TED2018
Pierre Barreau: How AI could compose a personalized soundtrack to your life
皮耶巴勒勞: 人工智慧如何為你的人生譜寫個人化的配樂
Filmed:
Readability: 4.1
1,460,825 views
來見見艾娃（AIVA），她是人工智慧，接受音樂創作藝術的訓練，讀了超過三萬首歷史上最偉大的曲子。在這場迷人的演說和展示當中，皮耶巴勒勞播放了艾娃創作的作品，並分享他的夢想：根據我們的心情和個性來創作原創現場配樂。
Pierre Barreau - AI and music entrepreneur
Pierre Barreau is an entrepreneur, computer scientist, composer and director who loves to create impactful things. Full bio
Pierre Barreau is an entrepreneur, computer scientist, composer and director who loves to create impactful things. Full bio
Double-click the English transcript below to play the video.
00:12
About two and a half years ago,
I watched this movie called "Her."
I watched this movie called "Her."
0
913
3428
大約兩年半前，我看了
《雲端情人》這部電影。
《雲端情人》這部電影。
00:16
And it features Samantha,
a superintelligent form of AI
a superintelligent form of AI
1
4365
5127
片中的莎曼珊
是一種超級人工智慧，
是一種超級人工智慧，
00:21
that cannot take physical form.
2
9516
1760
她無法有實體。
00:23
And because she can't
appear in photographs,
appear in photographs,
3
11858
2230
因為莎曼珊無法出現在照片中，
00:26
Samantha decides to write a piece of music
4
14112
2016
她決定要寫一首音樂，
00:28
that will capture a moment of her life
just like a photograph would.
just like a photograph would.
5
16152
3466
像照片一樣捕捉她人生的片刻。
00:32
As a musician and an engineer,
and someone raised in a family of artists,
and someone raised in a family of artists,
6
20953
4408
我是音樂家也是工程師，
且在藝術家的家庭中長大，
且在藝術家的家庭中長大，
00:37
I thought that this idea of musical
photographs was really powerful.
photographs was really powerful.
7
25385
4176
我認為這音樂照片的點子強而有力。
00:41
And I decided to create an AI composer.
8
29955
2868
我決定創造一個人工智慧作曲家。
00:44
Her name is AIVA,
and she's an artificial intelligence
and she's an artificial intelligence
9
32847
3488
她的名字叫艾娃（AIVA），
她是人工智慧，
她是人工智慧，
00:48
that has learned the art
of music composition
of music composition
10
36359
2393
她已經讀過了歷史上
最偉大的三萬首曲子，
最偉大的三萬首曲子，
00:50
by reading over 30,000 scores
of history's greatest.
of history's greatest.
11
38776
2785
從中學會了音樂作曲的藝術。
00:54
So here's what one score
looks like to the algorithm
looks like to the algorithm
12
42165
2456
從演算法的角度來看樂譜
就是這個樣子，
就是這個樣子，
00:56
in a matrix-like representation.
13
44645
2202
用類似矩陣的方式來表示。
00:58
And here's what 30,000 scores,
14
46871
2246
如果把莫札特和貝多芬
等級的作曲家
等級的作曲家
01:01
written by the likes
of Mozart and Beethoven,
of Mozart and Beethoven,
15
49141
2096
所寫的三萬首曲子
放到一個畫面中，
放到一個畫面中，
01:03
look like in a single frame.
16
51261
2031
看起來就是這樣子。
01:07
So, using deep neural networks,
AIVA looks for patterns in the scores.
AIVA looks for patterns in the scores.
17
55609
4340
艾娃會用深度學習的類神經網路
在樂譜中找模式。
在樂譜中找模式。
01:12
And from a couple of bars
of existing music,
of existing music,
18
60260
3563
從既有音樂的一些小節當中，
01:15
it actually tries to infer what notes
should come next in those tracks.
should come next in those tracks.
19
63847
3708
她能夠試著推論出下一個
出現的音符應該是什麼。
出現的音符應該是什麼。
01:19
And once AIVA gets good
at those predictions,
at those predictions,
20
67887
2498
等艾娃很擅長預測之後，
01:22
it can actually build a set
of mathematical rules
of mathematical rules
21
70409
3613
她就可以為那種音樂風格
建立一組數學規則，
01:26
for that style of music
22
74046
1166
01:27
in order to create
its own original compositions.
its own original compositions.
23
75236
2788
用來創作她自己的原創曲。
01:30
And in a way, this is kind of
how we, humans, compose music, too.
how we, humans, compose music, too.
24
78490
3709
就某種意義上來說，
我們人類也是這樣作曲的。
我們人類也是這樣作曲的。
01:34
It's a trial-and-error process,
25
82561
1492
它是一個試誤的過程，
01:36
during which we may not
get the right notes all the time.
get the right notes all the time.
26
84077
3008
在這個過程中，我們不見得
總是都能讓所有音符完美。
總是都能讓所有音符完美。
01:39
But we can correct ourselves,
27
87109
1389
但我們能做自我修正，
01:40
either with our musical ear
or our musical knowledge.
or our musical knowledge.
28
88522
3293
用的是用我們聽音樂的耳朵，
或是用我們的音樂知識。
或是用我們的音樂知識。
01:45
But for AIVA, this process
is taken from years and years of learning,
is taken from years and years of learning,
29
93495
4143
但對艾娃來說，藝術家、
音樂家，和作曲家會需要
音樂家，和作曲家會需要
01:49
decades of learning as an artist,
as a musician and a composer,
as a musician and a composer,
30
97662
3262
花數年甚至數十年時間
來學習的這個過程，
來學習的這個過程，
01:52
down to a couple of hours.
31
100948
1733
可縮短為幾小時。
01:55
But music is also a supersubjective art.
32
103030
2880
但音樂是非常主觀的藝術。
01:57
And we needed to teach AIVA
33
105934
1564
我們得要教導艾娃
01:59
how to compose the right music
for the right person,
for the right person,
34
107522
2445
如何譜寫出對的音樂給對的人，
02:01
because people have different preferences.
35
109991
2141
因為大家的偏好都不相同。
02:04
And to do that, we show to the algorithm
over 30 different category labels
over 30 different category labels
36
112156
4190
為了達到這個目標，我們讓演算法
看過我們資料庫中每一首曲子的
看過我們資料庫中每一首曲子的
02:08
for each score in our database.
37
116370
1945
至少三十種不同的類別標籤。
02:10
So those category labels are like mood
38
118339
2516
這些標籤包括像是調性、
02:12
or note density or composer
style of a piece
style of a piece
39
120879
2920
音符密度、作曲家風格、
02:15
or the epoch during which it was written.
40
123823
2524
曲子被譜寫的時期。
02:18
And by seeing all this data,
41
126371
1935
看過這些資料之後，
02:20
AIVA can actually respond
to very precise requirements.
to very precise requirements.
42
128330
3056
艾娃就可以對非常精確的
需求來做出反應。
需求來做出反應。
02:23
Like the ones, for example,
we had for a project recently,
we had for a project recently,
43
131966
3103
比如，最近我們接了一個專案計畫，
02:27
where we were commissioned
to create a piece
to create a piece
44
135093
3035
我們受委託要創作一首作品，
02:30
that would be reminiscent
of a science-fiction film soundtrack.
of a science-fiction film soundtrack.
45
138152
3027
它要能讓聽眾憶起科幻電影配樂。
02:33
And the piece that was created
is called "Among the Stars"
is called "Among the Stars"
46
141839
4500
創作出來的作品叫做《星星之中》，
02:38
and it was recorded
with CMG Orchestra in Hollywood,
with CMG Orchestra in Hollywood,
47
146363
3317
且錄音時請到好萊塢的
CMG 交響樂團來演奏，
CMG 交響樂團來演奏，
02:41
under great conductor John Beal,
48
149704
1714
指揮是偉大的約翰貝爾，
02:43
and this is what they
recorded, made by AIVA.
recorded, made by AIVA.
49
151442
3067
以下是錄音的結果，由艾娃創作。
02:47
(Music)
50
155657
7000
（音樂）
03:30
(Music ends)
51
198196
2190
（音樂結束）
03:34
What do you think?
52
202719
1207
你們覺得如何？
03:35
(Applause)
53
203950
4380
（掌聲）
03:40
Thank you.
54
208354
1150
謝謝。
03:42
So, as you've seen, AI can create
beautiful pieces of music,
beautiful pieces of music,
55
210001
4055
所以，你們都看到了，
人工智慧可以創作出美麗的音樂，
人工智慧可以創作出美麗的音樂，
03:46
and the best part of it
56
214080
1803
最棒的部分是，
03:47
is that humans can actually
bring them to life.
bring them to life.
57
215907
2581
人類可以賦予這些音樂生命。
03:51
And it's not the first time in history
58
219506
1838
這並不是史上第一次
03:53
that technology has augmented
human creativity.
human creativity.
59
221368
3344
科技可以增強人類創意。
03:56
Live music was almost always
used in silent films
used in silent films
60
224736
3072
默片通常都是用現場音樂，
03:59
to augment the experience.
61
227832
1666
目的就是要增強體驗。
04:01
But the problem with live music
is that it didn't scale.
is that it didn't scale.
62
229522
3182
但現場音樂的問題是
它的規模有限。
它的規模有限。
04:04
It's really hard to cram a full symphony
into a small theater,
into a small theater,
63
232728
3429
實在很難把整個
交響樂團塞到小戲院中，
交響樂團塞到小戲院中，
04:08
and it's really hard to do that
for every theater in the world.
for every theater in the world.
64
236181
2991
且很難在世界上每個戲院
都提供現場音樂。
都提供現場音樂。
04:11
So when music recording
was actually invented,
was actually invented,
65
239196
2849
所以，當音樂錄音發明出來之後，
04:14
it allowed content creators,
like film creators,
like film creators,
66
242069
2349
內容創作者，比如電影製作人，
04:16
to have prerecorded and original music
67
244442
2786
就可以用事前錄製好的原創音樂
04:19
tailored to each and every frame
of their stories.
of their stories.
68
247252
2873
根據他們故事的每一個畫格
來客製化打造。
來客製化打造。
04:22
And that was really
an enhancer of creativity.
an enhancer of creativity.
69
250149
2626
那其實就是創意的強化器。
04:26
Two and a half years ago,
when I watched this movie "Her,"
when I watched this movie "Her,"
70
254617
3286
兩年半前，我看《雲端情人》時，
04:29
I thought to myself
that personalized music
that personalized music
71
257927
2907
我心想，個人化的音樂
04:32
would be the next single biggest change
in how we consume and create music.
in how we consume and create music.
72
260858
4417
會為消費與創作音樂的方式
帶來下一個大改變。
帶來下一個大改變。
04:38
Because nowadays, we have
interactive content, like video games,
interactive content, like video games,
73
266187
4222
因為現今我們有互動式的
內容，比如電玩遊戲，
內容，比如電玩遊戲，
04:42
that have hundreds of hours
of interactive game plays,
of interactive game plays,
74
270433
3015
雖然能播放數百小時的互動遊戲，
04:45
but only two hours of music, on average.
75
273472
2113
但平均只有兩小時的音樂。
04:47
And it means that the music
loops and loops and loops
loops and loops and loops
76
275609
2492
那就意味著音樂不斷重覆，
04:50
over and over again,
and it's not very immersive.
and it's not very immersive.
77
278125
2332
一而再再而三地播放，
很難非常身歷其境。
很難非常身歷其境。
04:52
So what we're working on
is to make sure that AI can compose
is to make sure that AI can compose
78
280467
3951
所以我們正在努力做的，
是要讓人工智慧能夠創作出
是要讓人工智慧能夠創作出
04:56
hundreds of hours of personalized music
79
284442
2302
數百小時的個人化音樂，
04:58
for those use cases
where human creativity doesn't scale.
where human creativity doesn't scale.
80
286768
3866
用在人類創意規模
受限的那些情況中。
受限的那些情況中。
05:03
And we don't just want
to do that for games.
to do that for games.
81
291363
2206
且我們的目標不只是遊戲。
05:06
Beethoven actually wrote a piece
for his beloved, called "Für Elise,"
for his beloved, called "Für Elise,"
82
294657
4428
貝多芬為他的愛人寫過
一首作品《給愛麗絲》，
一首作品《給愛麗絲》，
05:11
and imagine if we could
bring back Beethoven to life.
bring back Beethoven to life.
83
299109
3651
想像一下，如果我們
能讓貝多芬復活。
能讓貝多芬復活。
05:14
And if he was sitting next to you,
composing a music for your personality
composing a music for your personality
84
302784
5230
如果他就坐在你旁邊，
為你的個性及人生故事
為你的個性及人生故事
05:20
and your life story.
85
308038
1333
譜寫音樂。
05:22
Or imagine if someone like
Martin Luther King, for example,
Martin Luther King, for example,
86
310632
2779
或是，想像一下，
比如像是金恩博士這樣的人，
比如像是金恩博士這樣的人，
05:25
had a personalized AI composer.
87
313435
2039
有一個個人化的人工智慧作曲家，
05:27
Maybe then we would remember
88
315498
1373
也許我們對於
「我有一個夢」的記憶
「我有一個夢」的記憶
05:28
"I Have a Dream" not only
as a great speech,
as a great speech,
89
316895
2056
就不只是偉大的演說，也是
很棒的音樂，我們歷史的一部分，
很棒的音樂，我們歷史的一部分，
05:30
but also as a great piece of music,
part of our history,
part of our history,
90
318975
2626
05:33
and capturing Dr. King's ideals.
91
321625
2133
捕捉到金恩博士的理念。
05:36
And this is our vision at AIVA:
92
324069
1889
這就是我們對於艾娃的遠景：
05:37
to personalize music
so that each and every one of you
so that each and every one of you
93
325982
2578
將音樂個人化，讓在座每一個人
05:40
and every individual in the world
94
328584
1649
以及世界上的每一個人
05:42
can have access to a personalized
live soundtrack,
live soundtrack,
95
330257
3074
都能取得個人化的現場配樂，
05:45
based on their story
and their personality.
and their personality.
96
333355
2505
依據他們的故事和個性所譜寫。
05:49
So this moment here together at TED
is now part of our life story.
is now part of our life story.
97
337915
4079
現在，我們一起在 TED 的這一刻，
就是我們人生故事的一部分。
就是我們人生故事的一部分。
05:54
So it only felt fitting that AIVA
would compose music for this moment.
would compose music for this moment.
98
342018
4169
所以，讓艾娃為這一刻
譜寫音樂是再適合不過了。
譜寫音樂是再適合不過了。
05:58
And that's exactly what we did.
99
346674
2444
我們也的確這麼做了。
06:01
So my team and I worked on biasing AIVA
on the style of the TED jingle,
on the style of the TED jingle,
100
349436
5022
我和我的團隊讓艾娃
採用偏向 TED 的風格，
採用偏向 TED 的風格，
06:06
and on music that makes us feel
a sense of awe and wonder.
a sense of awe and wonder.
101
354482
3444
再加上讓我們感到
敬畏感和奇妙感的音樂。
敬畏感和奇妙感的音樂。
06:09
And the result is called
"The Age of Amazement."
"The Age of Amazement."
102
357950
3913
產出的成果叫做《驚奇年代》。
06:13
Didn't take an AI to figure that one out.
103
361887
2396
這不需要人工智慧也能想得出來。
06:16
(Laughter)
104
364307
1150
（笑聲）
06:18
And I couldn't be more proud
to show it to you,
to show it to you,
105
366152
2402
接下來就要放給各位聽，
我感到非常驕傲，
我感到非常驕傲，
06:20
so if you can, close your eyes
and enjoy the music.
and enjoy the music.
106
368578
2428
如果可以的話，
請閉上眼睛，享受音樂。
請閉上眼睛，享受音樂。
06:23
Thank you very much.
107
371030
1333
非常謝謝。
06:25
(Music)
108
373537
4195
（音樂）
06:35
[The Age of Amazement
Composed by AIVA]
Composed by AIVA]
109
383176
2667
【驚奇時代，艾娃作品】
08:19
(Music ends)
110
487649
1151
（音樂結束）
08:20
This was for all of you.
111
488824
1373
這是給在座所有人的。
08:22
Thank you.
112
490221
1166
謝謝。
08:23
(Applause)
113
491411
4573
（掌聲）
ABOUT THE SPEAKER
Pierre Barreau - AI and music entrepreneurPierre Barreau is an entrepreneur, computer scientist, composer and director who loves to create impactful things.
Why you should listen
Pierre Barreau is the CEO of AIVA, an artificial intelligence that composes music. As Barreau writes: "Ever since I was a child, I was always passionate about building things. This drive to make the imaginary real is what pushed me to create a company as soon as I got out of university. The seed of the idea for AIVA was planted once I saw the science fiction movie Her, where an AI composes a beautiful piece of piano that captures the essence of the moment she is currently living. This simple concept of creating an artificial intelligence capable of composing personalized music is how I believe that I can make the world a slightly more magical place and meaningfully support the storytelling of content creators through music."
Pierre was nominated for a Gold Panda Award in the "Best Director" category when he was 15 years old for a four-film documentary series, One Night in the Cosmos.
Pierre Barreau | Speaker | TED.com