(Overlapping voices sing)
(歌声重叠)
(Singing ends)
(歌声结束)
(Applause)
(掌声)
Hi, my name is Holly, and I’m an artist. That was my voice, but I didn’t sing that clip. I trained an AI on my own voice, and now she can sing anything in multiple languages. Her name is Holly+, and you just heard her perform “El Cant de la Sibilla,” which is a traditional song arranged by Maria Arnal in Catalan. Not a language that I speak and not a vocal tradition that I've trained in. Those melismatic runs are really difficult to hit.
大家好,我叫霍莉(Holly), 我是一个艺术家。 这是我的声音, 但是我没有亲自唱这段。 我训练了基于我自己声音的 AI (人工智能), 她可以以多种语言 演唱任何歌曲。 她叫霍莉+(Holly+), 各位刚刚听到的是她演唱的 《西贝尔之歌》(El Cant de la Sibilla), 由玛利亚·阿纳尔(Maria Arnal) 以加泰罗尼亚语编曲的传统歌曲。 我不讲这种语言, 我也没有这种发声方式。 唱这么多段美声可是非常难的。
To show you Holly+'s full range, I'll also play an example in German. This is "Mack the Knife" by Brecht.
我来播放一段德语歌曲, 给大家展示一下霍莉+的各种语言能力。 来自布莱希特(Brecht)的 《小麦飞刀》(Mack the Knife)。
(Singing in German)
(德语演唱)
(Music ends)
(音乐结束)
Of course Holly+ can -- thank you.
霍莉+当然可以……谢谢。
(Applause)
(掌声)
Of course, Holly+ can also perform my own music, so here's an excerpt from my own song, "Frontier."
霍莉+当然可以唱出 我自己的作品, 以下为我自己的歌曲 《边界》(Frontier)的节选。
(Singing "Frontier" in overlapping voices)
(歌声重叠演唱《边界》)
(Singing ends)
(演唱结束)
Holly+ uses a process called timbre transfer, where the timbre, or sound quality of one sound, may be mapped onto the performance of another. Timbre transfer is done by creating a machine-learning model of a sound. In this case, it's my voice. So I recorded a wide variety of phrases in my entire vocal range. To be clear, this version of Holly+ is reading notes from a score. So I'll also play you an example of her singing in Spanish, “Bésame Mucho” by Velázquez.
霍莉+使用的技术称为“音色迁移” (timbre transfer), 音色,或声音的音质, 可以映射到另一个音乐作品上。 音色迁移的过程通过搭建 基于这个声音的机器学习模型完成。 在这个例子中, 这个声音即我的嗓音。 所以我录制了我本人 全音域上的各种词语。 澄清一下,这个版本的霍莉+ 只是从乐谱上读音符。 所以我想给大家展示一个 以西班牙语演唱的例子, 来自委拉兹开斯(Velázquez)的 《深深地吻我吧》(Bésame Mucho)。
(Music: "Bésame Mucho")
(音乐:《深深地吻我吧》)
(Music ends)
(音乐结束)
Thank you.
谢谢。
(Applause)
(掌声)
I can't speak Spanish, by the way, so.
我可不会说西班牙语。
Teaching an AI the sonic properties of one sound in order to generate an entirely new sound is what I like to call "spawning." Spawning is what allows Holly+ to create a wide range of vocals that I didn't sing from a set of recorded phrases that I did sing. I like to think of spawning as a kind of 21st-century corollary to the musical tradition of sampling, which had a really big impact on both music and intellectual property. But I think spawning is far more exciting and potentially really weird.
把声音的特性教给 AI, 再产生一个全新的声音, 我将这个过程 称为“繁殖”(spawning)。 “繁殖”让霍莉+可以唱出 一大堆我没有唱过的歌曲, 来自我亲口录下的词语录音。 我认为繁殖是 21 世纪音乐的 传统采样方式的必然结果, 会对音乐产业和知识产权 产生巨大的影响。 但是我认为繁殖还要有趣得多, 而且有可能非常奇怪。
(Laughter)
(笑声)
So, for example, with sampling, usually you copy and remix a recording by someone else to create something new. But with spawning, you can perform as someone else based on trained information about them. And as an artist, this is making me rethink my own past work as not only my archive but potentially also I myself could become reanimated with AI. This also opens up the question of how we deal with a collective human archive if we can reanimate old media. It opens up really big ethical and intellectual property questions that require entirely new conceptual and legal frameworks.
比如,声音采样的过程是 你复制并混合别人的录音, 创作一个新的作品。 但是繁殖是 你可以基于他人的已训练数据 以他人的演唱方式演唱。 作为一名艺术家,我受此启发 思考起了我以前的作品, 因为不仅是我过往的作品, 连我自己都会被 AI 赋予新生。 这也引出了一个问题: 如果我们可以重新 让以往的媒体资料焕发新生, 那我们该如何处理 全人类自己的老档案。 这引发了一个非常重要的伦理 和知识产权问题, 需要我们重新构想 我们的概念和法律。
One way that I like to think about intellectual property I call identity play. So rather than limiting the use of my voice, I'm creating instruments to allow as many people as possible to create music with me, and even as me. That's why I've made versions of Holly+ freely available for anyone to use online. If I can allow people to play with my IP, my digital identity, my intellectual property, what might they come up with? Could someone else go on tour as me, with my permission? Could I be in a thousand different bands in multiple languages? And what would that even sound like?
关于知识产权, 我有一个想法 叫做“身份扮演” (identity play)。 我不但不会限制使用我的嗓音, 还会创造出工具, 邀请尽可能多的人 和我,甚至是以我的身份 一起创作音乐。 这也就是为什么我把 不同版本的霍莉+放在网上, 供所有人免费使用。 如果我可以 让人们使用我的知识产权、 我的数字身份, 他们能做出什么东西呢? 会不会有人在我的允许下, 以我的身份开巡回演唱会呢? 我可以加入一千个 不同语种的乐队吗? 会是什么样的场景呢?
To be clear, musicians have been taught to be really protective over our IP, and that's for really good reason. But I'm trying to think of ways to make this new capability mutually beneficial. So to allow people to use my voice but still to maintain the ability to approve certain derivative works.
澄清一下,音乐人一直 有着很强的知识产权保护意识, 这不是没有道理的。 但是我在思考 如何让这种意识使双方都能受益。 所以,我让别人使用我的嗓音, 但是依旧拥有 审批某些衍生作品的权利。
So I invite you to consider, if given the opportunity, who would you like to perform through? And can you imagine someone else performing you? With that in mind, I'd like to invite the incredible musician Pher to the stage.
我想请你思考一下, 如果有机会, 你想用谁的声音来唱歌? 你可以想象一下 别人用你的声音演唱吗? 带着这样的想象, 有请优秀音乐人 Pher 来到舞台。
(Applause)
(掌声)
So today, Pher will be performing his own song, "Murky." And with one microphone you'll hear Pher's beautiful, natural voice.
今天,Pher 将为我们演唱 他的歌曲《浑浊》(Murky)。 这个话筒是 Pher 优美自然的嗓音。
(Pher vocalizing)
(Pher 歌声)
(Audience cheers)
(观众欢呼声)
And with this microphone, you'll hear a live version of Holly+ developed with Voctro Labs.
这个话筒是 Voctro Labs 开发的 霍莉+现场版本。
(Pher vocalizing in Holly+ voice)
(Pher 使用霍莉+的歌声)
(Laughter and applause)
(笑声和掌声)
Take it away Pher.
来吧,Pher。
(Pher singing "Murky")
(Pher 演唱《浑浊》)
It gets so murky
太浑浊了
Loving what you know
爱你所知
But I, I keep on swimming,
但是我一直游着
I'm swimming
一直游着
Further up the road
逆流而上
See, the problem is,
你看,问题是
I don't know what to say
我不知道说些什么
When you come around
你来到我身边
Acting this way
这么做
Oh oh
噢,噢
And, yes, the truth is
没错,真相是
I show you every day
我每天给你看
Cause you love to stay
因为你会留下
(Applause)
(掌声)
Living in all the pain
忍受着痛苦
And it gets so murky
越来越浑浊
Loving what you know
爱你所知
But I'll keep on swimming
但是我还是会一直游着
Further up the road
逆流而上
And I've been calling out
我呼唤着
Calling out your name
呼唤着你的名字
Deep down in my sleep
在我睡眠深处
And I even memorized your face
我甚至还记得你的脸
So ain't no leaving' me
所以不要离开我
And I just handle my biz
我会管好自己的事
And keep the train moving on
让火车继续飞驰
And you know what it is
你知道这是什么
Is just you that
只要你
I'm choosing
我只会选择你
Cause it gets so murky
因为越来越浑浊了
Loving what you know
爱你所知
And I'll
我会
I'll keep on swimming
我会继续游着
Further up the road
逆流而上
And it gets so murky
越来越浑浊了
Loving what you know
爱你所知
And I’ll,
我会
I'll keep on swimming
我会继续游着
Further up the road
逆流而上
Swimming
游着
I'm swimming
我游着
Further up the road
逆流而上
And I'll keep on swimming
我会一直游着
Swimming
游着
Further up the road
逆流而上
(Vocalizing)
(歌声)
(Cheers and applause)
(欢呼声和掌声)
Holly Herndon: Thank you. Thank you.
霍莉·赫恩登 (Holly Herndon):谢谢。 谢谢大家。