best part of it
56
226080
1803
ื•ื”ื—ืœืง ื”ื›ื™ ื˜ื•ื‘ ื‘ื–ื”
03:47
is that humans can actually bring them to life.
57
227907
2581
ื”ื•ื ืฉื‘ื ื™ ืื“ื ื™ื›ื•ืœื™ื ืžืžืฉ ืœื”ืคื™ื— ื‘ื”ืŸ ืจื•ื— ื—ื™ื™ื.
03:51
And it's not the first time in history
58
231506
1838
ื–ื• ืœื ื”ืคืขื ื”ืจืืฉื•ื ื” ื‘ื”ื™ืกื˜ื•ืจื™ื”
03:53
that technology has augmented human creativity.
59
233368
3344
ืฉื‘ื” ื”ื˜ื›ื ื•ืœื•ื’ื™ื” ืžืจื—ื™ื‘ื” ืืช ื”ื™ืงืฃ ื”ื™ืฆื™ืจื” ื”ืื ื•ืฉื™ืช.
03:56
Live music was almost always used in silent films
60
236736
3072
ื‘ืกืจื˜ื™ื ืื™ืœืžื™ื ืชืžื™ื“ ื”ืชื ื’ื ื” ืžื•ื–ื™ืงื” ื—ื™ื”
03:59
to augment the experience.
61
239832
1666
ืขืœ ืžื ืช ืœื”ืขืฆื™ื ืืช ื”ื—ื•ื•ื™ื”,
04:01
But the problem with live music is that it didn't scale.
62
241522
3182
ืืš ื”ื‘ืขื™ื” ืขื ืžื•ื–ื™ืงื” ื—ื™ื” ื”ื™ื™ืชื” ืฉืœื ื ื™ืชืŸ ืœื”ืชืื™ื ืื•ืชื” ืœื›ืœ ืžืงื•ื.
04:04
It's really hard to cram a full symphony into a small theater,
63
244728
3429
ื›ืœื•ืžืจ, ืงืฉื” ืžืื•ื“ ืœื“ื—ื•ืก ืชื–ืžื•ืจืช ืฉืœืžื” ืœืชื•ืš ืื•ืœื ืงื˜ืŸ,
04:08
and it's really hard to do that for every theater in the world.
64
248181
2991
ื•ืงืฉื” ืžืื•ื“ ืœืขืฉื•ืช ื–ืืช ื‘ืฉื‘ื™ืœ ื›ืœ ืื•ืœื ื‘ืขื•ืœื.
04:11
So when music recording was actually invented,
65
251196
2849
ืื– ื›ืฉื”ื•ืžืฆืื” ื”ืืคืฉืจื•ืช ืœื”ืงืœื™ื˜ ืžื•ื–ื™ืงื”,
04:14
it allowed content creators, like film creators,
66
254069
2349
ื”ื“ื‘ืจ ืืคืฉืจ ืœื›ื•ืชื‘ื™ ืชื•ื›ืŸ, ื›ืžื• ื™ื•ืฆืจื™ ืกืจื˜ื™ื,
04:16
to have prerecorded and original music
67
256442
2786
ืœื”ืฉืชืžืฉ ื‘ืžื•ื–ื™ืงื” ืžืงื•ืจื™ืช ืฉื”ื•ืงืœื˜ื” ืžืจืืฉ
04:19
tailored to each and every frame of their stories.
68
259252
2873
ื•ื”ื•ืชืืžื” ืœื›ืœ ืกืฆื ื” ื•ืกืฆื ื” ื‘ืกื™ืคื•ืจื™ื ืฉืœื”ื.
04:22
And that was really an enhancer of creativity.
69
262149
2626
ื•ื”ื“ื‘ืจ, ืœืžืขืฉื”, ื”ืจื—ื™ื‘ ืืช ื”ื™ืงืฃ ื”ื™ืฆื™ืจื”.
04:26
Two and a half years ago, when I watched this movie "Her,"
70
266617
3286
ืœืคื ื™ ืฉื ืชื™ื™ื ื•ื—ืฆื™, ื›ืฉืฆืคื™ืชื™ ื‘ืกืจื˜ "ื”ื™ื",
04:29
I thought to myself that personalized music
71
269927
2907
ื—ืฉื‘ืชื™ ืœืขืฆืžื™ ืฉืžื•ื–ื™ืงื” ืžื•ืชืืžืช ืื™ืฉื™ืช
04:32
would be the next single biggest change in how we consume and create music.
72
272858
4417
ืชื”ื™ื” ื”ืฉื™ื ื•ื™ ื”ื’ื“ื•ืœ ื”ื‘ื ื‘ืื•ืคืŸ ืฉื‘ื• ืื ื• ืฆื•ืจื›ื™ื ื•ื™ื•ืฆืจื™ื ืžื•ื–ื™ืงื”.
04:38
Because nowadays, we have interactive content, like video games,
73
278187
4222
ื›ื™ื•ื•ืŸ ืฉื‘ื™ืžื™ื ื•, ื™ืฉ ืชื•ื›ืŸ ืื™ื ื˜ืจืืงื˜ื™ื‘ื™, ื›ืžื• ืžืฉื—ืงื™ ืžื—ืฉื‘,
04:42
that have hundreds of hours of interactive game plays,
74
282433
3015
ืฉื›ื•ืœืœื™ื ืžืื•ืช ืฉืขื•ืช ืฉืœ ืžื”ืœื›ื™ ืžืฉื—ืง ืื™ื ื˜ืจืืงื˜ื™ื‘ื™ื™ื,
04:45
but only two hours of music, on average.
75
285472
2113
ืื‘ืœ ืจืง ืฉืขืชื™ื™ื ืฉืœ ืžื•ื–ื™ืงื”, ื‘ืžืžื•ืฆืข.
04:47
And it means that the music loops and loops and loops
76
287609
2492
ื–ืืช ืื•ืžืจืช ืฉืื•ืชื” ืžื•ื–ื™ืงื” ืžืชื ื’ื ืช ืฉื•ื‘ ื•ืฉื•ื‘ ื•ืฉื•ื‘
04:50
over and over again, and it's not very immersive.
77
290125
2332
ืคืขื ืื—ืจ ืคืขื, ื•ื”ื™ื ืœื ื›ืœ ื›ืš ืžื•ื˜ืžืขืช.
04:52
So what we're working on is to make sure that AI can compose
78
292467
3951
ืื– ืžื” ืฉืื ื—ื ื• ืขื•ื‘ื“ื™ื ืขืœื™ื• ื”ื•ื ืฉืœื‘ื™ื ื” ื”ืžืœืื›ื•ืชื™ืช ืชื”ื™ื” ืืคืฉืจื•ืช ืœื”ืœื—ื™ืŸ
04:56
hundreds of hours of personalized music
79
296442
2302
ืžืื•ืช ืฉืขื•ืช ืฉืœ ืžื•ื–ื™ืงื” ืžื•ืชืืžืช ืื™ืฉื™ืช
04:58
for those use cases where human creativity doesn't scale.
80
298768
3866
ื‘ื“ื™ื•ืง ืœืื•ืชื ืžืงืจื™ื ื‘ื”ื ื”ื™ืงืฃ ื”ื™ืฆื™ืจื” ื”ืื ื•ืฉื™ืช ืœื ืžืกืคื™ืง ื’ื“ื•ืœ.
05:03
And we don't just want to do that for games.
81
303363
2206
ื•ืื ื—ื ื• ืœื ืจื•ืฆื™ื ืœืขืฉื•ืช ื–ืืช ืจืง ื‘ืฉื‘ื™ืœ ืžืฉื—ืงื™ื.
05:06
Beethoven actually wrote a piece for his beloved, called "Fรผr Elise,"
82
306657
4428
ื‘ื˜ื”ื•ื‘ืŸ ื›ืชื‘ ื™ืฆื™ืจื” ืœืื”ื•ื‘ืชื• ื‘ืฉื "ื‘ืฉื‘ื™ืœ ืืœื™ื–",
05:11
and imagine if we could bring back Beethoven to life.
83
311109
3651
ื•ื“ืžื™ื™ื ื• ืœืขืฆืžื›ื ืžื” ืื ื”ื™ื™ื ื• ื™ื›ื•ืœื™ื ืœื”ืงื™ื ืืช ื‘ื˜ื”ื•ื‘ืŸ ืœืชื—ื™ื™ื”.
05:14
And if he was sitting next to you, composing a music for your personality
84
314784
5230
ื•ืื ื”ื™ื” ื™ื›ื•ืœ ืœืฉื‘ืช ืœืฆื™ื“ื›ื ื•ืœื”ืœื—ื™ืŸ ืžื•ื–ื™ืงื” ืฉืžืชืื™ืžื” ืœืื™ืฉื™ื•ืช ืฉืœื›ื
05:20
and your life story.
85
320038
1333
ื•ืœืกื™ืคื•ืจ ื—ื™ื™ื›ื.
05:22
Or imagine if someone like Martin Luther King, for example,
86
322632
2779
ืื• ืฉืชื“ืžื™ื™ื ื• ืœืขืฆืžื›ื ืฉืžื™ืฉื”ื• ื›ืžื• ืžืจื˜ื™ืŸ ืœื•ืชืจ ืงื™ื ื’, ืœื“ื•ื’ืžื”,
05:25
had a personalized AI composer.
87
325435
2039
ื”ื™ื” ืžืฉืชืžืฉ ื‘ื”ืœื—ื ื” ืฉืœ ื‘ื™ื ื” ืžืœืื›ื•ืชื™ืช.
05:27
Maybe then we would remember
88
327498
1373
ืื•ืœื™ ืื– ื”ื™ื™ื ื• ื–ื•ื›ืจื™ื
05:28
"I Have a Dream" not only as a great speech,
89
328895
2056
ืืช "ื™ืฉ ืœื™ ื—ืœื•ื" ืœื ืจืง ื›ื ืื•ื ื ื”ื“ืจ,
05:30
but also as a great piece of music, part of our history,
90
330975
2626
ืืœื ื’ื ื›ื™ืฆื™ืจื” ืžื•ื–ื™ืงืœื™ืช ื ื”ื“ืจืช, ื—ืœืง ืžื”ื”ื™ืกื˜ื•ืจื™ื” ืฉืœื ื•,
05:33
and capturing Dr. King's ideals.
91
333625
2133
ืืฉืจ ืœื›ื“ื” ืืช ืจืขื™ื•ื ื•ืชื™ื• ืฉืœ ื“"ืจ ืงื™ื ื’.
05:36
And this is our vision at AIVA:
92
336069
1889
ื–ื” ื”ื—ื–ื•ืŸ ืฉืœ ืื™ื•"ื”:
05:37
to personalize music so that each and every one of you
93
337982
2578
ืžื•ื–ื™ืงื” ื‘ื”ืชืืžื” ืื™ืฉื™ืช, ื›ืš ืฉืœื›ืœ ืื—ื“ ืžื›ื
05:40
and every individual in the world
94
340584
1649
ื•ืœื›ืœ ืื“ื ื‘ืขื•ืœื
05:42
can have access to a personalized live soundtrack,
95
342257
3074
ืชื”ื™ื” ื’ื™ืฉื” ืœืคืกืงื•ืœ ื—ื™ ืžื•ืชืื ืื™ืฉื™ืช
05:45
based on their story and their personality.
96
345355
2505
ื”ืžื‘ื•ืกืก ืขืœ ืกื™ืคื•ืจ ื—ื™ื™ื”ื ื•ืื™ืฉื™ื•ืชื.
05:49
So this moment here together at TED is now part of our life story.
97
349915
4079
ื”ืจื’ืข ื”ื–ื” ืฉืœ ื›ื•ืœื ื• ื›ืืŸ ื‘ื™ื—ื“ ื‘ื˜ื“ ื”ื•ื ื—ืœืง ืžืกื™ืคื•ืจ ื—ื™ื™ื ื•.
05:54
So it only felt fitting that AIVA would compose music for this moment.
98
354018
4169
ืื– ื—ืฉื‘ื ื• ืฉืžืŸ ื”ืจืื•ื™ ืฉืื™ื•"ื” ืชืœื—ื™ืŸ ืžื•ื–ื™ืงื” ื‘ืฉื‘ื™ืœ ื”ืจื’ืข ื”ื–ื”.
05:58
And that's exactly what we did.
99
358674
2444
ื•ื–ื” ื‘ื“ื™ื•ืง ืžื” ืฉืขืฉื™ื ื•.
06:01
So my team and I worked on biasing AIVA on the style of the TED jingle,
100
361436
5022
ื”ืฆื•ื•ืช ืฉืœื™ ื•ืื ื™ ืขื‘ื“ื ื• ืขืœ ื”ื˜ื™ื” ืฉืœ ืื™ื•"ื” ืœืกื’ื ื•ืŸ ื”ื’'ื™ื ื’ืœ ืฉืœ ื˜ื“,
06:06
and on music that makes us feel a sense of awe and wonder.
101
366482
3444
ื•ืœืžื•ื–ื™ืงื” ืฉืชื’ืจื•ื ืœื ื• ืœื”ืจื’ื™ืฉ ื™ืจืืช ื›ื‘ื•ื“ ื•ื”ืฉืชืื•ืช.
06:09
And the result is called "The Age of Amazement."
102
369950
3913
ื”ืชื•ืฆืื” ื ืงืจืืช "ืขื™ื“ืŸ ื”ืคืœื™ืื”".
06:13
Didn't take an AI to figure that one out.
103
373887
2396
ืœื ื”ื™ื” ืฆื•ืจืš ื‘ื‘ื™ื ื” ืžืœืื›ื•ืชื™ืช ื‘ืฉื‘ื™ืœ ืœื”ืžืฆื™ื ืืช ื”ืฉื ื”ื–ื”.
06:16
(Laughter)
104
376307
1150
06:18
And I couldn't be more proud to show it to you,
105
378152
2402
ืื™ืŸ ื’ืื” ืžืžื ื™ ืœื”ืฆื™ื’ ื–ืืช ืœืคื ื™ื›ื.
06:20
so if you can, close your eyes and enjoy the music.
106
380578
2428
ืื– ืื ื ืžื›ื, ืขืฆืžื• ืขื™ื ื™ื™ื ื•ืชื”ื ื• ืžื”ืžื•ื–ื™ืงื”.
06:23
Thank you very much.
107
383030
1333
ืชื•ื“ื” ืจื‘ื” ืœื›ื.
06:25
(Music)
108
385537
4195
06:35
[The Age of Amazement Composed by AIVA]
109
395176
2667
["ืขื™ื“ืŸ ื”ืคืœื™ืื”", ื”ื•ืœื—ืŸ ืขืœ ื™ื“ื™ ืื™ื•"ื”]
08:19
(Music ends)
110
499649
1151
08:20
This was for all of you.
111
500824
1373
ื–ื” ื‘ืฉื‘ื™ืœื›ื.
08:22
Thank you.
112
502221
1166
ืชื•ื“ื” ืจื‘ื”.
08:23
(Applause)
113
503411
4573
ื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