Focus of Attention in a Distributed-logic Speech Understanding System

Résumé du livre

The Hearsay II speech understanding system under development at Carnegie-Mellon University is a complex, distributed-logic processing system. Processing in the system is effected by independent, data-directed knowledge source processes which examine and alter values in a global data base representing hypothesized phones, phonemes, syllables, words, and phrases, as well as the hypothetical temporal and logical relationships among them. The question of how to schedule the numerous potential activities of the knowledge sources so as to understand the utterance in minimal time is called the 'focus of attention problem'. Near optimal focusing is especially important in a speech understanding system because of the very large solution space that potentially needs to be searched. Using the concepts of stimulus and response frames of scheduled knowledge source instantiations, competition among alternative responses, goals, and the desirability of a knowledge source instantiation, a general attentional control mechanism is developed. This general focusing mechanism facilitates the experimental evaluation of a variety of specific attentional control policies (such as best-first, bottom-up, and top-down search heuristics) and allows the modular addition of specialized heuristics for the speech understanding task. (Author).