PASS: a parallel speech understanding system

The authors present a parallel computational model for the integration of speech and natural language processing. The model adopts a hierarchically-structured knowledge base and memory-based parsing techniques. Processing is carried out by passing multiple markers in parallel through the knowledge base. Speech-specific problems such as insertion, deletion, substitution, and word boundaries have been analyzed and their parallel solutions are provided. The complete system has been implemented on a parallel machine and is operational. Results show a 80% sentence recognition rate for the air traffic control domain. A 10-fold speed-up can be obtained over an identical sequential implementation with an increasing speed advantage as the size of the knowledge base grows.<<ETX>>