欢迎光临散文网 会员登陆 & 注册

【TED演讲稿】用你最爱的音乐人的声音歌唱

2023-05-23 11:03 作者:锡育软件  | 我要投稿

TED演讲者:Holly Herndon / 霍莉·赫恩登

演讲标题:What if you could sing in your favorite musician's voice? / 用你最爱的音乐人的声音歌唱

内容概要:What if you could create new music using your favorite musician's voice? Sharing her melodic gifts with the world, multidisciplinary artist Holly Herndon introduces Holly+, an AI-powered instrument that lets people sing with her own voice. Musician Pher joins her onstage to demonstrate this mind-blowing tech while singing into two microphones -- one that amplifies his natural voice and another that makes him sound just like Holly.

如果你可以用你最喜爱的音乐人的声音创作新乐曲,会怎么样?跨界艺术家霍莉·赫恩登 (Holly Herndon)将她的音乐馈赠给世界,她为我们介绍了霍莉+(Holly+)——一款让人们用她的嗓音歌唱的工具。音乐人 Pher 登上舞台,对着两个话筒示范了这项令人震撼的技术,一个话筒扩音的是他本身的声音,另一个让他听起来和霍莉一样。

*******************************************

【1】(Overlapping voices sing)

(歌声重叠)

【2】(Singing ends)

(歌声结束)

【3】(Applause) Hi, my name is Holly, and I’m an artist.

(掌声) 大家好,我叫霍莉(Holly), 我是一个艺术家。

【4】That was my voice, but I didn’t sing that clip.

这是我的声音, 但是我没有亲自唱这段。

【5】I trained an AI on my own voice, and now she can sing anything in multiple languages.

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。

【6】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.

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。

【7】Not a language that I speak and not a vocal tradition that I've trained in.

我不讲这种语言, 我也没有这种发声方式。

【8】Those melismatic runs are really difficult to hit.

唱这么多段美声可是非常难的。

【9】To show you Holly+'s full range, I'll also play an example in German.

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。

【10】This is "Mack the Knife" by Brecht.

来自布莱希特(Brecht)的 《小麦飞刀》(Mack the Knife)。

【11】(Singing in German)

(德语演唱)

【12】(Music ends) Of course Holly+ can -- thank you.

(音乐结束) 霍莉+当然可以……谢谢。

【13】(Applause) Of course, Holly+ can also perform my own music, so here's an excerpt from my own song, "Frontier."

(掌声) 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。

【14】(Singing "Frontier" in overlapping voices)

(歌声重叠演唱《边界》)

【15】(Singing ends) Holly+ uses a process called timbre transfer, where the timbre, or sound quality of one sound, may be mapped onto the performance of another.

(演唱结束) 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。

【16】Timbre transfer is done by creating a machine-learning model of a sound.

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。

【17】In this case, it's my voice.

在这个例子中, 这个声音即我的嗓音。

【18】So I recorded a wide variety of phrases in my entire vocal range.

所以我录制了我本人 全音域上的各种词语。

【19】To be clear, this version of Holly+ is reading notes from a score.

澄清一下,这个版本的霍莉+ 只是从乐谱上读音符。

【20】So I'll also play you an example of her singing in Spanish, “Bésame Mucho” by Velázquez.

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)。

【21】(Music: "Bésame Mucho")

(音乐:《深深地吻我吧》)

【22】(Music ends) Thank you.

(音乐结束) 谢谢。

【23】(Applause) I can't speak Spanish, by the way, so.

(掌声) 我可不会说西班牙语。

【24】Teaching an AI the sonic properties of one sound in order to generate an entirely new sound is what I like to call "spawning."

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)。

【25】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.

“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。

【26】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.

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。

【27】But I think spawning is far more exciting and potentially really weird.

但是我认为繁殖还要有趣得多, 而且有可能非常奇怪。

【28】(Laughter) So, for example, with sampling, usually you copy and remix a recording by someone else to create something new.

(笑声) 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。

【29】But with spawning, you can perform as someone else based on trained information about them.

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。

【30】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.

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。

【31】This also opens up the question of how we deal with a collective human archive if we can reanimate old media.

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。

【32】It opens up really big ethical and intellectual property questions that require entirely new conceptual and legal frameworks.

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。

【33】One way that I like to think about intellectual property I call identity play.

关于知识产权, 我有一个想法 叫做“身份扮演” (identity play)。

【34】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.

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。

【35】That's why I've made versions of Holly+ freely available for anyone to use online.

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。

【36】If I can allow people to play with my IP, my digital identity, my intellectual property, what might they come up with?

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?

【37】Could someone else go on tour as me, with my permission?

会不会有人在我的允许下, 以我的身份开巡回演唱会呢?

【38】Could I be in a thousand different bands in multiple languages?

我可以加入一千个 不同语种的乐队吗?

【39】And what would that even sound like?

会是什么样的场景呢?

【40】To be clear, musicians have been taught to be really protective over our IP, and that's for really good reason.

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。

【41】But I'm trying to think of ways to make this new capability mutually beneficial.

但是我在思考 如何让这种意识使双方都能受益。

【42】So to allow people to use my voice but still to maintain the ability to approve certain derivative works.

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。

【43】So I invite you to consider, if given the opportunity, who would you like to perform through?

我想请你思考一下, 如果有机会, 你想用谁的声音来唱歌?

【44】And can you imagine someone else performing you?

你可以想象一下 别人用你的声音演唱吗?

【45】With that in mind, I'd like to invite the incredible musician Pher to the stage.

带着这样的想象, 有请优秀音乐人 Pher 来到舞台。

【46】(Applause) So today, Pher will be performing his own song, "Murky."

(掌声) 今天,Pher 将为我们演唱 他的歌曲《浑浊》(Murky)。

【47】And with one microphone you'll hear Pher's beautiful, natural voice.

这个话筒是 Pher 优美自然的嗓音。

【48】(Pher vocalizing)

(Pher 歌声)

【49】(Audience cheers) And with this microphone, you'll hear a live version of Holly+ developed with Voctro Labs.

(观众欢呼声) 这个话筒是 Voctro Labs 开发的 霍莉+现场版本。

【50】(Pher vocalizing in Holly+ voice)

(Pher 使用霍莉+的歌声)

【51】(Laughter and applause) Take it away Pher.

(笑声和掌声) 来吧,Pher。

【52】(Pher singing "Murky") It gets so murky Loving what you know But I, I keep on swimming, I'm swimming Further up the road

(Pher 演唱《浑浊》) 太浑浊了 爱你所知 但是我一直游着 一直游着 逆流而上

【53】See, the problem is, I don't know what to say When you come around Acting this way Oh oh And, yes, the truth is

你看,问题是 我不知道说些什么 你来到我身边 这么做 噢,噢 没错,真相是

【54】I show you every day Cause you love to stay

我每天给你看 因为你会留下

【55】(Applause) Living in all the pain And it gets so murky Loving what you know But I'll keep on swimming

(掌声) 忍受着痛苦 越来越浑浊 爱你所知 但是我还是会一直游着

【56】Further up the road And I've been calling out Calling out your name Deep down in my sleep And I even memorized your face

逆流而上 我呼唤着 呼唤着你的名字 在我睡眠深处 我甚至还记得你的脸

【57】So ain't no leaving' me And I just handle my biz And keep the train moving on And you know what it is

所以不要离开我 我会管好自己的事 让火车继续飞驰 你知道这是什么

【58】Is just you that I'm choosing Cause it gets so murky Loving what you know And I'll I'll keep on swimming

只要你 我只会选择你 因为越来越浑浊了 爱你所知 我会 我会继续游着

【59】Further up the road And it gets so murky Loving what you know And I’ll, I'll keep on swimming Further up the road

逆流而上 越来越浑浊了 爱你所知 我会 我会继续游着 逆流而上

【60】Swimming I'm swimming Further up the road And I'll keep on swimming Swimming Further up the road

游着 我游着 逆流而上 我会一直游着 游着 逆流而上

【61】(Vocalizing)

(歌声)

【62】(Cheers and applause) Holly Herndon: Thank you.

(欢呼声和掌声) 霍莉·赫恩登 (Holly Herndon):谢谢。

【63】Thank you.


【TED演讲稿】用你最爱的音乐人的声音歌唱的评论 (共 条)

分享到微博请遵守国家法律