Using Hybrid Connectionist Learning for Speech/Language Analysis

In this paper we describe a screening approach for speech/ language analysis using learned, flat connectionist representations. For investigating this approach we built a hybrid connectionist system using a large number of connectionist and symbolic modules. Our system SCREEN learns a flat syntactic and semantic analysis of incremental streams of word hypothesis sequences. In this paper we focus on techniques for improving the quality of pruned hypotheses from a speech recognizer using acoustic, syntactic, and semantic knowledge. We show that the developed architecture is able to cope with real-world spontaneously spoken language in an incremental and parallel manner.

@InCollection{WW96a, 
 	 author =  {Weber, Volker and Wermter, Stefan},  
 	 title = {Using Hybrid Connectionist Learning for Speech/Language Analysis}, 
 	 booktitle = {Connectionist, Statistical and Symbolic Approaches to Learning for Natural Language Processing},
 	 editors = {Wermter, Stefan; Riloff, Ellen; Scheler, Gabriele},
 	 number = {},
 	 volume = {},
 	 pages = {87--101},
 	 year = {1996},
 	 month = {Jan},
 	 publisher = {Springer},
 	 doi = {10.1007/3-540-60925-3_40}, 
 }