speech recognition / automated transcribing

[Bob Cole]

It would be great if someone could develop software that would transcribe from a Quicktime file. It seems to me that a file would offer a lot more time for software to use contextual cues to improve word recognition. Rather than computing “on the fly” as from a live voice, file-based voice recognition could use as much time as necessary to translate sounds into words.

Just a dream? or is there someone out there who is working on file-based voice recognition?

MacPro 2 x 3GHz dualcore; 10 GB 667MHz
Kona LHe
Sony HDV Z1
Sony HDV M25U
HD-Connect MI
Betacam UVW1800
DVCPro AJ-D650

[David Roth weiss]

Bob, you must have missed my post above in this thread. Adobe SoundBooth has a transcription feature using just about any video file, i.e. Quicktime files. But, as I explained, the accuracy is not great…

David Roth Weiss
Director/Editor
David Weiss Productions, Inc.
Los Angeles

POST-PRODUCTION WITHOUT THE USUAL INSANITY ™

A forum host of Creative COW’s Apple Final Cut Pro, Business & Marketing, and Indie Film & Documentary forums.

[Bob Cole]

Thanks David. Actually I did read your post, and I should have mentioned that. Too bad Soundbooth doesn’t work well; the concept is terrific. It’s worth tracking to see whether it improves.

Bob

MacPro 2 x 3GHz dualcore; 10 GB 667MHz
Kona LHe
Sony HDV Z1
Sony HDV M25U
HD-Connect MI
Betacam UVW1800
DVCPro AJ-D650

[Mimi Kent]

I am trying to find out — two years since this thread began — if there is now software that can transcribe video interviews using voice recognition. Does this exist yet, or do I have to wait until I get my own personal jet pack?

Also, if any of you writers/story editors/editors have worked with any video software that you liked — in which watching video, writing, and doing rough edits that were then passed on to editors were all well-integrated tasks — please tell me which kind of software it was.

Thank you very much!

Best,

Mimi Kent
Preditorial
https://www.preditorial.tv/

[Bob Cole]

Hi Mimi,

Voice recognition software is rampant in the wider world. Dragon Naturally Speaking continues to improve, and there are undoubtedly many more programs.

More interesting to me is transcription from files, a feature of Adobe’s Premiere Pro. I can’t tell you how well it works; the APP forum may be a better place to explore that option.

If you find out more, let us know! I love these long-dormant threads coming to life.

Bob C

[Dennis Radeke]

The basic idea of speech-to-text feature in Premiere Pro has not changed much from CS4 to CS5 though there are some minor workflow improvements. What Adobe added in CS5 was in addition to the speech-to-text the ability to syncronize the video and dialog to a script. You can also manually enter the text and have it line up that way as well. So, there are two different methods now, depending on the materials you have.

[Kari Herring]

Try https://www.inqscribe.com- looks really good 🙂

[Bob Cole]

Just installed InqScribe. It does not transcribe on its own – it facilitates manual transcription and allows you to insert timecode. Very nice, and I’m sure it has many other features, but I was hoping for automatic transcription.

btw – tried Premiere Pro (CS4) transcription, and it was useless for the interviews I supplied. Some of the interviews were man-on-street but others were highly-controlled studio sessions, recorded with a Schoeps, very clean. The nonsense words that the software supplies are so far off base that the transcript is more trouble to read than it’s worth. ymmv!! I’d love to hear from someone who finds it useful.

Bob C

[Bob Cole]

correction: Premiere Pro didn’t provide nonsense words — it guessed real words, which was worse. If it had just provided phonetic equivalents, it would actually be easier to understand.

[Andrij Evans]

Anyone tried this?
https://www.av3software.com/products/get-for-fcp-application-v1-1-us-english

Sounds too good to be true.