Development of a Spoken Language System

Abstract

This report describes the activities performed and the progress made in the development of HARC (Hear And Respond to Continuous speech), BBN's spoken language system, from May 1, 1989 to February 29, 1992. Significant progress has been made both in terms of speed of understanding and accuracy of understanding. New search algorithms BBN developed during this period increased the speed of HARC by more than three orders of magnitude. The result has been the first spoken language system that runs in real-time on an off-the-shelf workstation, with no additional hardware. Furthermore, real-time performance was achieved without losing understanding accuracy. In tests performed by the National Institute of Standards and Technology (NIST) on data collected from the DARPA airline Travel Information System (ATIS) domain, the BBN HARC system had the best speech recognition and speech understanding performance. Another important milestone in this project has been the demonstration of HARC in a military logistical transportation planning application.

Open PDF

Document Details

Document Type
Technical Report
Publication Date
Apr 01, 1992
Accession Number
ADA251210

Entities

People

  • C. Barry
  • D. Ayuso
  • D. Ellard
  • F. Kubala
  • J. Makhoul
  • M. Bates
  • R. Bobrow
  • R. Ingria
  • S. Austin
  • S. Boisen

Organizations

  • BBN Technologies

Tags

Communities of Interest

  • C4I

DTIC Thesaurus Topics

  • Automated Speech Recognition
  • Birds
  • Computational Linguistics
  • Computational Science
  • Computer Programming
  • Computers
  • Databases
  • Grammars
  • Information Systems
  • Language
  • Linguistics
  • Lisp Programming Language
  • Markov Models
  • Natural Language Processing
  • Natural Language Understanding
  • Signal Processing
  • United States Transportation Command

Readers

  • Parallel and Distributed Computing.
  • Speech Processing/Speech Recognition.
  • Technical Research and Report Writing.

Technology Areas

  • AI & ML
  • AI & ML - DoD AI Strategy