Placeholder Image

字幕列表 影片播放

  • About two and a half years ago, I watched this movie called "Her."

    譯者: Lilian Chiu 審譯者: Helen Chang

  • And it features Samantha, a superintelligent form of AI

    大約兩年半前,我看了 《雲端情人》這部電影。

  • that cannot take physical form.

    片中的莎曼珊 是一種超級人工智慧,

  • And because she can't appear in photographs,

    她無法有實體。

  • Samantha decides to write a piece of music

    因為莎曼珊無法出現在照片中,

  • that will capture a moment of her life just like a photograph would.

    她決定要寫一首音樂,

  • As a musician and an engineer, and someone raised in a family of artists,

    像照片一樣捕捉她人生的片刻。

  • I thought that this idea of musical photographs was really powerful.

    我是音樂家也是工程師, 且在藝術家的家庭中長大,

  • And I decided to create an AI composer.

    我認為這音樂照片的點子強而有力。

  • Her name is AIVA, and she's an artificial intelligence

    我決定創造一個人工智慧作曲家。

  • that has learned the art of music composition

    她的名字叫艾娃(AIVA), 她是人工智慧,

  • by reading over 30,000 scores of history's greatest.

    她已經讀過了歷史上 最偉大的三萬首曲子,

  • So here's what one score looks like to the algorithm

    從中學會了音樂作曲的藝術。

  • in a matrix-like representation.

    從演算法的角度來看樂譜 就是這個樣子,

  • And here's what 30,000 scores,

    用類似矩陣的方式來表示。

  • written by the likes of Mozart and Beethoven,

    如果把莫札特和貝多芬 等級的作曲家

  • look like in a single frame.

    所寫的三萬首曲子 放到一個畫面中,

  • So, using deep neural networks, AIVA looks for patterns in the scores.

    看起來就是這樣子。

  • And from a couple of bars of existing music,

    艾娃會用深度學習的類神經網路 在樂譜中找模式。

  • it actually tries to infer what notes should come next in those tracks.

    從既有音樂的一些小節當中,

  • And once AIVA gets good at those predictions,

    她能夠試著推論出下一個 出現的音符應該是什麼。

  • it can actually build a set of mathematical rules

    等艾娃很擅長預測之後,

  • for that style of music

    她就可以為那種音樂風格

  • in order to create its own original compositions.

    建立一組數學規則,

  • And in a way, this is kind of how we, humans, compose music, too.

    用來創作她自己的原創曲。

  • It's a trial-and-error process,

    就某種意義上來說, 我們人類也是這樣作曲的。

  • during which we may not get the right notes all the time.

    它是一個試誤的過程,

  • But we can correct ourselves,

    在這個過程中,我們不見得 總是都能讓所有音符完美。

  • either with our musical ear or our musical knowledge.

    但我們能做自我修正,

  • But for AIVA, this process is taken from years and years of learning,

    用的是用我們聽音樂的耳朵, 或是用我們的音樂知識。

  • decades of learning as an artist, as a musician and a composer,

    但對艾娃來說,藝術家、 音樂家,和作曲家會需要

  • down to a couple of hours.

    花數年甚至數十年時間 來學習的這個過程,

  • But music is also a supersubjective art.

    可縮短為幾小時。

  • And we needed to teach AIVA

    但音樂是非常主觀的藝術。

  • how to compose the right music for the right person,

    我們得要教導艾娃

  • because people have different preferences.

    如何譜寫出對的音樂給對的人,

  • And to do that, we show to the algorithm over 30 different category labels

    因為大家的偏好都不相同。

  • for each score in our database.

    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

  • So those category labels are like mood

    至少三十種不同的類別標籤。

  • or note density or composer style of a piece

    這些標籤包括像是調性、

  • or the epoch during which it was written.

    音符密度、作曲家風格、

  • And by seeing all this data,

    曲子被譜寫的時期。

  • AIVA can actually respond to very precise requirements.

    看過這些資料之後,

  • Like the ones, for example, we had for a project recently,

    艾娃就可以對非常精確的 需求來做出反應。

  • where we were commissioned to create a piece

    比如,最近我們接了一個專案計畫,

  • that would be reminiscent of a science-fiction film soundtrack.

    我們受委託要創作一首作品,

  • And the piece that was created is called "Among the Stars"

    它要能讓聽眾憶起科幻電影配樂。

  • and it was recorded with CMG Orchestra in Hollywood,

    創作出來的作品叫做《星星之中》,

  • under great conductor John Beal,

    且錄音時請到好萊塢的 CMG 交響樂團來演奏,

  • and this is what they recorded, made by AIVA.

    指揮是偉大的約翰貝爾,

  • (Music)

    以下是錄音的結果,由艾娃創作。

  • (Music ends)

    (音樂)

  • What do you think?

    (音樂結束)

  • (Applause)

    你們覺得如何?

  • Thank you.

    (掌聲)

  • So, as you've seen, AI can create beautiful pieces of music,

    謝謝。

  • and the best part of it

    所以,你們都看到了, 人工智慧可以創作出美麗的音樂,

  • is that humans can actually bring them to life.

    最棒的部分是,

  • And it's not the first time in history

    人類可以賦予這些音樂生命。

  • that technology has augmented human creativity.

    這並不是史上第一次

  • Live music was almost always used in silent films

    科技可以增強人類創意。

  • to augment the experience.

    默片通常都是用現場音樂,

  • But the problem with live music is that it didn't scale.

    目的就是要增強體驗。

  • It's really hard to cram a full symphony into a small theater,

    但現場音樂的問題是 它的規模有限。

  • and it's really hard to do that for every theater in the world.

    實在很難把整個 交響樂團塞到小戲院中,

  • So when music recording was actually invented,

    且很難在世界上每個戲院 都提供現場音樂。

  • it allowed content creators, like film creators,

    所以,當音樂錄音發明出來之後,

  • to have prerecorded and original music

    內容創作者,比如電影製作人,

  • tailored to each and every frame of their stories.

    就可以用事前錄製好的原創音樂

  • And that was really an enhancer of creativity.

    根據他們故事的每一個畫格 來客製化打造。

  • Two and a half years ago, when I watched this movie "Her,"

    那其實就是創意的強化器。

  • I thought to myself that personalized music

    兩年半前,我看《雲端情人》時,

  • would be the next single biggest change in how we consume and create music.

    我心想,個人化的音樂

  • Because nowadays, we have interactive content, like video games,

    會為消費與創作音樂的方式 帶來下一個大改變。

  • that have hundreds of hours of interactive game plays,

    因為現今我們有互動式的 內容,比如電玩遊戲,

  • but only two hours of music, on average.

    雖然能播放數百小時的互動遊戲,

  • And it means that the music loops and loops and loops

    但平均只有兩小時的音樂。

  • over and over again, and it's not very immersive.

    那就意味著音樂不斷重覆,

  • So what we're working on is to make sure that AI can compose

    一而再再而三地播放, 很難非常身歷其境。

  • hundreds of hours of personalized music

    所以我們正在努力做的, 是要讓人工智慧能夠創作出

  • for those use cases where human creativity doesn't scale.

    數百小時的個人化音樂,

  • And we don't just want to do that for games.

    用在人類創意規模 受限的那些情況中。

  • Beethoven actually wrote a piece for his beloved, called "Für Elise,"

    且我們的目標不只是遊戲。

  • and imagine if we could bring back Beethoven to life.

    貝多芬為他的愛人寫過 一首作品《給愛麗絲》,

  • And if he was sitting next to you, composing a music for your personality

    想像一下,如果我們 能讓貝多芬復活。

  • and your life story.

    如果他就坐在你旁邊, 為你的個性及人生故事

  • Or imagine if someone like Martin Luther King, for example,

    譜寫音樂。

  • had a personalized AI composer.

    或是,想像一下, 比如像是金恩博士這樣的人,

  • Maybe then we would remember

    有一個個人化的人工智慧作曲家,

  • "I had a dream" not only as a great speech,

    也許我們對於 「我有一個夢」的記憶

  • but also as a great piece of music, part of our history,

    就不只是偉大的演說,也是 很棒的音樂,我們歷史的一部分,

  • and capturing Dr. King's ideals.

    捕捉到金恩博士的理念。

  • And this is our vision at AIVA:

    這就是我們對於艾娃的遠景:

  • to personalize music so that each and every one of you

    將音樂個人化,讓在座每一個人

  • and every individual in the world

    以及世界上的每一個人

  • can have access to a personalized live soundtrack,

    都能取得個人化的現場配樂,

  • based on their story and their personality.

    依據他們的故事和個性所譜寫。

  • So this moment here together at TED is now part of our life story.

    現在,我們一起在 TED 的這一刻, 就是我們人生故事的一部分。

  • So it only felt fitting that AIVA would compose music for this moment.

    所以,讓艾娃為這一刻 譜寫音樂是再適合不過了。

  • And that's exactly what we did.

    我們也的確這麼做了。

  • So my team and I worked on biasing AIVA on the style of the TED jingle,

    我和我的團隊讓艾娃 採用偏向 TED 的風格,

  • and on music that makes us feel a sense of awe and wonder.

    再加上讓我們感到 敬畏感和奇妙感的音樂。

  • And the result is called "The Age of Amazement."

    產出的成果叫做《驚奇年代》。

  • Didn't take an AI to figure that one out.

    這不需要人工智慧也能想得出來。

  • (Laughter)

    (笑聲)

  • And I couldn't be more proud to show it to you,

    接下來就要放給各位聽, 我感到非常驕傲,

  • so if you can, close your eyes and enjoy the music.

    如果可以的話, 請閉上眼睛,享受音樂。

  • Thank you very much.

    非常謝謝。

  • (Music)

    (音樂)

  • [The Age of Amazement Composed by AIVA]

    【驚奇時代,艾娃作品】

  • (Music ends)

    (音樂結束)

  • This was for all of you.

    這是給在座所有人的。

  • Thank you.

    謝謝。

  • (Applause)

    (掌聲)

About two and a half years ago, I watched this movie called "Her."

譯者: Lilian Chiu 審譯者: Helen Chang

字幕與單字

影片操作 你可以在這邊進行「影片」的調整,以及「字幕」的顯示

A2 初級 中文 美國腔 TED 作曲家 人工 曲子 創作 音符

TED】Pierre Barreau:AI如何為你的生活譜寫個性化的背景音樂(AI如何為你的生活譜寫個性化的背景音樂|皮埃爾-巴雷奧)。 (【TED】Pierre Barreau: How AI could compose a personalized soundtrack to your life (How AI could compose a personalized soundtrack to your life | Pierre Barreau))

  • 1381 77
    林宜悉 發佈於 2021 年 01 月 14 日
影片單字