SME 2018: B正确的cove的Matt Smith谈论机器学习和上下文感知编码
Learn more about AI and 环境敏感 encoding at 流媒体的下一个事件.
Read the complete transcript of this interview:
蒂姆Siglin: Welcome back to 流媒体 East 2018. 这是第二天. 我是蒂姆·西格林, contributing editor with 流媒体 magazine, and I've got with me my good friend Matt Smith. Matt, you jump companies like I fill my gas tank in my new SUV. But I think you're still at B正确的cove, 正确的?
马特·史密斯: 我还在B正确的cove. But I will remind you that I'm a good luck charm. When I show up at companies they generally end up getting bigger and-
蒂姆Siglin: 得到了. And then you decide to leave really quickly after that. 最近有个新闻 ... in fact we talked about this on the SM Advanced Forum, 你曾经客串过吗, 关于思科出售videscape的事, 或者想要购买videscape. In that it was bought around the same time as the ... I can't remember what the three-letter acronym was.
马特·史密斯: NDS，它出现得稍晚一些.
蒂姆Siglin: 好吧. And were those two essentially combined together to create Videoscape?
马特·史密斯: No, there were many components that formed Videoscape. 我的意思是，视频景观是思科在收购Inlet时提出的一个概念. Inlet became a piece of the pie, if you will. And there were a handful of other companies and technologies, 安全, video, transactions that were part of what became Videoscape.
蒂姆Siglin: 这对我来说似乎很有趣, 爱立信在视频服务模式上遇到了一些困难. 思科遇到了困难. They're at their core network delivery companies. Is this a trend that we're seeing in the industry, 这些公司认为视频将成为他们的下一个增长引擎, they're sort of having to go back to basics?
马特·史密斯: 是的, I think there's a disparity in what strategically, a handful of people in a conference room thought 10 years ago, was that we're in the data movement business. 我们有开关和这样的想法，视频最终只是1和0. There's a lot of bits that can be moved. 我记得几年前一位高管告诉我，有一天我们将在这个开关上进行编码, 正确的? 看那块岩石的顶部，看到那些闪烁的灯光，我们也会在那里做视频. And I thought, that's pretty bold.
蒂姆Siglin: 像Optibase和Black Arrow这样的公司基本上提供5-9个解决方案, but they were very limited to MPEG-2 only, 一定的数据速率. 诸如此类的事情.
马特·史密斯: 是的, but I think the very disruptive element was that OTT started, 断断续续, but then really got on this hockey stick growth, even when people were doing the no-cord-cutting, 正确的? 但我永远不会忘记几年前在旧金山湾区与一位科技记者的谈话, and was with a different company of course. And he said, “This is fascinating stuff.他说, “告诉我，我的康卡斯特(Comcast)电视什么时候会拆掉所有传统硬件，换上这个.我说:“嗯，第一，当你在飞行时，你不会把飞机上的四个引擎都换了。.”
蒂姆Siglin: 是的，当然.
马特·史密斯: 但是第二点, 大规模地传送视频, 我们还在寻找, even at the OTT side of the fence, it takes a long time to get where TV is, because TV's been doing it for 100 years.
蒂姆Siglin: 事实上, 前几天我跟别人说，有了HDR之类的东西，我们终于回到了25年前的电视时代, 或者至少试图获得接近我们在电影和原始NTSC电视中所做的图像质量.
马特·史密斯: Sure, but back to the big-heavy-iron scenarios. 我想那里发生了什么, 而且还在继续发生, is that you're realizing that virtualization has 改变了 all this. 云, 云的概念是能够处理视频，并在这些巨大的计算百家乐软件中做其他事情, 完全改变了一切. 我记得在Inlet Technologies公司的日子里，我们有了Armada产品. We would have someone who would call us and say, “我有一个10人的图书馆,000种图书, 我想要授权, 我能多快做这件事?” And the question evolved to, “How much hardware do you have?“现在气球被压缩了, and the power if you will has shifted to, as long as you've got a decent pipe to get them on that on ramp, we can process them in the cloud and do whatever you want.
The same applies for live linear, 正确的? 如果你能得到10, a hundred signals out of a facility into the cloud, and you don't have to use the traditional Fiber or satellite, 正确的? 这改变了很多. TS、SRT和快速标准是瑞士军刀中很酷的新部件，它们可以将内容从设备中取出，放入云工作流中，在那里可以对其进行操作, 改变了, we can do whatever we want with it, and then distribute it to wherever we needed to. 就在三年多以前，你和我坐在这里谈论最新的iPhone或最新的三星Galaxy. Now it's FireTVs, Rokus, AppleTVs. It's where else can I get this content.
蒂姆Siglin: Tell me what you're doing at B正确的cove. 显然，我们有上下文感知编码，你们都在做. 你在媒体方面工作，可以这么说，支持下一代电视传输. What are the key points for B正确的cove this year?
马特·史密斯: CAE's been the really exciting one. I know you and I have talked about that at length. 我们在NAB得到了非常非常好的反馈，关于这项技术的作用. 出于自私的考虑，我想说，在接下来的一年到18个月里，你会听到很多类似的军刀声. But there is really a fundamental science to this, and we have someone on staff who's very smart, 我知道你跟他谈过. Ph.D.柯达型天才, 谁会热心地指出，你可以打破某些规则，让事情看起来像我提高了质量，节省了一堆比特和带宽. 但这个故事的寓意是，有一种非常科学的方法可以做到这一点，而且不会降低信号, that doesn't change the number of frames, 有一个非常聪明的算法说你曾经在这些你熟悉的速率下使用8个数据速率. I've gone through and crunched this and spit out four, 或者是三种经过科学处理的数据速率，在感知质量上不会有任何差异, but will reduce the amount of throughput and storage.
这仍然很令人兴奋. 所以我有几个不同的客户，他们有不同类型的内容, 这才是最重要的. 你知道吗, 从动画片到独立赛车比赛或类似的游戏，实际里程会有所不同, 正确的? It's going to be different all along that curve, 但所有人都说这真的很酷，我们需要在我们自己的组织中投资, 他们的组织, 我应该说.
蒂姆Siglin: 事实上, I remember one test case video you used years ago, was I think a US Open or Wimbledon, 视频编码器的重点是确保玩家是可见的, 球是看得见的, but the faces in the crowd were just completely blanked out, and the perceptual quality optimization pieces there, 环境敏感, 会说, “好吧，脸很重要，所以我们可以把衣服扔掉, 但不一定——”
马特·史密斯: 好吧, and I think just to kind of dovetail off that, I think we're gonna get even better at it as an industry, 不仅仅是B正确的cove, 在接下来的几年里，因为机器学习使我们能够做的事情是惊人的. I don't ever want there to be weaponized capability in the cloud, then we're all going to be dealing with SkyNet. 还发生了什么事? 我们今年的重点是广播公司，帮助他们了解我们为他们提供的一系列工具和服务. 无论是在一天中不同时间播放的单一频道的新闻节目, 如果这是一个24/7的事情. But reaching those organizations, 甚至站群也会说这里有一套你可以使用的服务, where you may not have had that much choice before. 所以这是我们关注的一个领域.
蒂姆Siglin: 广播工具，比如处理SCTE 30/35和其他一些广播公司必须处理的问题，这些问题不一定是OTT问题.
马特·史密斯: Closed captions, even editing in the cloud. 这是过去几年我们必须考虑的问题. So when a live broadcast is going on, and there's ... 这是新闻广播, 有一场汽车追逐, I want to clip a piece of that car chase and get it in the station app, 在车站网站上, and also into our Twitter feed and onto our Facebook channel. 即使是在Snapchat上. 所以去了所有的目的地，知道那里有观众喜欢这个电视台的品牌
蒂姆Siglin: 能够接触到那些分散的用户群体等等. So Matt, as always, appreciate your time. We'll be 正确的 back with our next guest.
相关文章
2018 was the year that 环境敏感 encoding (CAE) went mainstream, 但2019年将是上下文感知编码达到临界质量的一年.
2019年4月3日
流媒体特约编辑蒂姆·西格林在流媒体东2018采访了IAB的埃里克·约翰
2018年5月17日
流媒体特约编辑蒂姆Siglin采访了Technicolor-Postworks的Anthony Raffaele，他在流媒体东2018上发表了主题演讲
2018年5月16日