Toward speech as a knowledge resource

Speech is a tantalizing mode of human communication. On the one hand, human s understand speech with ease and use speech to express complex ideas, info rmation, and knowledge. On the other hand, automatic speech recognition wit h computers is very hard, and extracting knowledge from speech is even hard er. Nevertheless, the potential reward for solving this problem drives us t o pursue it. Before we can exploit speech as a knowledge resource, however, we must understand the current state of the art in speech recognition and the relevant, successful applications of speech recognition in the related areas of multimedia indexing and search. In this paper we advocate the stud y of speech as a knowledge resource, provide a brief introduction to the st ate of the art in speech recognition, describe a number of systems that use speech recognition to enable multimedia analysis, indexing, and search, an d present a number of exploratory applications of speech recognition that m ove toward the goal of exploiting speech as a knowledge resource.