One of the visions driving the AMI Consortium's current work is content linking; that is, presenting meeting participants with an easy way of finding archived documents and segments of meeting recordings that are relevant to an ongoing meeting.

Even if meeting participants remember about past recordings or documents that are relevant and can find them, they do not have time to search for the information they need.

Our first demonstration of this concept is a just-in-time document retrieval system that constantly retrieves documents and excerpts from previous meetings, based on recognized spoken keywords and on a context model, and displays the results in a user-friendly interface.