| Novel Communications and Hearing Protection for Helmet Systems: Communications Earplug |
MAR 1998 |
13 pages |
| Authors:
Ben T. Mozo; Barbara A. Murphy; ARMY AEROMEDICAL RESEARCH LAB FORT RUCKER AL
|
 | Communications and hearing protection are usually necessary for personnel involved in Army operations. Aircraft and ground vehicles produce noise levels in excess of the limits defined in current hearing conservation standards. Hearing protection and communications elements of most helmets constitute a significant portion of the weight of standard helmets. Further, performance of most helmets is marginal with respect to speech intelligibility and hearing protection. Some noise environments require that earplugs ... |
|
| Software Package for Speaker Independent or Dependent Speech RecognitionUsing Standard Objects for Phonetic Speech Recognition |
09 FEB 98 |
46 pages |
| Authors:
M. Pfister; STANDARD OBJECT SYSTEMS INC
|
| The research identified the overall requirements of an end to end phonetic speech recognition process for a speech recognition software product (SPSR). The effort has focused on expanding the existing Standard Objects for Phonetic Speech Recognition technology to the design of innovative software for a speaker independent continuous speech recognition system that can exploit the current parallel digital signal processing and mircocomputer technology. This ... |
|
| Architecture and Concept of Operations for a Warfighter's Internet. Volume 2: Appendices |
28 JAN 98 |
|
| Authors:
MASSACHUSETTS INST OF TECH LEXINGTON LINCOLN LAB
|
 | This report consists of two volumes. This is Volume 2: Appendices, which contains Appendices A-L of the main report (volume 1). Military operations in the twenty-first century will be conducted in an increasingly information- rich environment. But delivery of this information is difficult in the forward areas of the tactical theater where current communications equipment is slow to deploy and not matched to the mobility of forward forces. This report ... |
|
| Monitoring the Simultaneous Presentation of Spatialized Speech Signals in a Virtual Acoustic Environment |
1998 |
9 pages |
| Authors:
W. T. Nelson; Robert S. Bolia; Mark A. Ericson; Richard L. McKinley; AIR FORCE RESEARCH LAB WRIGHT-PATTERSON AFB OH HUMAN EFFECTIVENESS DIRECTORATE
|
| The effect of spatial auditory information on a listener's ability to detect, identify, and monitor multiple simultaneous speech signals was evaluated using virtual audio technology. Factorial combinations of three variables - the number of localized speech signals, the location of the speech signals around the horizontal plane, and the sex of the talker - were employed using a within- subjects design. Participants were required to detect the presentation of a ... |
|
| Application of Network Voice to Navy and DOD Telecommunications |
1998 |
5 pages |
| Authors:
Michael S. McBeth; R. B> Adamson; Raymond Cole Jr.; NAVAL RESEARCH LAB WASHINGTON DC INFORMATION TECHNOLOGY DIV
|
| The application of network voice technology~ to Navy and DoD telecommunications offers possibilities for highly integrated communications services including voice, data, and video while maintaining interoperability with legacy communication systems. The need for network voice technology can be understood by considering the level of voice integration being achieved in contemporary shipboard backbone networks. Voice transport across shipboard Asynchronous Transfer Mode (ATM networks being installed under the Navy's Information Technology for ... |
|
| Voice Technology Study Report |
DEC 1997 |
29 pages |
| Authors:
Richard M. Mogford; Armida Rosiles; Dan Wagner; Kenneth R. Allendoerfer; FEDERAL AVIATION ADMINISTRATION TECHNICAL CENTER ATLANTIC CITY NJ
|
| This document presents the findings of a voice technology study that evaluated the potential of a speech to text and voice recognition system to support an Airway Facilities maintenance task. Researchers conducted the test at an Airport Surveillance Radar (ASR)-9 site at the William J. Hughes Technical Center. Thirteen Airway Facilities specialists completed the procedure twice, once with the voice technology system and again with a ... |
|
| Human Factors Evaluation of Vocoders for Air Traffic Control Environments Phase II: ATC Simulation |
DEC 1997 |
48 pages |
| Authors:
Randy L. Sollenberger; James LaDue; Brian Carver; Annmarie Heinze; FEDERAL AVIATION ADMINISTRATION TECHNICAL CENTER ATLANTIC CITY NJ
|
| Vocoders offer a potential solution to radio congestion by digitizing human speech and compressing the signal to achieve low bandwidth voice transmissions. A reduction in bandwidth will allow the addition of more communication channels to the system and reduce radio congestion. This air traffic control simulation study is the second phase of a research effort to compare the effectiveness of two 4.8 kbps vocoders (designated as ... |
|
| OPNET Implementation of Spread Spectrum Network for Voice and Data Distribution |
DEC 1997 |
137 pages |
| Authors:
Roger D. Standfield; NAVAL POSTGRADUATE SCHOOL MONTEREY CA
|
| This thesis presents an OPNET model and simulation of a single cell wireless communications system within a proposed expeditionary warfare communications network. The focus of this thesis is to model and implement data and voice traffic generation, slofted ALOHA medium access control protocol, and direct sequence spread spectrum code division multiple access (CDMA) mechanisms in OPNET. The RF channel is modeled as both a Rayleigh ... |
|
| Air Force Instruction 33-217 Communications and Information Voice Call Sign Program |
01 OCT 1997 |
|
| Authors:
DEPARTMENT OF THE AIR FORCE WASHINGTON DC
|
|
| Lip Tracking for Audio-Visual Speech Recognition |
30 SEP 97 |
|
| Authors:
Robert A. Kaucic Jr; AIR FORCE INST OF TECH WRIGHT-PATTERSON AFB OH
|
| Human speech is conveyed through both acoustic and visual channels and is therefore inherently multi-modal. Further, the two channels are largely complementary in that the acoustic signal typically contains information about the manner of articulation while the visual signal embodies knowledge of the place of articulation. This orthogonal nature of the audio and visual components has enticed researchers to develop audio-visual speech recognition systems that have been shown to be ... |
|
| Robust Speech Recognition Interface to the Electronic Crewmember: Progress and Challenges |
15 SEP 1997 |
7 pages |
| Authors:
David T. Williamson; AIR FORCE RESEARCH LAB WRIGHT-PATTERSON AFB OH
|
| Speech is a natural form of communication between humans. It should come as no surprise that it would also be the ideal form of communication between a pilot and an electronic crewmember. High-level commands spoken by the pilot would be interpreted and carried out by the electronic crewmember in much the same way that a pilot would talk to another crewmember. The realization of this natural interface will depend on ... |
|
| Human Factors Evaluation of Vocoders for Air Traffic Control Environments Phase I: Field Evaluation |
SEP 97 |
61 pages |
| Authors:
James LaDue; Randy L. Sollenberger; Bill Belanger; Annemarie Heinze; FEDERAL AVIATION ADMINISTRATION TECHNICAL CENTER ATLANTIC CITY NJ
|
| Communication congestion is a major problem facing the air traffic control system. Vocoders offer a potential solution to this problem by compressing a digitized human speech signal to achieve low bandwidth voice transmissions. Air traffic controllers and pilots must find new systems usable and acceptable before the FAA authorizes implementation. This study compared the performance of two 4.8 kbps vocoders (designated as A and B) with the current analog radio ... |
|
| Economic Evaluation of Voice Recognition (VR) for the Clinician's Desktop at the Naval Hospital Roosevelt Roads |
SEP 1997 |
159 pages |
| Authors:
NAVAL POSTGRADUATE SCHOOL MONTEREY CA
|
| This thesis investigates the current status of VR technology, its use in support of Joint vision 2010, its use in the Healthcare environment and provides an analysis of the VR Pilot Project at NHRR. The objective of the analysis is to determine the viability and economical benefits of using a Commercial Off-The-Shelf (COTS) VR application as a clinicians input device for transcribing clinical encounter (SOAP) notes. The VR application used ... |
|
| Acoustic Communication System. |
26 AUG 1997 |
|
| Authors:
Paul W. Sutton; DEPARTMENT OF THE NAVY WASHINGTON DC
|
| An acoustic communication system comprises: a voice processing circuit which generates a first signal representing a voice message; a noise sensor channel which generates a second signal in response to detecting background noise in an environment; a microcomputer which receives the first and second signals and provides a third signal to a selected one of first and second output ports of the microcomputer where the amplitude of the third signal ... |
|
| The Voice-Activated Multilingual Interview System |
AUG 97 |
30 pages |
| Authors:
Paul G. Bamberg; Carol Kunz; DRAGON SYSTEMS INC NEWTON MA
|
| The Multilingual Interview System is a Windows-based application program designed to let users conduct simple interviews by voice in languages they do not speak. Any statement or question that is within the vocabulary, when spoken into a microphone attached to the computer, is recognized by a large- vocabulary speech recognition system and converted into a sequence of pre- recorded wave files which are they played back through a loudspeaker attached ... |
|
| Analytical and Computational Methods for Nonlinear Feedback Design |
AUG 1997 |
37 pages |
| Authors:
Christopher I. Byrnes; Alberto Isidori; WASHINGTON UNIV ST LOUIS MO DEPT OF SYSTEMS SCIENCE AND MATHEMATICS
|
| The lack of a systematic methodology for the design of feedback laws capable of controlling complex dynamical systems has been a limiting factor in several current and emerging DoD missions. The research carried out by the principal investigators in this three year research effort has focused on analyzing and computing the steady-state behavior of controlled complex dynamical systems. One of the fundamental discoveries made during ... |
|
| Technology Review of the Use of Continuous Speech Recognition for Language Training |
JUL 97 |
156 pages |
| Authors:
C. M. Knerr; V. M. Holland; HUMAN RESOURCES RESEARCH ORGANIZATION ALEXANDRIA VA
|
| The Technology Review for Speech Recognition for Language Sustainment was an effort of the Special Operations Research, Development and Acquisition Center, the U.S. Army Research Institute and the Advanced Research Projects Agency in cooperation with the U.S. Army Special Operations Command Language Office. The review examined the state-of-the-art in continuous speech recognition (CSR) as it applies to foreign language training, sustainment, and enhancement for the Special Operations Forces (SOF). The ... |
|
| Demodulation Processes in Auditory Perception |
01 JUN 97 |
8 pages |
| Authors:
Lawrence Feth; OHIO STATE UNIV COLUMBUS DEPT OF SPEECH AND HEARING SCIENCE
|
| The long range goal of this project was the understanding of human auditory processing of information conveyed by complex, time varying signals such as speech, music or important environmental sounds. Our work was guided by the assumption that human auditory communication is a 'modulation - demodulation' process. That is, we assume that sound sources produce a complex stream of sound pressure waves with information encoded as variations (modulations) of the ... |
|
| Audio Effectiveness in Aviation (L'Efficacite des Communications Vocales en Aeronautique) |
JUN 97 |
|
| Authors:
ADVISORY GROUP FOR AEROSPACE RESEARCH AND DEVELOPMENT NEUILLY-SUR-SEINE (FRAN CE)
|
| The Aerospace Medical Panel of the Advisory Group for Aerospace Research and Development (AGARD) held a Symposium entitled 'Audio Effectiveness in Aviation', in Copenhagen, Denmark, 7-11 October 1996. It was held in order to address concerns that, while effective voice communications and aural signals are important in military and civil aviation, their implementations are often less than satisfactory in modern aircraft. Factors that influence this are: (a) in many cases ... |
|
| Human Factors Recommendations for Airborne Controller-Pilot Data Link Communications (CPDLS) Systems: A Synthesis of Research Results and Literature |
JUN 97 |
93 pages |
| Authors:
Albert J. Rehmann; FEDERAL AVIATION ADMINISTRATION TECHNICAL CENTER ATLANTIC CITY NJ
|
| This document provides a synthesis of research results and literature culminating in specific human factors recommendations for Controller-Pilot Data Link Communications (CPDLC) systems. The report concentrates on two major human factors top areas; system operability, and system implementation. System operability includes issues such as display location, crew alerting, and message formatting, etc. System implementation includes issues such as situation awareness/party line, airspace environment, mixed modality communications, etc. The findings provide ... |
|
| Speech Coding and Phoneme Classification Using a Back-Propagation Neural Network |
07 MAY 1997 |
78 pages |
| Authors:
Brett A. St. George; NAVAL ACADEMY ANNAPOLIS MD
|
| Speech is a natural, unspecialized method of communication that is perhaps the ultimate machine interface. Previous attempts to provide such an interface, however, have been limited to pre-defined vocabularies of an artificial syntax. This paper presents a method for speaker-dependent speech identification that uses a back-propagation neural network to determine the phonemes present within a voice signal. The vocal tract changes slowly in time and can be modeled using the ... |
|
| 3-Dimensional Audio Ergonomic Improvement Project for the NORAD CMOC |
MAY 1997 |
32 pages |
| Authors:
Debra North; William R. D'Angelo; ARMSTRONG LAB WRIGHT-PATTERSON AFB OH CREW SYSTEMS DIRECTORATE
|
| This technical report describes the concept, design, development, and on-site evaluation of a 3-dimensional (3-D) audio interface system for potential operational use by North American Aerospace Defense (NORAD). An initial prototype phase was used to evaluate the 3-D audio interface system in an operational exercise setting giving NORAD operators the capability to conduct hands-free communication over multiple communication lines. This 3-D audio interface system enabled hands-free communications by providing a ... |
|
| A Transducer/Equipment System for Capturing Speech and Telemedicine Information for Subsequent Processing by Computer Systems |
APR 1997 |
65 pages |
| Authors:
Benjamin Tirabassi; TECHNICAL EVALUATION RESEARCH INC LITTLE SILVER NJ
|
| Benchmarked speech capture data formed a corpus for the research to determine how the noise characterization information can best be used to improve speech recognition performance under tactical high noise conditions. The various speech capture improvement remedies investigated focused on a combination of methods that are matched to the FFT derived characterization of the tactical noise or medical sensor signals. These methods include stochastic canceling techniques for random (non-stationary) noise ... |
|
| The Assessment of Sound Attenuation and Speech Intelligibility of Selected Active Noise Reduction Devices and the Communications Earplug When Used with the HGU-56/P Aviator Helmet |
JAN 1997 |
|
| Authors:
Ben T. Mozo; Barbara A. Murphy; ARMY AEROMEDICAL RESEARCH LAB FORT RUCKER AL
|
| The Program Manager for Aircrew Integrated Systems (PM-ACIS), formerly Aviation Life Support Equipment (PM-ALSE), requested the U.S. Army Aeromedical Research Laboratory (USAARL) examine the status of active noise reduction (ANR) systems available in the marketplace. The mechanism for acquiring the devices was a Cooperative Research and Development Agreement (ORDA) which was implemented with three U.S. corporations. Each corporation agreed to modify three HGU-56 aviator helmets, furnished by the Government, by ... |
|
| The Acoustic-to-Articulatory Mapping of Voiced and Fricated Speech |
1997 |
179 pages |
| Authors:
Edward L. Riegelsberger; AIR FORCE RESEARCH LAB BOLLING AFB DC
|
| Acoustic-to-articulatory mapping is the estimation of a time-varying vocal-tract shape from an acoustic waveform. While most research in acoustic-to- articulatory mapping considers only purely voiced speech, this dissertation investigates the problem for speech that includes fricatives. Aspects of fricative production and perception challenge many of the assumptions and techniques used in existing acoustic-to-articulatory mapping algorithms. This work investigates these issues and extends existing techniques for the acoustic- to-articulatory mapping of ... |
|
| A Two-Phase Damped-Exponential Model for Speech Synthesis |
17 DEC 96 |
106 pages |
| Authors:
H. A. Arb; AIR FORCE INST OF TECH WRIGHT-PATTERSON AFB OH SCHOOL OF ENGINEERING
|
| It is well known that there is room for improvement in the resultant quality of speech synthesizers in use today. This research focuses on the improvement of speech synthesis by analyzing various models for speech signals. An improvement in synthesis quality will benefit any system incorporating speech synthesis. Many synthesizers in use today use linear predictive coding (LPC) techniques and only use one set of vocal tract parameters per analysis ... |
|
| Recognition-Time Speaker Adaptation in a Tied-Mixture HMM Continuous Speech Recognizer |
16 DEC 96 |
|
| Authors:
B. F. Necioglu; D. B. Paul; MASSACHUSETTS INST OF TECH LEXINGTON LINCOLN LAB
|
| All speech recognition systems, whether speaker-independent or speaker-dependent, require large amounts of training data to estimate the model parameters and, generally, the more training data available, the better the recognition performance. To improve the recognition performance of a system for a new speaker without having to train entirely new models, adapting the existing models during the recognition process is a practical solution. This report describes an investigation into the subject ... |
|
| Weighted Mahalanobis Distance for Hyper-Ellipsoidal Clustering |
DEC 96 |
110 pages |
| Authors:
Khaled S. Younis; AIR FORCE INST OF TECH WRIGHT-PATTERSON AFB OH SCHOOL OF ENGINEERING
|
| Cluster analysis is widely used in many applications, ranging from image and speech coding to pattern recognition. A new method that uses the weighted Mahalanobis distance (WMD) via the covariance matrix of the individual clusters as the basis for grouping is presented in this thesis. In this algorithm, the Mahalanobis distance is used as a measure of similarity between the samples in each cluster. This thesis discusses some difficulties associated ... |
|
| MEDTAG: An Evaluation of Three Data Input Methods for Battlefield Medical Documentation |
DEC 96 |
46 pages |
| Authors:
Paula J. Konoske; Richard B. Fitzgerald; Kristee E. Emens-Hesslink; Robert J. Reed; NAVAL HEALTH RESEARCH CENTER SAN DIEGO CA
|
| Historically, the Field Medical Card (FMC) has been used to provide the clinical documentation that moves with a casualty during evacuation. The Department of Defense (DoD) Medical Readiness Strategic Plan (MRSP), promulgated in February 1988, determined that the FMC was deficient, and a quad-service working group was formed to develop a revised card. Consensus among the services determined that the revised card captured all of the information needed at the ... |
|
| Development and Performance of a Cockpit Control System Operated by Voice: Summary Report of Project DMKLu/ACO2/A/9lO5 |
29 NOV 96 |
|
| Authors:
H. J. Steeneken; HUMAN FACTORS RESEARCH INST TNO SOESTERBERG (NETHERLANDS)
|
| Phase 3 of this project is concerned with the evaluation of an automatic speech recognizer for cockpit control functions in the MLU-F16. The report is a summary of the following 3 reports: (1) Automatic speech recognition performance in a simulation-based fast-jet cockpit application, (2) Spontaneous- speech data base for cockpit control applications applied to commercial state- of-the-art speech recognition technology, and (3) Evaluation of integrated automatic speech recognition on the ... |
|
| Automatic Speech Recognition Performance in a Simulation-Based Fast-Jet Cockpit Application (Automatische spraakherkenning toegepast voor controletaken in de cockpit van een jachtvliegtuig) |
28 NOV 96 |
|
| Authors:
H. J. Steeneken; J. J. Kriekaard; D. A. van Leeuwen; HUMAN FACTORS RESEARCH INST TNO SOESTERBERG (NETHERLANDS)
|
| A project on automatic speech recognition for control of systems in a fast-jet cockpit was conducted by the TNO Human Factors Research Institute (TNO- HFRI) and the National Aerospace Laboratory (NLR). The project comprised performance testing in an advanced fast jet simulator. In total the results of 17 sorties, performed by three experienced pilots, are presented. During each sortie the pilot had access to a control by voice of radio ... |
|
| Multiprocessor Implementation of a Real-Time Celp Algorithm |
NOV 96 |
91 pages |
| Authors:
Glenn Prescott; Hari N. Chakravarthula; Sinivas Sivaprakasam; Timouthy Johnson; KANSAS UNIV CENTER FOR RESEARCH INC LAWRENCE TELECOMMUNICATIONS AND INFORMATI ON SCIENCES LAB
|
| The objective of this effort was to develop the methodology of transferring communication signal processing algorithms from a single processor (SUN Workstation) to multiple DSP processors TMS32OC4Os. The CELP (Code Excited Linear Prediction) voice compression algorithm was chosen for real time implementation of 3 processors. The algorithm operates at an output rate of 4800 bits per second with an input sampling rate of 8000 samples per second. Using efficient parallel ... |
|
| Dialogue Theory for Virtual Environments |
NOV 96 |
9 pages |
| Authors:
Alan W. Biermann; DUKE UNIV DURHAM NC
|
| This project has developed a theory of dialogue that enables a machine to cooperate with a human in the solution of a problem. Specifically, the machine proceeds to prove the top level goal that represents the solution to the problem. If it finds subgoals in its proof that it cannot solve, it resorts to an interaction with the user to attempt to obtain the needed information to finish the proof. ... |
|
| A Survey of Rollback-Recovery Protocols in Message-Passing Systems |
03 OCT 96 |
|
| Authors:
E. N. Elnozahy; D. B. Johnson; Y. M. Wang; CARNEGIE-MELLON UNIV PITTSBURGH PA DEPT OF COMPUTER SCIENCE
|
| The problem of rollback-recovery in message-passing systems has undergone extensive study. In this survey, we review rollback-recovery techniques that do not require special language constructs, and classify them into two primary categories. Checkpoint-based rollback-recovery relies solely on checkpointed states for system state restoration. Depending on when checkpoints are taken, existing approaches can be divided into uncoordinated checkpointing, coordinated checkpointing and communication-induced checkpointing. Log-based rollback-recovery uses checkpointing and message logging. The ... |
|
| An Analysis of Approach Control/Pilot Voice Communications |
OCT 96 |
40 pages |
| Authors:
O. V. Prinzo; FEDERAL AVIATION ADMINISTRATION OKLAHOMA CITY OK CIVIL AEROMEDICAL INST
|
| This report consists of an analysis of air traffic control and pilot voice communications that occurred at 3 terminal air traffic control facilities (TRACONs). Each transmission was parsed into communication elements. Each communication element was assigned to a speech act category (e.g., address, instruction, request, advisory) and aviation topic (e.g., heading, altitude, speed, readback) and evaluated using the aviation topic-speech act taxonomy (ATSAT, Prinzo, et al., 1995). A total of ... |
|
| Telemedicine Evaluation - Human Factors |
OCT 1996 |
54 pages |
| Authors:
Deborah Birkmire; ARMY RESEARCH LAB ABERDEEN PROVING GROUND MD
|
| The problem of evaluating telemedicine applications has recently been recognized and addressed by both researchers and policy makers. In particular, the DoD Telemedicine Evaluation Working Group (TEWG) has adopted a conceptual framework to guide the development of methodologies to evaluate telemedicine projects in the Department of Defense. One of the five areas the TEWG proposed for evaluation in telemedicine projects is human factors. One aspect of human factors that was ... |
|
| Technology Review of the Use of Continuous Speech Recognition for Language Training |
SEP 96 |
157 pages |
| Authors:
C. M. Knerr; V. M. Holland; HUMAN RESOURCES RESEARCH ORGANIZATION ALEXANDRIA VA
|
| The Technology Review for Speech Recognition for Language Sustainment was an effort of the Special Operations Research, Development and Acquisition Center. The U.S. Army Research Institute and the Advanced Research Projects Agency in cooperation with the U.S. Army Special Operations Command Language Office. The review examined the state-of-the-art in continuous speech recognition (CSR) as it applies to foreign language training, sustainment, and enhancement for the Special Operations Forces (SOF). The ... |
|
| System Support for Mobility |
SEP 96 |
4 pages |
| Authors:
Andrew Black; Jon Inouye; OREGON GRADUATE INST BEAVERTON
|
| As we move closer to world-wide networking and the merger of computing and communications, truly mobile computing-computing while on the move-will become as unexceptional as truly mobile communication (using cellular telephones) is today. However, mobile computing poses new challenges for both system and application designers. Unlike telephony, where a new communications and terminal infrastructure was created to provide a well-understood service (peer-to-peer voice communication), and inter-operability was maintained at the ... |
|
| Implementing Voice Recognition and Natural Language Processing in the NPSNET Networked Virtual Environment |
SEP 96 |
193 pages |
| Authors:
Edward M. DeVilliers; NAVAL POSTGRADUATE SCHOOL MONTEREY CA
|
| Interfaces to military Virtual Reality (VR) systems, such as NPSNET IV.9, have been limited mainly to keyboard, mouse, and joystick devices. This presents two major problems; remembering how to access all the functionality of the system, and using the interface when the user is otherwise physically constrained. This can occur during the use of body-position tracking devices and Heads-Up-Displays (HUD). Voice recognition and Natural Language Processing (NLP) were used as ... |
|
| Potentials of Speech and Language Technology Systems for Military Use: An Application and Technology-Oriented Survey |
14 AUG 96 |
|
| Authors:
H. J. Steeneken; HUMAN FACTORS RESEARCH INST TNO SOESTERBERG (NETHERLANDS)
|
| The primary goal of this report is to describe the military applications of speech and language processing and the corresponding available technologies. The RSG.10 hopes that this report will be a useful tool for Operational staffs, Defence Research Staffs, and potential users within procurement departments of the NATO countries, by helping them to define and meet military requirements. The military applications are itemized in six categories: Command and Control, Communications, ... |
|
| Aviation Topics Speech Acts Taxonomy (ATSAT) pc User's Guide. Version 2. 0 |
AUG 96 |
23 pages |
| Authors:
O. V. Prinzo; Otto Maclin; NEVADA UNIV RENO
|
| ATSATpc is a Windows(TM)-based software program designed to facilitate posting of transcribed voice communications data into a pre-defined electronic spreadsheet. The steps involved in processing air traffic control communications using ATSATpc coincide with the steps that must be followed when manually encoding communications according to the procedures outlined in Development of a Coding Form for Approach Control/Pilot Voice Communications (Prinzo, Britton, & Hendrix, 1995). |
|
| Short Segment Data Base |
AUG 96 |
29 pages |
| Authors:
R. Lay; NAVAL COMMAND CONTROL AND OCEAN SURVEILLANCE CENTER RDT AND E DIV SAN DIEGO CA
|
| The objective of this project was to construct the Short Segment Data Base, a data base of short speech segments with various dwell times and various periods. This was accomplished by switching a receiver back and forth between an occupied and an unoccupied frequency. There must be no audio signal present when the receiver is tuned to the unoccupied frequency. This switching technique simulates a scanning receiver recording the audio ... |
|
| Automatic Language Identification with Sequences of Language-Independent Phoneme Clusters |
AUG 96 |
164 pages |
| Authors:
Kay M. Berkling; ARMY FOREIGN SCIENCE AND TECHNOLOGY CENTER CHARLOTTESVILLE VA
|
| Automatic Language Identification involves analyzing language specific features in speech to determine the language of an utterance without regard to topic, speaker or length of speech. Although much progress has been made in recent years, language identification systems have not been built on detailed underlying theory or linguistically meaningful design criteria. This thesis is motivated by the belief that features used to discriminate between languages should be linguistically sound; the ... |
|
| Modular Neural Networks for Speech Recognition |
AUG 96 |
|
| Authors:
Juergen Fritsch; CARNEGIE-MELLON UNIV PITTSBURGH PA DEPT OF COMPUTER SCIENCE
|
| In recent years, researchers have established the viability of so called hybrid NN/IIMM large vocabulary, speaker independent continuous speech recognition systems, where neural networks (NN) are used for the estimation of acoustic emission probabilities for hidden Markov models (IIMM) which provide statistical temporal modeling. Work in this direction is based on a proof, that neural networks can be trained to estimate posterior class probabilities. Advantages of the hybrid approach over ... |
|
| Knowledge Representation in the TRAINs-93 Conversation System |
AUG 96 |
55 pages |
| Authors:
David R. Traum; Lenhart K. Schubert; Massimo Poesio; Nathaniel G. Martin; Marc Light; ROCHESTER UNIV NY DEPT OF COMPUTER SCIENCE
|
| We describe the goals, architecture, and functioning of the TRAIN 5- 93 system, with emphasis on the representational issues involved in putting together a complex language processing and reasoning agent. The system is intended as an experimental prototype of an intelligent, conversationally proficient planning advisor in a dynamic domain of cargo trains and factories. For this team effort, our strategy at the outset was to let the designers of the ... |
|
| Flight Test Results of ITT VRS-1290 In NASA OV-10 |
10 JUL 1996 |
9 pages |
| Authors:
David T. Williamson; Timothy P. Barry; Kristen K. Liggett; AIR FORCE RESEARCH LAB WRIGHT-PATTERSON AFB OH
|
| This paper discusses the results of a recently completed flight test of an ITT VRS-1290 speaker dependent, continuous speech recognition system onboard a NASA Lewis Research Center OV-10A aircraft. A 54-word vocabulary was tested with thirteen pilots using an M-162 boom-mounted microphone on the ground and under 1g and 3g flight conditions. Digital audio tape (DAT) recordings were made of both the subjects spoken phrases and the ambient background noise. ... |
|
| Diphone-Based Speech Recognition Using Neural Networks |
JUN 96 |
357 pages |
| Authors:
Mark E. Cantrell; NAVAL POSTGRADUATE SCHOOL MONTEREY CA
|
| Speaker-independent automatic speech recognition (ASR) is a problem of long-standing interest to the Department of Defense. Unfortunately, existing systems are still too limited in capability for many military purposes. Most large-vocabulary systems use phonemes (individual speech sounds, including vowels and consonants) as recognition units. This research explores the use of diphones (pairings of phonemes) as recognition units. Diphones are acoustically easier to recognize because coarticulation effects between the diphones's phonemes ... |
|
| An Analysis of TRACON (Terminal Radar Approach Control) Controller - Pilot Voice Communications |
JUN 96 |
32 pages |
| Authors:
Kim M. Cardosi; Bryan Brett; Sherwin Han; JOHN A VOLPE NATIONAL TRANSPORTATION SYSTEMS CENTER CAMBRIDGE MA
|
| The purpose of this analysis was to examine pilot-controller communication practices in the TRACON (Terminal Radar Approach Control) environment. Forty-eight hours of communications recorded on the voice tapes from eight TRACONs were analyzed. There were 13,089 controller-to-pilot transmissions examined in this study. This included 9,409 clearances (e.g., assignment of attitude; instructions to change heading, speed, or radio frequencies; instructions for arrival, etc.) and 3,680 requests for information, salutations, etc. The ... |
|
| Focus of Attention in Video Conferencing |
JUN 96 |
29 pages |
| Authors:
Jie Yang; Leejay Wu; Alex Waibel; CARNEGIE-MELLON UNIV PITTSBURGH PA SCHOOL OF COMPUTER SCIENCE
|
| In this report we present an approach to low bitrate video teleconferencing by focusing attention on important information. We show that by selectively degrading the quality of less important regions, more important regions can be sent without loss of quality but with greatly reduced bandwidth requirements. Low bitrate transmission for real-time video delivery over a dynamic network is achieved by region blurring and cropping. A prototype system has been developed ... |
|
| Vocal Cord Function and Voice Quality Evaluation of Active Duty U.S. Army Drill Instructors |
JUN 1996 |
49 pages |
| Authors:
Eric A. Mann; WALTER REED ARMY MEDICAL CENTER WASHINGTON DC
|
| Although dysphonia is a recognized consequence of acute vocal abuse, associated changes in vocal cord anatomy and function are not well understood. To document these presumed effects of acute vocal abuse, we prospectively obtained videostroboscopic exams and serial voice recordings on U.S. Army drill sergeants during a vocally demanding training exercise. High quality digital audio recordings of sustained vowel production were obtained from 36 drill sergeants at baseline (following a ... |
|
Voice Communications
