LISTEN: A System for Recognizing Connected Speech Over Small, Fixed Vocabularies, In Real Time.

Abstract

This report describes the development of a system for recognizing connected speech in real time using a commercially available speech preprocessor, a minicomputer and programs written in FORTRAN. The system was tested on two speakers using the digits and the word 'point' with inconclusive results. Recognition accuracy of 86% was achieved for one speaker whereas accuracy for the other speaker was lower (39%) due to an anomalous difference between training and test data for that speaker's voice. (Author)

Open PDF

Document Details

Document Type
Technical Report
Publication Date
Apr 01, 1978
Accession Number
ADA056231

Entities

People

  • J. E. Porter

Tags

Communities of Interest

  • Biomedical
  • C4I
  • Human Systems
  • Space
  • Weapons Technologies

DTIC Thesaurus Topics

  • Automated Speech Recognition
  • Computational Science
  • Computer Programming
  • Computers
  • Confidence Limits
  • Decision Theory
  • Electrical Engineering
  • Engineering
  • Human Factors Engineering
  • Lists (Data Structures)
  • Mathematical Models
  • Psychology
  • Recognition
  • Statistical Decision Theory
  • Surveys
  • Systems Engineering
  • Word Recognition

Readers

  • Computational Linguistics
  • Computer Science.
  • Neural Network Machine Learning.