A Preliminary Analysis of Human Factors Affecting the Recognition Accuracy of a Discrete Word Recognizer for C3 Systems.

Abstract

Literature pertaining to Voice Recognition abounds with information relevant to the assessment of transitory speech recognition devices. In the past, engineering requirements have dictated the path this technology followed. But, other ractors do exist that influence recognition accuracy. This thesis explores the impact of Human Factors on the successful recognition of speech, principally addressing the differences or variability among users. A Threshold Technology T-600 was used for a 100 utterance vocubalary to test 44 subjects. A statistical analysis was conducted on 5 generic categories of Human Factors: Occupational, Operational, Psychological, Physiological and Personal. How the equipment is trained and the experience level of the speaker were found to be key characteristics influencing recognition accuracy. To a lesser extent computer experience, time or week, accent, vital capacity and rate of air flow, speaker cooperativeness and anxiety were found to affect overall error rates.

Open PDF

Document Details

Document Type
Technical Report
Publication Date
Mar 01, 1983
Accession Number
ADA128546

Entities

People

  • Howard William Yellen

Organizations

  • Naval Postgraduate School

Tags

Communities of Interest

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

DTIC Thesaurus Topics

  • Accuracy
  • Air Flow
  • Automated Speech Recognition
  • Computational Science
  • Computers
  • Databases
  • Education
  • Engineering
  • Flow
  • Information Processing
  • Information Science
  • Language
  • Plastic Explosives
  • Recognition
  • Statistical Analysis
  • Systems Engineering
  • United States

Readers

  • Speech Processing/Speech Recognition.
  • Systems Analysis and Design

Technology Areas

  • AI & ML
  • Fully Networked C3
  • Fully Networked C3 - Command and Control