NAB 2018: Adobe Talks Premiere Pro and AI

肖恩林: It's 肖恩林 here for 流媒体 Producer at NAB 2018. I'm here with Steve Forde from Adobe. 我们今天在这里讨论的是Premiere Pro和人工智能老师. What new features do you have?

史蒂夫·福德: 我最喜欢的两个, especially with Adobe Sensei, 我们在哪些方面使用人工智能和机器学习来真正增强创意过程. One of the key things is called shot matching. This is where we take the color workflow and make sure that, as you apply a color grade across, 说, 一系列剪辑, we'll actually detect the face. 我们主要围绕着人脸检测和人类在场景中的互动, and then we orient the color grade around that.

So, what we're doing is we're doing matching to the 肤色, 诸如此类的东西, and it really brings out the color profile. 作为一名编辑, 你基本上可以依靠这样一个事实，即色彩等级是围绕你的才能和镜头的焦点而定的.

肖恩林: That's really where it should be, 正确的? The talent is the focus. That's where you need to get those 肤色 just 正确的. How accurate is it as a starting point?

史蒂夫·福德: It's actually fairly accurate. 当我们说机器学习或人工智能时，我们实际上是教Premiere Pro看电视. 我们教应用程序观察和遍历成千上万个, especially if you know of our other products like Lightroom.

Lightroom的每个用户, 这是很多, is uploading every photo that they take into our Creative Cloud. We then take our algorithm and machine learn, 根据他们的照片, to understand facial structures, 肤色, and all those types of things. Then we take what that algorithm learns, and we put it into a product like Premiere Pro, so that as the editor works with the shot, 他们可以知道我们实际上是相当准确的，对于各种不同类型的用户，因为算法通过扫描创意云中的成千上万张照片学到的东西.

肖恩林: 所以，因为它有色彩匹配的应用程序，我们在其他地方看到老师在Premiere Pro工作?

史蒂夫·福德: 在音频. Another key thing is how we do understand when you have, 说, a voice as we're talking now, but you want to auto duck the background noise, or you want to be able to use a music bit. The 正确的 thing is, for us, again, Premiere Pro ... in this case, actually Audition. Audition learned to listen to what it was working with. 基本上，当人们在处理他们的内容时，他们当然允许我们. We don't do this just out of the gate.

但基本上, 当人们试图应用这些东西时，Audition作为一个算法会理解并学习, 结果就是, we can then take that algorithm and apply that in the product. As other people bring in their content, we're taking everything we've learned from before, and we're being able to do an auto keyframe, basically at a volume level and then really separate the tracks.

作为一个例子，你可以调整你的轨道的关键帧，如果它不是很准确. But the results are pretty astounding. 结果比我一开始想象的要准确得多.

肖恩林: 这也很令人兴奋，因为我肯定会有一些应用或者用例, without having to review everything, you're making sure you're not peaking, 正确的?

史蒂夫·福德: 这是正确的.

肖恩林: 添加音频当你在上面添加多层音频时，这可能会很麻烦.

史蒂夫·福德: And that's what we're trying to do with machine learning. We're not trying to replace the creative process with algorithms. 我们想要做的是加强创意过程，这样乏味的任务就不会碍事了. Those are the types of tasks that machines are really good at, so why don't we let the machine do all that stuff, and then you can focus on the creative. 它确实提高了人们可以创造的内容的标准.

肖恩林: Now, on the Adobe Media Encoder side, H.264 has been a codec that's tried and true. Everyone's using it on a daily basis. 随着下一代编解码器的发展，HEVC, AVI编解码器，它们现在的处理速度真的很慢. They don't have the hardware acceleration. What's happening in the future with Adobe? Where do you see those codecs going?

史蒂夫·福德: 我们在这个版本中真正关注的一件事是定位H.264，从那个开始.

We wanted to be able to 说, 通过解码, 就在你的回放中, but also in the encode process, we've added the hardware acceleration to that. 换句话说, 在很多情况下, 我们的速度快了五倍，几乎可以和其他应用相提并论, 如果不是更快的话, 与H.264和编码.

解码, 同样的道理, especially now that Apple released with the iPhone, HEVC is native in iOS 11, so we really wanted to up the game in terms of performance. As users are bringing not just professional cameras, but iPhones and all 诸如此类的东西 into the mix. Hardware encode and decode is a key priority for that. 我认为 we've made a lot of progress on encode. 你会看到更多的解码，所以我们得到真正流畅的4K, 8K播放，使用硬件.

But we also did one key differentiator, 所以我认为，我们的产品与市场上许多其他竞争对手的区别之一是，我们以随叫随到为导向，然后才是性能. 我们想确保你可以拨回去，因为当你做一个硬件解码或编码, you are dependent on the hardware profile. 有时，一个硬件解码与另一个硬件解码之间会有细微的差异. 我们希望能够做到的是允许用户拨回它并说, “好吧, it's going to be slower, but the pixel perfection will be there as well."

Now it's really a choice. Do I want this fast, and I can live with the output? And the output is really good. I'm not 说ing it's bad. 但如果你需要很好的像素质量，尤其是在后期使用时，H.264 is a highly compressed format, 所以我们希望能够让你获得最高质量的输出，并以此为基础.

我认为 we're now best in class, and we're not going to stop there. 我认为, as HEVC and other codecs come online, Premiere Pro的出名之处在于它可以处理任何格式，并且可以实时地进行本地处理. That is our story, and we will always continue to do that.

肖恩林: 好吧. Thank you very much, Steve. This has been a look at Adobe Premiere Pro at NAB 2018. I'm 肖恩林 for 流媒体 Producer.