A Parallel Computational Model For Integrated Speech And Natural-Language Understanding

    Authors

    S. H. Chung; D. I. Moldovan;R. F. Demara

    Comments

    Authors: contact us about adding a copy of your work at STARS@ucf.edu

    Abbreviated Journal Title

    IEEE Trans. Comput.

    Keywords

    Speech Understanding; Parallel Computational Model; Marker-Passing; Architecture; Integrated Speech And Natural Language Understanding; Memory-Based Parsing; Computer Science, Hardware & Architecture; Engineering, Electrical &; Electronic

    Abstract

    We present a parallel approach for integrating speech and natural language understanding. The method emphasizes 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 boundary detection have been analyzed and their parallel solutions are provided. Results on the SNAP-1 multiprocessor show an 80% sentence recognition rate for the Air Traffic Control (ATC) domain. Furthermore, speed-up of up to 15-fold is obtained from the parallel platform which provides response times of a few seconds per sentence for the ATC domain.

    Journal Title

    Ieee Transactions on Computers

    Volume

    42

    Issue/Number

    10

    Publication Date

    1-1-1993

    Document Type

    Article

    Language

    English

    First Page

    1171

    Last Page

    1183

    WOS Identifier

    WOS:A1993MJ55600003

    ISSN

    0018-9340

    Share

    COinS