-
Speech analysis concept
Here’s an interesting “what if”.
FCP X already analyzes audio waveform patterns. Apple owns speech recognition software in the form of Siri. It would be great to see them enhance the FCP X Event Find bar to include speech detection, much like Avid’s PhraseFind or BorisFX’s Soundbite. Potentially there may be some patent issues, but at least in theory this concept could be built upon technology Apple owns.
Type in a phrase string and FCP X finds the clips that match this string based solely on the audio within the clip.
– Oliver
Oliver Peters Post Production Services, LLC
Orlando, FL
http://www.oliverpeters.com -
40 Replies
-
Hey Oliver,
Siri is actaully a human voice, I heard an interview just this past week with the VO artist herself, on NPR. However, I guess you’re referring to the speech recognition of user voices that generates responses from Siri, right?
With regard to speech recognition built-in to X, I am under the impression that Apple is still very much into having 3rd parties supply the majority of add-ons, so wouldn”t 3rd party software such as that from Boris suffice?
– David
David Roth Weiss
ProMax Systems
Burbank
DRW@ProMax.comSales | Integration | Support
David is a Creative COW contributing editor and a forum host of the Apple Final Cut Pro forum.
-
[David Roth Weiss] “However, I guess you’re referring to the speech recognition of user voices that generates responses from Siri, right?”
Correct.
[David Roth Weiss] “so wouldn”t 3rd party software such as that from Boris suffice”
No, because it doesn’t originate from within the application. Boris places markers that have to be imported as XML. Not nearly as useful as when you want to find a specific word to properly button the inflection of a “frankenbite”.
– Oliver
Oliver Peters Post Production Services, LLC
Orlando, FL
http://www.oliverpeters.com -
Another “what if” is Apple using iCloud’s coming server-side solution for shared libraries… That said, that would require some serious re-thinking of how Apple ID’s are setup for groups.
-
Oliver,
Demo of relevant feature from Premiere Pro / AME (Speech Analysis) (this demo uses a reference script that aids the indexing process … also it shows “clicking on words” to jump that point in the clip):
https://www.youtube.com/watch?v=DyM4NtrpY3U
Franz.
Some contents or functionalities here are not available due to your cookie preferences!This happens because the functionality/content marked as “Google Youtube” uses cookies that you choosed to keep disabled. In order to view this content or use this functionality, please enable cookies: click here to open your cookie preferences.
-
When Adobe first introduced this feature, it was very hit-or-miss. That’s because it was positioned as an instant transcription. Later Adobe sort of admitted that it was primarily a way to link text to keywords derived from the text. So they added this “dictionary” function as a way to improve the accuracy. Give it some sample text to improve the interpolation of the dialogue.
It works even better when you have the actual transcript and load that into the text field. The point is that it links the words to the point in the track when that word is spoken. In that sense it actually works a bit more like Avid ScriptSync than Avid PhraseFind. This way you can click on the word in the text field and find that portion of the clip.
– Oliver
Oliver Peters Post Production Services, LLC
Orlando, FL
http://www.oliverpeters.com -
Except that unlike ScriptSync, there is no unified view of text and all related clips.
Michael
-
[Michael Phillips] “Except that unlike ScriptSync, there is no unified view of text and all related clips. “
That’s what struck me too. There are a lot of different implementations, including several built around licensing the same Nexedia technology that Avid has, but if it was easy to build something as feature-complete as ScriptSync, more people would.
Or maybe not enough people have seen it work that they know the target to hit, or surpass, or to understand the transformative potential of getting this right.
The fact is that even the less capable or less complete alternatives are pretty amazing. Whether it’s a plug-in, or something built in to one’s NLE of choice, more people should be using it, and telling developers how to make it even more useful.
-
People will find a way to make technologies work for them if it fits their price point. But if I were working on a complicated feature or doc, my first choice would be Avid strictly because of ScriptSync (and Phrase Find, which – although it is now charged for separately used to be, if memory serves, part and parcel of ScriptSync.) Yes, Avid has it’s set of problems. But the availability of ScriptSync can often be a deal breaker.
Tim
-
ScriptSync is the automated part and is separate from script integration, which can be done manually. Both ScriptSync and PhraseFind have been extra cost options. Neither is currently available with new Avid software due to ongoing and as yet unresolved negotiations between Avid and Nexidia.
Oliver
Oliver Peters Post Production Services, LLC
Orlando, FL
http://www.oliverpeters.com -
True, but it still works with older Avid Software – at least for now. As for them being separate functions – maybe. But charging for them as separate functions – at least as I remember it – was a relatively recent happening.
Tim
Reply to this Discussion! Login or Sign Up