A Preliminary Analysis of Human Factors Affecting the Recognition Accuracy of a Discrete Word Recognizer for C3 Systems.
NAVAL POSTGRADUATE SCHOOL MONTEREY CA
Pagination or Media Count:
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.
- Human Factors Engineering and Man Machine Systems
- Command, Control and Communications Systems