评论
打印
Artist Holly Herndon does not speak Catalan.
艺术家霍莉·赫恩登不会说加泰罗尼亚语。
That was my voice but I didn't sing that clip.
那是我的声音，但那片段不是我唱的。
I trained in AI on my own voice and now she can sing anything in multiple languages.
我用自己的声音训练人工智能，现在她可以用多种语言唱任何歌。
Herndon and her team developed an artificial intelligence or AI machine learning model trained on her own voice that read musical scores in multiple languages and in any vocal range.
赫恩登和她的团队开发了一种人工智能或人工智能机器学习模型，通过她自己的声音进行训练，可以阅读多种语言和任何音域的乐谱。
She calls it her digital twin “Holly Plus”.
她称它为她的数字双胞胎“霍莉+”。
So I think a lot of people think of AI as this kind of alien other intelligence that just kind of came from nowhere.
所以我认为很多人认为人工智能是一种不知道从哪里冒出来的外星智能。
And really what it is, is aggregated human intelligence.
实际上，它是人类智慧的集合。
Herndon says any kind of media that's made machine legible can be used to train an AI to create infinite generative versions.
赫恩登说，任何一种让机器可读的媒体都可以用来训练人工智能，让它创造出无限的生成版本。
This is the real time version of Holly Plus whereas someone sings, the machine learning model produces music in Herndon's voice.
这是霍莉+的实时版本，当有人唱歌时，机器学习模型就会用赫恩登的声音制作音乐。
The musician Fur shows his real voice on one mic and sings through Holly Plus on the other.
音乐家富尔在一个麦克风上展示他的真实声音，而在另一个麦克风上霍莉+也开始唱歌。
Unlike musical deep fakes, that imitate other musicians and copy their sound.
和音乐深度造假不同，这是模仿其他音乐家并复制他们的声音。
Herndon sees machine learning as engaging with artists to create unique content.
赫恩登认为，机器学习可以与艺术家一起创造独特的内容。
I think right now it seems really scary and I completely understand why people are apprehensive about it.
我现在感觉这真的很可怕，我完全理解为什么人们会对此感到担忧。
But I think in the future it could be something that's really playful and that there are ways where the artist doesn't necessarily feel like they have relinquished all control over their work.
但我认为在未来，它可能会变得非常有趣，而且艺术家未必会认为自己的作品脱离了控制。
Already, Canadian musician Grimes this year launched AI voice software using technology similar to Holly Plus that allows people to profit from what they create, as long as they are willing to share half of their master recording royalties.
加拿大音乐家格兰姆斯今年已经推出了人工智能语音软件，使用类似于霍莉+的技术，只要人们愿意分享一半的母带唱片版税，就可以从他们的创作中获利。
Deana Mitchell, VOA news.
VOA新闻，迪娜·米切尔报道。
