Archive notice: This article was originally published on June 20, 2012. Links and embedded videos are preserved as part of the historical record.
The interface structure appears relatively simple. At the bottom of the screen is a timeline; the space above is divided into a video window and a scrolling-text editor. A specially developed algorithm analyzes the raw data from the audio and video signals, then displays it visually. By means of vertical markers, the user is told in the continuous-text editor and in the timeline where suitable places for cutting are intended to be located. The analysis relates, among other things, to positions at which the speaker is relatively still and places a marker there. The video’s images are subjected to simultaneous analysis and checked for movements that are included in the overall analysis.
The actual cutting then takes place in the text window. By deleting the words/texts, invisible cuts are or are intended to be created.
But the analysis goes several steps further and, according to the development team, is even intended to be able, at the press of a button, to remove short pauses for thought that end with an "Um," as well as repeated words. Artificial pauses in speech are also intended to be integrable with a click, allowing the rhythm to be changed afterward.
A short introduction to the program’s existing functionality:
In addition to the pure video presentation, the individual case examples can be inspected separately at the following address: Redirect
Whether and how well the tool establishes itself remains to be seen. Editors will certainly approach the tool with a healthy dose of skepticism. Furthermore, it can only be speculated whether this tool will be found in Adobe products in future.
Source: Floraine.org
