18 research outputs found
A longitudinal study of computer voice recognition performance and vocabulary size
No full textThis research examined voice recognition performance as a function of time and showed no decrement in performance after 21 weeks. In addition, vocabulary sizes up to 240 utterances showed stable performance. Two people also combined their voice reference patterns and were then able to achieve an error rate of less than 2% when either person spoke to the speaker-dependent voice recognition unit. (Author)N0003981WROX008NAsponsored by Mr. Frank Deckelman, NAVELEX, Code 330, The work was performed by the author at the Naval Postgraduate Schoolhttp://archive.org/details/longitudinalstud00poo
Experiments with voice input for command and control: Using voice input to operate a distributed computer network
No full textThis report describes an experiment in which military officers used voice recognition equipment to verbally enter commands to a computer network similar to that of a command and control center, or a shipboard information center. Results suggest that voice input can result in faster operation and fewer errors for such activities and give the operator more time to do other things. In addition, operators are very comfortable using voice input because of the more natural man-machine interface. (Author)N0003980WR09041NANaval Electronic Systems Command, Washington, D. C.http://archive.org/details/experimentswithv00poo
The effect of sequentially changing background color during target detection
No full textThis experiment investigated the effect of sequentially changing the
background color during target detection. Two color sequences, three
speeds, and twenty-four subjects were used on an experimental apparatus
designed and built at the Naval Postgraduate School. A three-way factorial
analysis of variance was used to analyze the data. It appears that
both the sequence of background colors and the speed at which the color
changes have an effect on target detection time.Approved for public release; distribution is unlimited.Captain, United States Marine Corpshttp://archive.org/details/theeffectofseque109451568
Effects of emotional and perceptual-motor stress on a voice recognition system's accuracy: An applied investigation
No full textThis was an applied investigation examining the ability of a speech recognition system to recognize speakers' inputs when the speakers were under different stress levels. Subjects were asked to speak to a voice recognition system under three conditions: 1) Normal office environment, 2) Emotional Stress and 3) Perceptual-Motor Stress. Results indicate a definite relationship between voice recognition system performance and the type of low stress reference patterns used to achieve recognition. (Author)N0003983WRDX083NANaval Electronics Systems Commandhttp://archive.org/details/effectsofemotion00poo
Speech recognition in a command and control workstation environment
No full textDistinguished Alumni Award Program author. RADM Michael A. LeFever, USN (Presented 30 May 06)This thesis investigates speech recognition in a command and control workstation environment. It discusses the Navy's need for a command and control workstation (CCWS) and the importance of the human interface design. In particular, it evaluates the performance of Stanford Research Institute International (SRI's) 1000 word discrete speech recognizer. The speech board is intended to be used in the Command and Control Multi-Media workstation being developed by SRI. Additionally, it investigates a VOTAN continuous recognizer (currently for use by research and commercial vendors) in an interactive warfare simulation game. The results indicate that speech recognition systems could increase the capability of the commander to input and access information, provide more rapid response to information desired or displayed, and enhance human interaction in the man-machine interface. Past, current, and future speech applications are discussedApproved for public release; distribution is unlimited.Lieutenant Commander, United States Navyhttp://archive.org/details/speechrecognitio109452283
Effect of task duration on voice recognition system performance
No full textThis report describes an experiment examining voice recognition performance when subjects were required to make a decision every 1.5 seconds for 20 consecutive minutes while speaking to a voice recognizer at the same time. Results showed mental loading degraded voice recognition performance. Results also showed performance degradation similar to a vigilance decrement over eight trials of 2.5 minutes each. (Author)N0003980WR09041NAsponsored by Mr. Frank Deckelman, NAVELEX, Code 330.
The work was performed by the authors at the Naval Postgraduate School, Monterey,
Californiahttp://archive.org/details/effectoftaskdura00arm
Investigation and evaluation of a zero input tracking analyzer (ZITA).
No full textThis study was designed to evaluate a psychomotor testing instrument known as the ZITA (Zero Input Tracking Analyzer). This instrument was being considered as a prediction device in the selection of applicants for the U. S. Navy aircrew training program. Analysis of the data obtained from six subjects (all U. S. Navy pilots) over 26 hours of testing, showed the machine capable of consistent results in distinguishing between subjects with respect to this particular psychomotor task. A major disadvantage of the ZITA that became apparent was the amount of time (approximately 2 hours) required before learning curves were leveled out and the rate at which different individuals develop their learning curve.Approved for public release; distribution is unlimited.Lieutenant Commander, United States Navyhttp://archive.org/details/investigationnde109451781
Voice recognition vocabulary lists for the Army's TACFIRE system
No full textWithin the last year, the Naval Postgraduate School has been investigating the feasibility of using voice recognition technology as a possible input methodology to the Army's tactical fire direction system, TACFIRE. A major reason behind considering voice data entry was the desire to increase the speed and accuracy in which data could be entered into the system. In order to evaluate the effectiveness of voice data entry to TACFIRE, the speed and accuracy advantages of voice recognition technology had to be weighted against numerous performance characteristics of available state of the art recognition equipment. One such performance factor was vocabulary size limitation. This report analyzes the vocabulary requirements needed to operate the Artillery Control Console from a Division artillery display group shelter. It also presents the suggested vocabulary organization within the constraints of a specific recognizer which tested to be best suited for the TACFIRE environment. (Author)9th Infantry Division, Fort Lewis, WAhttp://archive.org/details/voicerecognition01poo
Experimental design and analyses for initial ACCAT test bed experimental demonstrations
No full textThis report documents the experimental designs and associated analyses recommended for the initial test bed experimental demonstrations at NOSC, San Diego. The areas in which initial demonstrations are to be conducted include: (1) displays; (2) TECA; (3) man-machine interface with LADDER; and (4) man-machine interface with RITA. (Author)NAsupported by the Naval Ocean Sciences Center, San Diego, Californiahttp://archive.org/details/experimentaldesi00bar
Proposed model for forecasting demand for telecommunications services for the United States Navy.
No full textThe purpose of this thesis is to examine several forecasting models for predicting demand for telecommunications services. The research addresses the determinants of demand under different conditions and examines the decision makers choice in choosing one particular method as opposed to another. After reviewing and critiquing the models, the author proposes a number of considerations in constructing a model for use in addressing the demand for telecommunications services for the United States Navy.Approved for public release; distribution is unlimited.Lieutenant Commander, United States Navyhttp://archive.org/details/proposedmodelfor109452205
