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

167,508 views ・ 2018-10-01

TED


請雙擊下方英文字幕播放視頻。

譯者: Lilian Chiu 審譯者: Helen Chang
00:12
About two and a half years ago, I watched this movie called "Her."
0
12913
3428
大約兩年半前,我看了 《雲端情人》這部電影。
00:16
And it features Samantha, a superintelligent form of AI
1
16365
5127
片中的莎曼珊 是一種超級人工智慧,
00:21
that cannot take physical form.
2
21516
1760
她無法有實體。
00:23
And because she can't appear in photographs,
3
23858
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
26112
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.
5
28152
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,
6
32953
4408
我是音樂家也是工程師, 且在藝術家的家庭中長大,
00:37
I thought that this idea of musical photographs was really powerful.
7
37385
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
41955
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
9
44847
3488
她的名字叫艾娃(AIVA), 她是人工智慧,
00:48
that has learned the art of music composition
10
48359
2393
她已經讀過了歷史上 最偉大的三萬首曲子,
00:50
by reading over 30,000 scores of history's greatest.
11
50776
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
12
54165
2456
從演算法的角度來看樂譜 就是這個樣子,
00:56
in a matrix-like representation.
13
56645
2202
用類似矩陣的方式來表示。
00:58
And here's what 30,000 scores,
14
58871
2246
如果把莫札特和貝多芬 等級的作曲家
01:01
written by the likes of Mozart and Beethoven,
15
61141
2096
所寫的三萬首曲子 放到一個畫面中,
01:03
look like in a single frame.
16
63261
2031
看起來就是這樣子。
01:07
So, using deep neural networks, AIVA looks for patterns in the scores.
17
67609
4340
艾娃會用深度學習的類神經網路 在樂譜中找模式。
01:12
And from a couple of bars of existing music,
18
72260
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.
19
75847
3708
她能夠試著推論出下一個 出現的音符應該是什麼。
01:19
And once AIVA gets good at those predictions,
20
79887
2498
等艾娃很擅長預測之後,
01:22
it can actually build a set of mathematical rules
21
82409
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
86046
1166
01:27
in order to create its own original compositions.
23
87236
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.
24
90490
3709
就某種意義上來說, 我們人類也是這樣作曲的。
01:34
It's a trial-and-error process,
25
94561
1492
它是一個試誤的過程,
01:36
during which we may not get the right notes all the time.
26
96077
3008
在這個過程中,我們不見得 總是都能讓所有音符完美。
01:39
But we can correct ourselves,
27
99109
1389
但我們能做自我修正,
01:40
either with our musical ear or our musical knowledge.
28
100522
3293
用的是用我們聽音樂的耳朵, 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,
29
105495
4143
但對艾娃來說,藝術家、 音樂家,和作曲家會需要
01:49
decades of learning as an artist, as a musician and a composer,
30
109662
3262
花數年甚至數十年時間 來學習的這個過程,
01:52
down to a couple of hours.
31
112948
1733
可縮短為幾小時。
01:55
But music is also a supersubjective art.
32
115030
2880
但音樂是非常主觀的藝術。
01:57
And we needed to teach AIVA
33
117934
1564
我們得要教導艾娃
01:59
how to compose the right music for the right person,
34
119522
2445
如何譜寫出對的音樂給對的人,
02:01
because people have different preferences.
35
121991
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
36
124156
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
02:08
for each score in our database.
37
128370
1945
至少三十種不同的類別標籤。
02:10
So those category labels are like mood
38
130339
2516
這些標籤包括像是調性、
02:12
or note density or composer style of a piece
39
132879
2920
音符密度、作曲家風格、
02:15
or the epoch during which it was written.
40
135823
2524
曲子被譜寫的時期。
02:18
And by seeing all this data,
41
138371
1935
看過這些資料之後,
02:20
AIVA can actually respond to very precise requirements.
42
140330
3056
艾娃就可以對非常精確的 需求來做出反應。
02:23
Like the ones, for example, we had for a project recently,
43
143966
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
44
147093
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.
45
150152
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"
46
153839
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,
47
158363
3317
且錄音時請到好萊塢的 CMG 交響樂團來演奏,
02:41
under great conductor John Beal,
48
161704
1714
指揮是偉大的約翰貝爾,
02:43
and this is what they recorded, made by AIVA.
49
163442
3067
以下是錄音的結果,由艾娃創作。
02:47
(Music)
50
167657
7000
(音樂)
03:30
(Music ends)
51
210196
2190
(音樂結束)
03:34
What do you think?
52
214719
1207
你們覺得如何?
03:35
(Applause)
53
215950
4380
(掌聲)
03:40
Thank you.
54
220354
1150
謝謝。
03:42
So, as you've seen, AI can create beautiful pieces of music,
55
222001
4055
所以,你們都看到了, 人工智慧可以創作出美麗的音樂,
03:46
and the best part of it
56
226080
1803
最棒的部分是,
03:47
is that humans can actually bring them to life.
57
227907
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
231506
1838
這並不是史上第一次
03:53
that technology has augmented human creativity.
59
233368
3344
科技可以增強人類創意。
03:56
Live music was almost always used in silent films
60
236736
3072
默片通常都是用現場音樂,
03:59
to augment the experience.
61
239832
1666
目的就是要增強體驗。
04:01
But the problem with live music is that it didn't scale.
62
241522
3182
但現場音樂的問題是 它的規模有限。
04:04
It's really hard to cram a full symphony into a small theater,
63
244728
3429
實在很難把整個 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.
64
248181
2991
且很難在世界上每個戲院 都提供現場音樂。
04:11
So when music recording was actually invented,
65
251196
2849
所以,當音樂錄音發明出來之後,
04:14
it allowed content creators, like film creators,
66
254069
2349
內容創作者,比如電影製作人,
04:16
to have prerecorded and original music
67
256442
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.
68
259252
2873
根據他們故事的每一個畫格 來客製化打造。
04:22
And that was really an enhancer of creativity.
69
262149
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,"
70
266617
3286
兩年半前,我看《雲端情人》時,
04:29
I thought to myself that personalized music
71
269927
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.
72
272858
4417
會為消費與創作音樂的方式 帶來下一個大改變。
04:38
Because nowadays, we have interactive content, like video games,
73
278187
4222
因為現今我們有互動式的 內容,比如電玩遊戲,
04:42
that have hundreds of hours of interactive game plays,
74
282433
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
285472
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
76
287609
2492
那就意味著音樂不斷重覆,
04:50
over and over again, and it's not very immersive.
77
290125
2332
一而再再而三地播放, 很難非常身歷其境。
04:52
So what we're working on is to make sure that AI can compose
78
292467
3951
所以我們正在努力做的, 是要讓人工智慧能夠創作出
04:56
hundreds of hours of personalized music
79
296442
2302
數百小時的個人化音樂,
04:58
for those use cases where human creativity doesn't scale.
80
298768
3866
用在人類創意規模 受限的那些情況中。
05:03
And we don't just want to do that for games.
81
303363
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,"
82
306657
4428
貝多芬為他的愛人寫過 一首作品《給愛麗絲》,
05:11
and imagine if we could bring back Beethoven to life.
83
311109
3651
想像一下,如果我們 能讓貝多芬復活。
05:14
And if he was sitting next to you, composing a music for your personality
84
314784
5230
如果他就坐在你旁邊, 為你的個性及人生故事
05:20
and your life story.
85
320038
1333
譜寫音樂。
05:22
Or imagine if someone like Martin Luther King, for example,
86
322632
2779
或是,想像一下, 比如像是金恩博士這樣的人,
05:25
had a personalized AI composer.
87
325435
2039
有一個個人化的人工智慧作曲家,
05:27
Maybe then we would remember
88
327498
1373
也許我們對於 「我有一個夢」的記憶
05:28
"I Have a Dream" not only as a great speech,
89
328895
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,
05:30
but also as a great piece of music, part of our history,
90
330975
2626
05:33
and capturing Dr. King's ideals.
91
333625
2133
捕捉到金恩博士的理念。
05:36
And this is our vision at AIVA:
92
336069
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
93
337982
2578
將音樂個人化,讓在座每一個人
05:40
and every individual in the world
94
340584
1649
以及世界上的每一個人
05:42
can have access to a personalized live soundtrack,
95
342257
3074
都能取得個人化的現場配樂,
05:45
based on their story and their personality.
96
345355
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.
97
349915
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。
05:54
So it only felt fitting that AIVA would compose music for this moment.
98
354018
4169
所以,讓艾娃為這一刻 譜寫音樂是再適合不過了。
05:58
And that's exactly what we did.
99
358674
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,
100
361436
5022
我和我的團隊讓艾娃 採用偏向 TED 的風格,
06:06
and on music that makes us feel a sense of awe and wonder.
101
366482
3444
再加上讓我們感到 敬畏感和奇妙感的音樂。
06:09
And the result is called "The Age of Amazement."
102
369950
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
373887
2396
這不需要人工智慧也能想得出來。
06:16
(Laughter)
104
376307
1150
(笑聲)
06:18
And I couldn't be more proud to show it to you,
105
378152
2402
接下來就要放給各位聽, 我感到非常驕傲,
06:20
so if you can, close your eyes and enjoy the music.
106
380578
2428
如果可以的話, 請閉上眼睛,享受音樂。
06:23
Thank you very much.
107
383030
1333
非常謝謝。
06:25
(Music)
108
385537
4195
(音樂)
06:35
[The Age of Amazement Composed by AIVA]
109
395176
2667
【驚奇時代,艾娃作品】
08:19
(Music ends)
110
499649
1151
(音樂結束)
08:20
This was for all of you.
111
500824
1373
這是給在座所有人的。
08:22
Thank you.
112
502221
1166
謝謝。
08:23
(Applause)
113
503411
4573
(掌聲)
關於本網站

本網站將向您介紹對學習英語有用的 YouTube 視頻。 您將看到來自世界各地的一流教師教授的英語課程。 雙擊每個視頻頁面上顯示的英文字幕,從那裡播放視頻。 字幕與視頻播放同步滾動。 如果您有任何意見或要求,請使用此聯繫表與我們聯繫。

https://forms.gle/WvT1wiN1qDtmnspy7