Forum Replies Created

  • Kip Watters

    January 7, 2010 at 3:56 pm in reply to: Spoken Word Search in Video Editing Applications

    Thanks for the input. I agree that a very good transcript, time-aligned accurately and complete, is an ideal scenario. Today’s automated transcription technology is very mature, and given the tools I’ve tested, as well as actual experiences documented on this and other forums, the quality of automated transcripts isnt likely to improve anytime soon.

    I’m looking at it from a different angle — although I have limited experience using video editing and production tools, with a large number of examples I’ve seen, *some form of text-based artifacts exist if not transcripts — shooting scripts, rundowns, teleprompter text, CC — that approximate some portion of what is spoken.

    In your experience, what % of the content being edited has or had some form of dialogue in text form?

    Our Sync technology is robust in that text can be chopped up, spelled incorrectly, a superset or subset of the audio – and relevant words will still be lined up with the dialogue.

    Another question is around what you’d actually like to do with the the time-aligned transctipt once it’s produced? I’d ultimately like to see the text included as a native part of any encoded video, enabling jump-to navigation and browsing within a video from any search box (i.e., iTunes, web portals, other content distribution points, allowing the actual audio to be included as another searchable metadata element.

    Assuming no text existed that was of high enough quality to be included with the video, I envision including the audio index that Nexidia creates – alternatively included as a native part of an encoded video. The result would be identical to the scenario above -fully searchable audio with higher accuracy and potentially more coverage than a poor transcript.

    Another idea thrown out on this forum is to manually transcribe only select sentences/lines in a video and have Sync find those relevant portions to be used as chapter markers in the video. Same scenario exists – any text that can sync’ed should be natively integrated into the video.

    What are your thoughts on other uses of the time-aligned text during and after the editing process?

We use anonymous cookies to give you the best experience we can.
Our Privacy policy | GDPR Policy