评论
打印
Hi, my name is Holly, and I'm an artist.
大家好，我叫霍莉，是一名艺术家。
That was my voice, but I didn't sing that clip.
那是我的声音，但那个片段不是我唱的。
I trained an AI on my own voice, and now she can sing anything in multiple languages.
我用我自己的声音训练了一个人工智能，现在她可以用多种语言唱各种歌曲。
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.
她的名字是霍莉+，你刚才听到的是她演唱的《El Cant de la Sibilla》，这是玛丽亚·阿尔纳尔用加泰罗尼亚语改编的一首传统歌曲。
Not a language that I speak and not a vocal tradition that I've trained in.
我不会说这种语言，也没有经过这种发声方式的训练。
Those melismatic runs are really difficult to hit.
这些花腔式唱法真的很难。
To show you Holly+'s full range, I'll also play an example in German.
为了向你展示Holly+的全音域，我还将展示一首德语歌作为例子。
This is "Mack the Knife" by Brecht.
这是布莱希特的《尖刀麦基》。
Of course Holly+ can - thank you.
当然，霍莉+可以——谢谢。
Of course, Holly+ can also perform my own music, so here's an excerpt from my own song, "Frontier".
当然，霍莉+也可以演奏我自己创作的音乐，所以下面是我自己的歌曲《边界》的节选。
Holly+ uses a process called timbre transfer, where the timbre, or sound quality of one sound, may be mapped onto the performance of another.
霍莉+使用一种名为音色转换的技术，在音色转换的过程中，一种声音的音色可以映射到另一种声音上。
Timbre transfer is done by creating a machine-learning model of a sound.
音色转换是通过创建声音的机器学习模型来完成的。
In this case, it's my voice.
所以，这是我的声音。
So I recorded a wide variety of phrases in my entire vocal range.
我用我的整个音域里录下了各种各样的乐句。
To be clear, this version of Holly+ is reading notes from a score.
需要明确的是，这个版本的霍莉+可以阅读乐谱中的音符。
So I'll also play you an example of her singing in Spanish, "Besame Mucho" by Velazquez.
我还会给你们放一个她用西班牙语演唱的例子，委拉斯开兹的《无尽的吻》。
Thank you.
谢谢。
I can't speak Spanish, by the way, so.
顺便说一下，我不会说西班牙语，所以……
Teaching an AI the sonic properties of one sound in order to generate an entirely new sound is what I like to call "spawning".
教人工智能学习一种声音的声学特征，以产生一种全新的声音，我喜欢把这个过程称为“产卵”。
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.
通过产卵，霍莉+可以利用一组我演唱的乐句创作出不是由我本人演唱的各种各样的曲目。
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.
我喜欢把产卵视为21世纪音乐采样传统的一种必然发展，采样对音乐本身和知识产权都产生了非常大的影响。
But I think spawning is far more exciting and potentially really weird.
但我认为产卵要更令人兴奋，而且它可能真的很奇怪。
So, for example, with sampling, usually you copy and remix a recording by someone else to create something new.
举例来说，采样通常是复制并再合成其他人的录音来创造新的音乐。
But with spawning, you can perform as someone else based on trained information about them.
但产卵可以利用人工智能训练的内容直接以他人的身份进行演唱。
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，这让我重新思考了自己过去的工作，不仅是思考我的作品，也让我发现自己可能会因为人工智能而重新焕发活力。
This also opens up the question of how we deal with a collective human archive if we can reanimate old media.
但这也引出了一个问题：如果能够重振传统媒体，我们如何处理所有人的档案。
It opens up really big ethical and intellectual property questions that require entirely new conceptual and legal frameworks.
它引出了真正的、巨大的与伦理和知识产权相关的问题，这些问题需要全新的概念和法律框架约束。
One way that I like to think about intellectual property I call identity play.
我喜欢把知识产权想象为一种身份扮演。
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.
因此，我不限制他人对我声音的使用，相反，我创造工具，让尽可能多的人和我一起创作音乐，甚至以我的身份来创作。
That's why I've made versions of Holly+ freely available for anyone to use online.
这就是为什么我免费提供霍莉+，供所有人在线使用。
If I can allow people to play with my IP, my digital identity, my intellectual property, what might they come up with?
如果我可以允许人们使用我的IP、我的数字身份、我的知识产权，他们会创作出什么？
Could someone else go on tour as me, with my permission?
其他人可以在我的允许下，以我的身份进行巡演吗？
Could I be in a thousand different bands in multiple languages?
我可以在一千个不同的乐队中使用多种语言吗？
And what would that even sound like?
这听起来会是什么样子呢？
