History-based visual mining of semi-structured audio and text

Accessing specific or salient parts of multimedia recordings remains a challenge as there is no obvious way of structuring and representing a mix of space-based and timebased media. A number of approaches have been proposed which usually involve translating the continuous component of the multimedia recording into a space-based representation, such as text from audio through automatic speech recognition and images from video (keyframes). In this paper, we present a novel technique which defines retrieval units in terms of a log of actions performed on spacebased artefacts, and exploits timing properties and extended concurrency to construct a visual presentation of text and speech data. This technique can be easily adapted to any mix of space-based artefacts and continuous media.