Learning Fault-Tolerant Speech Parsing with SCREEN

This paper describes a new approach and a system SCREEN1 for fault-tolerant speech parsing. Speech parsing describes the syntactic and semantic analysis of spontaneous spoken language. The general approach is based on incremental immediate at analysis, learning of syntactic and semantic speech parsing, parallel integration of current hypotheses, and the consideration of various forms of speech related errors. The goal for this approach is to explore the parallel interactions between various knowledge sources for learning incremental fault-tolerant speech parsing. This approach is examined in a system SCREEN using various hybrid connectionist techniques. Hybrid connectionist techniques are examined because of their promising properties of inherent fault tolerance, learning, gradedness and parallel constraint integration. The input for SCREEN is hypotheses about recognized words of a spoken utterance potentially analyzed by a speech system, the output is hypotheses about the at syntactic and semantic analysis of the utterance. In this paper we focus on the general approach, the overall architecture, and examples for learning at syntactic speech parsing. Dierent from most other speech language architectures SCREEN emphasizes an interactive rather than an autonomous position, learning rather than encoding, at analysis rather than in-depth analysis, and fault-tolerant processing of phonetic, syntactic and semantic knowledge.

@InProceedings{WW94, 
 	 author =  {Wermter, Stefan and Weber, Volker},  
 	 title = {Learning Fault-Tolerant Speech Parsing with SCREEN}, 
 	 booktitle = {Twelfth National Conference on Artificial Intelligence},
 	 number = {},
 	 volume = {},
 	 pages = {670--675},
 	 year = {1994},
 	 month = {},
 	 publisher = {},
 	 doi = {}, 
 }