The latest in our lunch series is with Ronny Courtens and Nouch Demeulenaere recorded during IBC in September 2016. Ronny has had an amazing career across Europe, from Olympic broadcasting to mainstream television. Nouch is both Ronny’s assistant and a video artist in her own right.
I’d like to introduce you to our first new piece of software for about two years: FinderCat. FinderCat is an easy-to-use app that converts your Final Cut Pro X Keywords into Finder Tags, so you can then filter and search for your media via Finder. In a world of Media Asset Management (MAM), and Digital Asset Management (DAM) this is a ‘no M’am’ asset organization tool.
The biggest advantage is that the FCP X keywords now travel with the media files, and will return to FCP X as keywords when re-imported, on any system.
I guess it won’t be any surprise that I have a lot of metadata entered in my Aperture photo library. In fact the lack of metadata support in Photos is the reason I can’t migrate there.
The real value of metadata is to help find photos, but sometimes the right piece of metadata is beyond value. For some paperwork related to my current husband’s ‘green card’ I needed the date of birth of my former wife. I could not remember it, but looking in my photo library, I found one taken on her 23rd birthday.
Of course I have the original date set on my photos, even those that I scanned from prints or slides. Because I had added the metadata when I knew it, I now had the all-important date I needed, and was able to file the paperwork.
Never underestimate the value of metadata!
Robert Cringely has never backed away from controversial ideas and in among a rant about Apple losing its ‘mojo’ he proposes that Apple buy up all the ‘Hollywood’ writers as an end run around Studios. And that’s an idea I proposed about seven years ago in my piece What if Apple or Google simply bypassed Networks and Studios?
Our lunch guest David Basulto graduated from being the media arts and animation instructor at award-winning San Marino High School in Southern California to an accidental entrepreneur and founder of iOgrapher. After seeing the shift to digital, he dove head first into learning as many tools as possible and fell in love with the iPad, leading to the development of the first iOgrapher devices.
He has had a interesting career as an actor and producer before becoming an education and later, entrepreneur.
The latest episode of The Terence and Philip Show features Zack Arnold, keeping fit while working in post production, and achieving full potential. It’s also our longest show ever.
One of the smart algorithms that developers can call on is Sentiment Analysis (by that or another name). Sentiment Analysis simply reads the sentiment – positive, neutral or negative – from a body of messages. It can also provide the same information on single ‘documents’, which could be transcripts.
MonkeyLearn – one of the providers of these smart algorithms – has an example of sentiment analysis from the current electoral cycle.
My question is, does this sort of metadata about the content of media, provide any benefit for post production processes; in sorting or organizing footage; or is this something you’d ever want to search for?
I’ve (along with many other people) have been beta testing SpeedScriber, an unreleased app that combines the power of an API for speech to text with a well thought out interface for correcting the machine transcription. Feed the SpeedScriber output to Lumberyard (part of Lumberjack System) and extract Magic Keywords and in a very short period of time (dependent largely on FCP X’s import speed for the XML) and you have an organized, keyworded Event with a fully searchable Transcript in the Notes field.
Microsoft claim a milestone with their Cordana speech to text transcription service, hitting an accuracy rate of 93.1% or a failure rate of 5.9%, which is reportedly the same accuracy as you’re paying $1 or $2 a minute for right now.
No human transcriber is completely accurate. There are generally some words that are unclear, or technical terms not known to the human transcriber that need correcting in a transcript.
I’ve also been one of the beta testers on SpeedScriber, which is built around an automatic engine, and have been very impressed with the accuracy, particularly with American accents. Accuracy dropped a bit when it had to deal with my still-mostly-Australian accent.
One of the powerful way Artificial Intelligence ‘learns’ is by using neural networks. Neural Networks are trained with a large number of examples where the result is known. The Neural Network adjusts until it gives the same result as the human ‘teacher’.
However, there’s a trap. If that source material contains biases – such as modeling Police ‘stop and frisk’ – then whatever biases are in the learning material will be contained in the subsequent AI modeling. This is the subject of an article in Nature: There is a blind spot in AI research and also the praise of Cathy O’Neil’s book Weapons of Math Destruction that not only brings up that issue, but the problem of “proxies”.
Proxies, in this context, are data sources that are used in AI programs that are not the actual data, but rather something that approximates the data: like using zip code as a proxy for income or ethnicity.
Based on O’Neil’s book, I’d say the authors of the Nature article are too late. There are already institutionalized biases in very commonly used algorithms in finance, housing, policing and criminal policy.