The present and future of post production business and technology | Philip Hodgetts

Oct/16

20

SpeedScriber, Lumberjack, Magic Keywords and Final Cut Pro X: magic combination

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.

The results are very encouraging with only about a 3% error rate: mostly correcting punctuation and speaker allocation. The error rate on the words is about 1% for a standard American accent. The area where I’d like to see improvement is in speaker identification. Two speakers in an interview are typically identified as 12-19 ‘speakers’. Fortunately it’s incredibly easy to correct in SpeedScriber.

That transcript is saved out as text, with time stamps every sentence, where a sentence is a very loose concept, but fine for our purposes. That transcript matches the Multicam Clip name in FCP X (or Synchronized Clip, or regular clip) and Lumberyard pairs them up, and extracts Magic Keywords.

Here’s the raw result in FCP X:

The results direct from Lumberyard.

The results direct from Lumberyard.

And here’s the result (literally) five seconds later after I tidied up the results:

Literally 5 seconds later.

Literally 5 seconds later.

I would say that those keywords are accurate for this interview.

No tags

7 comments

  • T. Payton · October 21, 2016 at 10:27 am

    Hi Philip,

    I’m testing as well and encouraged because I need this for a show I’m working on next week. However, in my tests the speakers names don’t come through to LumberYard. I’m exporting as text. Thanks!

    • Author comment by Philip · October 21, 2016 at 10:30 am

      Speaker names need to be in all caps: PHILIP not Philip. It’s the way that Lumberyard detects that it’s a speaker, and it’s the traditional way speakers or characters are identified in scripts or transcripts.

  • Shameer Mulji · October 23, 2016 at 9:31 am

    Just as an aside & out of curiousity, are you attending the Apple Keynote October 27th?

    • Author comment by Philip · October 23, 2016 at 9:39 am

      It’s an invite only event, and I didn’t get invited. However Peter Wiggins of FCP.co did get invited and will not doubt be covering anything FCP X related at fcp.co. We’ll be driving to Cupertino that day for the FCP X Creative Summit.

  • Ben Balser · October 24, 2016 at 8:14 pm

    Would this “SpeedScriber” work in helping to make SCC files for closed captioning?

    • Author comment by Philip · October 25, 2016 at 7:58 am

      .srt files were just added as an output.

<<

>>

October 2016
M T W T F S S
« Sep   Nov »
 12
3456789
10111213141516
17181920212223
24252627282930
31