Elizabeth Ellis asked a few posts ago about voice recognition software — whether it was ready for prime time, and what people’s experiences with it were. I’ll be interested, too, in the comments her post gets, because the digital / speech divide is an important one, and one that’s increasingly being bridged by technology.
One example of that bridging is the MIT Lecture Browser. MIT’s famous open access courseware includes a lot of filmed lectures. But one of the problems with such digitized knowledge, as it were, is finding your way into and around it. The Lecture Browser, which is still a project rather than a product, lets you search for terms within lectures (that have been automatically transcribed using voice recognition software) to arrive at the correct point of interest in a video.
It’s really a remarkable achievement and one that could be immensely useful to law. Think of being able to search through a video of a court proceeding or a deposition with this sort of ease.