| Military Voice Services over Wireless ATM Networks: ATM Adaptation Layer Study |
MAR 2001 |
|
| Authors:
Luis Villasenor-Gonzalez; Louise Lamont; DEFENCE RESEARCH ESTABLISHMENT OTTAWA (ONTARIO)
|
 | ATM technology has enjoyed great success, due in great part, for its ability to support a whole range of applications with Quality of Service (QoS) guarantees. Consequently, ATM has become of great interest for the support of services over military telecommunications networks. This report is provided as part of a study on the feasibility of military voice services over wireless ATM networks. In this study we are concerned with the ... |
|
| Military Voice Services over Wireless ATM Networks: Performance Analysis of FEC Schemes at ATM Transport Over Wireless Links |
MAR 2001 |
|
| Authors:
Sophia Tsakiridou; DEFENCE RESEARCH ESTABLISHMENT OTTAWA (ONTARIO)
|
| Wireless ATM was designed to extend the support of broadband, multimedia services provided in fixed ATM networks to the wireless/mobile environment in a seamless and efficient manner. It is a candidate wireless networking technology for future tactical military networks which have adopted ATM in the core network. The bandwidth-limited, error-prone nature of wireless links poses significant challenges in the design of wireless ATM. This report is part of a study ... |
|
| Representations and Protocols for Universal Access to the World-Wide- Web |
31 JAN 2001 |
25 pages |
| Authors:
Gary J. Sikora; PROGENY SYSTEMS CORP MANASSAS VA
|
 | Information integration and aggregation from a variety of sources, with distribution to users at all echelons has been pursued for some time. Developments have been slow for several reasons including funding priorities, previous false starts, and the gap between commercial technologies and the Defense specific needs. Developments under DARPA Information Technology Office, Intelligent Software, Communicator research program has lead the commercial industry in areas of speech recognition and interaction providing ... |
|
| Real Time Continuous Speech Recognition for C3I Applications |
JAN 2001 |
23 pages |
| Authors:
Marie Meteer; Christopher Barclay; Sean Colbath; BBN TECHNOLOGIES CAMBRIDGE MA
|
| This report describes the use of BBN's speech technology to provide support of ongoing Information Directorate programs in several areas, including research in intelligent interfaces and virtual reality. There were two major task areas: 1) to provide Hark Speech Recognizer product licenses to AFRL and their supporting contractors, and support them in the development of applications, and 2) develop tools and techniques to enhance the capability of the Hark Recognizer, ... |
|
| From Word-Spotting to OOV Modeling |
2001 |
5 pages |
| Authors:
Paul Fitzpatrick; MASSACHUSETTS INST OF TECH CAMBRIDGE ARTIFICIAL INTELLIGENCE LAB
|
| This paper explores one dimension along which word spotting and speech recognition differ: the nature of the background model. In word spotting, a relatively small number of keywords float on a sea of unknown words. In speech recognition, an occasional unknown word punctuates utterances that are otherwise completely within the vocabulary. Despite this difference in viewpoint, in some circumstances implementations of the two may become very similar. When transcribed data ... |
|
| Characterizing and Processing Robot-Directed Speech |
2001 |
|
| Authors:
Paulina Varchavskaia; Paul Fitzpatrick; Cynthia Breazeal; MASSACHUSETTS INST OF TECH CAMBRIDGE
|
| Humanoid robots are more suited to being generalists rather than specialists. Hence when designing a speech interface, we need to retain that generality. But speech recognition is most successful in strongly circumscribed domains. We examine whether some useful properties of infant directed speech can be evoked by a robot, and how the robot's vocabulary can be adapted. |
|
| Evaluation Results for the Talk'n'Travel System |
2001 |
4 pages |
| Authors:
David Stallard; BBN TECHNOLOGIES CAMBRIDGE MA
|
| We describe and present evaluation results for Talk n Travel, a spoken dialogue language system for making air travel plans over the telephone. Talk n Travel is a fully conversational, mixed initiative system that allows the user to specify the constraints on his travel plan in arbitrary order, ask questions, etc., in general spoken English. The system was independently evaluated as part of the DARPA Communicator program and achieved a ... |
|
| Automatic Title Generation for Spoken Broadcast News |
2001 |
4 pages |
| Authors:
Rong Jin; Alexander G. Hauptmann; CARNEGIE-MELLON UNIV PITTSBURGH PA LANGUAGE TECHNOLOGIES INST
|
| ABSTRACT In this paper, we implemented a set of title generation methods using training set of 21190 news stories and evaluated them on an independent test corpus of 1006 broadcast news documents, comparing the results over manual transcription to the results over automatically recognized speech. We use both F1 and the average number of correct title words in the correct order as metric. Overall, the results show that title generation ... |
|
| Activity Detection for Information Access to Oral Communication |
2001 |
7 pages |
| Authors:
Klaus Ries; Alex Waibel; CARNEGIE-MELLON UNIV PITTSBURGH PA
|
| Oral communication is ubiquitous and carries important information yet it is also time consuming to document. Given the development of storage media and networks one could just record and store a conversation for documentation. The question is, however, how an interesting information piece would be found in a large database. Traditional information retrieval techniques use a histogram of keywords as the document representation but oral communication may offer additional indices ... |
|
| Towards Automatic Sign Translation |
2001 |
7 pages |
| Authors:
Jie Yang; Jiang Gao; Ying Zhang; Alex Waibel; CARNEGIE-MELLON UNIV PITTSBURGH PA
|
| ABSTRACT Signs are everywhere in our lives. They make our lives easier when we are familiar with them. But sometimes they also pose problems. For example, a tourist might not be able to understand signs in a foreign country. In this paper, we present our efforts towards automatic sign translation. We discuss methods for automatic sign detection. We describe sign translation using example based machine translation technology. We use a ... |
|
| Dialogue Interaction with the DARPA Communicator Infrastructure: The Development of Useful Software |
2001 |
4 pages |
| Authors:
Samuel Bayer; Christine Doran; Bryan George; MITRE CORP BEDFORD MA
|
| To support engaging human users in robust, mixed-initiative speech dialogue interactions which reach beyond current capabilities in dialogue systems, the DARPA Communicator program [1] is funding the development of a distributed message-passing infrastructure for dialogue systems which all Communicator participants are using. In this presentation, we describe the features of and requirements for a genuinely useful software infrastructure for this purpose. |
|
| Automated Tutoring Dialogues for Training in Shipboard Damage Control |
2001 |
5 pages |
| Authors:
John Fry; Matt Ginzton; Stanley Peters; Brady Clark; Heather Pon-Barry; STANFORD UNIV CA CENTER FOR THE STUDY OF LANGUAGE AND INFORMATION
|
| This paper describes an application of state-of-the-art spoken language technology (OAA/Gemini/Nuance) to a new problem domain: engaging students in automated tutorial dialogs to evaluate and improve their performance in a training simulator. Shipboard damage control refers to the task of containing the effects of fire, explosions, hull breaches, flooding, and other critical events that can occur aboard Naval vessels. The high-stakes, high-stress nature of this task, together with limited opportunities ... |
|
| The Meeting Project at ICSI |
2001 |
8 pages |
| Authors:
Nelson Morgan; Don Baron; Jane Edwards; Dan Ellis; David Gelbart; Adam Janin; Thilo Pfau; Elizabeth Shriberg; Andreas Stolcke; INTERNATIONAL COMPUTER SCIENCE INST BERKELEY CA
|
| In collaboration with colleagues at UW, OGI, IBM, and SRI, we are developing technology to process spoken language from informal meetings. The work includes a substantial data collection and transcription effort, and has required a nontrivial degree of infrastructure development. We are undertaking this because the new task area provides a significant challenge to current HLT capabilities, while offering the promise of a wide range of potential applications. In this ... |
|
| Natural Language Generation in Dialog Systems |
2001 |
5 pages |
| Authors:
Owen Rambow; Srinivas Bangalore; Marilyn Walker; AT AND T LABS - RESEARCH FLORHAM PARK NJ
|
| Recent advances in Automatic Speech Recognition technology have put the goal of naturally sounding dialog systems within reach. However, the improved speech recognition has brought to light a new problem: as dialog systems understand more of what the user tells them, they need to be more sophisticated at responding to the user. The issue of system response to users has been extensively studied by the natural language generation community, though ... |
|
| A Three-Tiered Evaluation Approach for Interactive Spoken Dialogue Systems |
2001 |
6 pages |
| Authors:
Kathleen Stibler; James Denny; LOCKHEED MARTIN ADVANCED TECHNOLOGY LABS CAMDEN NJ
|
| We describe a three-tiered approach for evaluation of spoken dialogue systems. The three tiers measure user satisfaction, system support of mission success and component performance. We describe our use of this approach in numerous fielded user studies conducted with the U.S. military. |
|
| DATE: A Dialogue Act Tagging Scheme for Evaluation of Spoken Dialogue Systems |
2001 |
9 pages |
| Authors:
Marilyn Walker; Rebecca Passonneau; AT AND T LABS - RESEARCH FLORHAM PARK NJ
|
| This paper describes a dialogue act tagging scheme developed for the purpose of providing finer-grained quantitative dialogue metrics for comparing and evaluating DARPA COMMUNICATOR spoken dialogue systems. We show that these dialogue act metrics can be used to quantify the amount of effort spent in a dialogue maintaining the channel of communication or, establishing the frame for communication, as opposed to actually carrying out the travel planning task that the ... |
|
| Heterogeneous Architecture Support for Wireless Network Dynamics and Mobility |
29 DEC 2000 |
32 pages |
| Authors:
Joseph P. Macker; Vincent D. Park; NAVAL RESEARCH LAB WASHINGTON DC
|
| In this paper, we examine network architecture issues and protocols for applicability to mobile and dynamic wireless communication networks. Our focus is on networking technology to provide heterogeneous support and interoperability with existing and planned internetworking infrastructures and applications. First, we discuss engineering issues and technology components across a broad range of mobile networking system elements. Second, we focus in detail on a number of critical technology areas relating to ... |
|
| Feasibility Study of Speech Recognition Technologies for Operating within a Medical First Responder's Environment |
DEC 2000 |
73 pages |
| Authors:
Leroy W. Harris Jr.; NAVAL POSTGRADUATE SCHOOL MONTEREY CA
|
| This thesis was designed to address some of the issues facing the medical First Responder who is continually tasked with providing care within multi-national environments. Currently, there are no established billets or quota requirements at the Defense Language Institute Foreign Language Center for Navy Corpsmen for the purposes of foreign language education prior to an overseas assignment or deployment. The primary Speech Recognition (SR) device used in this study was ... |
|
| The Core Protocol Set for the Global Grid |
DEC 2000 |
8 pages |
| Authors:
Joseph Rajkowski; Kenneth Brayer; MITRE CORP BEDFORD MA
|
| The protocol set for the Global Grid is addressed. A rationale for specifying a core protocol set, the methodology for determining the protocols included, and a discussion of the extensibility of the core protocol set to address support for user-specific applications are provided. |
|
| A Perception and Nonlinear PDE Based Approach to Processing Spoken Words |
14 NOV 2000 |
6 pages |
| Authors:
Jack Xin; Yingyong Qi; ARIZONA UNIV TUCSON
|
| During the period of June 1999 to June 2000, supported by ARO grant DAAD 19-99-1-0248, we developed a novel nonlinear transformation to process spoken words in noisy environment, based on human hearing perception and properties of focusing partial differential equation (PDE). The transformation was made on the short-term Fourier spectra of speech signals. It was designed to reduce noise through time adaptation, and enhance spectral peaks (formants) by evolving a-focusing ... |
|
| A Dialogue-Based Approach to Mixed-Initiative Plan Management |
OCT 2000 |
77 pages |
| Authors:
James F. Allen; George M. Ferguson; Lenhart K. Schubert; ROCHESTER UNIV NY DEPT OF COMPUTER SCIENCE
|
| This research investigates ways to augment human plan reasoning capabilities in command and control tasks, such as logistics planning, crisis management and situation assessment. The goal was to avoid making the simplifying assumptions made in traditional research in planning that prevented effective human-computer collaborative planning. Specifically, no assumptions were made relative to goals being well specified in the beginning, or that the evaluation criteria can be precisely defined in a ... |
|
| Communications Problems in Marine Casualties |
OCT 2000 |
88 pages |
| Authors:
Marvin C. McCallum; Alice M. Forsythe; Mireille Raby; Anita M. Rothblum; Antoinette Slavich; COAST GUARD RESEARCH AND DEVELOPMENT CENTER GROTON CT
|
| The present study developed casualty investigation procedures that focused on communications problems. These procedures were applied by U.S. Coast Guard (USCG) Investigating Officers in their investigation of 589 marine casualties over a seven-month period. Analysis of the resulting casualty reports determined that communications is a prevalent causal factor in marine casualties, being a factor in 18 percent of critical vessel casualties, 28 percent of critical personnel injuries, and contributing to ... |
|
| IP Convergence in Global Telecommunications. Voice Over Internet Protocol (VolP) |
SEP 2000 |
|
| Authors:
Ian Zahorujko; Alfred Reynolds; Bill Blair; DEFENCE SCIENCE AND TECHNOLOGY ORGANISATION SALISBURY (AUSTRALIA) ELECTRONICS AND SURVEILLANCE RESEARCH
|
| A key application on any converged global network will be voice telephony. On an Internet Protocol (IP) network, this is given the generic title Voice over IP (VoIP). This paper examines the motivation behind VoIP and the standards being deployed in support of the application. It discusses the factors that determine the voice quality to users, and measures that can be made. The impact of VoIP on Speakeasy is given ... |
|
| Information Assurance Technical Framework (IATF) (CD-ROM) |
SEP 2000 |
|
| Authors:
NATIONAL SECURITY AGENCY/CENTRAL SECURITY SERVICE FORT GEORGE G MEADE MD
|
| ELECTRONIC FILE CHARACTERISTICS: 143 files; Adobe Acrobat PDf, MS Word97. PHYSICAL DESCRIPTION: 1 computer laser optical disc (CD-ROM); 4 3/4 in.; 41.7 MB. SYSTEMS DETAIL NOTE: IBM-clone PC-compatible; requires Adobe Acrobat Reader (software on disc). ABSTRACT: The Information Assurance Technical Framework (IATF) document was developed to help a broad audience of users both define and understand their technical needs as well as seiect approaches to meet those needs. The intended ... |
|
| Communication and Localization with Hearing Protectors |
SEP 2000 |
14 pages |
| Authors:
Richard L. McKinley; AIR FORCE RESEARCH LAB WRIGHT-PATTERSON AFB OH
|
| Hearing protectors are frequently used to preserve hearing when personnel are working in areas of high pulse and/or continuous noise. Speech communication and auditory localization are two important functions of the auditory system, which potentially are impeded when circumaural and/or insert hearing protectors are used. This paper describes the measured effects of hearing protectors on speech communication and auditory localization. The effects on auditory localization include interactions with the visual ... |
|
| Multi-Lingual Interoperability in Speech Technology (l'Interoperabilite multilinguistique dans la technologie de la parole) |
AUG 2000 |
|
| Authors:
NATO RESEARCH AND TECHNOLOGY ORGANIZATION NEUILLY-SUR-SEINE (FRANCE)
|
| Communications, command and control, intelligence, and training systems are more and more making use of speech technology components: i.e. speech coders, voice controlled C2 systems, speaker and language recognition, and automated training suites. Interoperability of these systems is not a simple standardization problem as the speech of each individual user is an uncontrolled variable such as non-native speakers using, additional to their own language, an official NATO language. For international ... |
|
| Patient Telephone Appointment System for High Volume Primary Care Sites |
AUG 2000 |
121 pages |
| Authors:
Francine M. Worthington; NAVAL MEDICAL CENTER SAN DIEGO CA
|
| The purpose of this research is to design a patient telephone appointment system for use in the Naval Medical Center San Diego's high volume Primary Care sites, which will reduce variation and ensure efficient, timely, convenient, and appropriate access to care. This study follows a Continuous Improvement philosophy of customer satisfaction, quality process improvement, and benchmarking, also known as "idealized process redesign." The study defines requirements for technology, staffing mix, ... |
|
| Speech Recognition by Goats, Wolves, Sheep and Non-Natives |
AUG 2000 |
8 pages |
| Authors:
Dirk V. Campernolle; LERNOUT AND HAUSPIE SPEECH PRODUCTS NV WEMMEL (BELGIUM)
|
| This paper gives an overview of current understanding of acoustic-phonetic issues arising when trying to recognize speech from non-native speakers. Regional accents can be modeled by systematic shifts in pronunciation. These can often better be represented by multiple models, than by pronunciation variants in the dictionary. The problem of non-native speech is much more difficult because it is influenced both by native and spoken language, making a multi-model approach inappropriate. ... |
|
| Acoustic-Phonetic Modeling of Non-Native Speech for Language Identification |
AUG 2000 |
6 pages |
| Authors:
R. Wanneroy; E. Bilinski; C. Barras; M. Adda-Decker; E. Geoffrois; SPOKEN LANGUAGE PROCESSING GROUP LIMSI-CNRS CEDEX (FRANCE)
|
| The aim of this paper is to investigate to what extent non native speech may deteriorate language identification (LID) performances and to improve them using acoustic adaptation. Our reference LID system is based on a phonotactic approach. The system makes use of language-independent acoustic models and language-specific phone-based bigram language models. Experiments are conducted on the SQALE test database, which contains recordings from English, Erench and German native speakers, and ... |
|
| How Foreign are 'Foreign' Speech Sounds? Implications for Speech Recognition and Speech Synthesis |
AUG 2000 |
6 pages |
| Authors:
TELIA RESEARCH AB FARSTA (SWEDEN)
|
| This paper reports results from a production study which shows in what ways the traditional Swedish phone set is expanded with phones similar to or approximating phones from other languages than Swedish in everyday speech. The inclusion of such sounds - here called xenophones - has implications for both automatic speech recognition and speech synthesis systems, especially in polylingual environments, which are discussed in the paper. |
|
| Clustering of Context Dependent Speech Units for Multilingual Speech Recognition |
AUG 2000 |
7 pages |
| Authors:
Bojan Imperl; MARIBOR UNIV (SLOVENIA)
|
| The paper addresses the problem of designing a language independent phonetic inventory for the speech recognizers with multilingual vocabulary. A new clustering algorithm for the definition of multilingual set of triphones is proposed. The clustering algorithm bases on a definition of a distance measure for triphones defined as a weighted sum of explicit estimates of the context similarity on a monophone level. The monophone similarity estimation method based on the ... |
|
| Speech Recognition of Non-Native Speech Using Native and Non-Native Acoustic Models |
AUG 2000 |
|
| Authors:
David A. van Leeuwen; Rosemary Orr; HUMAN FACTORS RESEARCH INST TNO SOESTERBERG (NETHERLANDS)
|
| A speech recognition system is subjected to the speech of non-native speakers, using both native and non-native acoustic phone models. The problems involved with the mapping of phone set from the non- native to native language are investigated, and a detailed analysis of phone confusions is made. For Dutch speakers, British English acoustic models give the best word recognition results. |
|
| An Overview of the EURESCOM MIVA Project |
AUG 2000 |
8 pages |
| Authors:
Denis Johnston; BRITISH TELECOM LONDON (UNITED KINGDOM)
|
| The goal of the MIVA project was to answer a number of fundamental questions concerned with the exploitation of speech technology enabled systems. The experimental service chosen was designed to help foreign people travelling in the country to find emergency and embassy numbers, country and area codes, useful numbers (directory service, country direct, etc.) and how to use Telecom and credit cards for placing calls. Services were implemented in each ... |
|
| A Platform for Multilingual Research in Spoken Dialogue Systems |
AUG 2000 |
7 pages |
| Authors:
Ronald A. Cole; Ben Serridge; John-Paul Hasom; Andrew Cronk; Ed Kaiser; COLORADO UNIV AT BOULDER CENTER FOR SPOKEN LANGUAGE UNDERSTANDING
|
| Multilingual speech technology research would be greatly facilitated by an integrated and comprehensive set of software tools that enable research and development of core language technologies and interactive language systems in any language. Such a multilingual platform has been one of our goals in developing the CSLU Toolkit. The Toolkit is composed of components that are essentially language-independent, and support research and development of recognition, understanding, text-to-speech synthesis, facial animation, ... |
|
| Auditory Features Underlying Cross-Language Human Capabilities in Stop Consonant Discrimination |
AUG 2000 |
7 pages |
| Authors:
Eduardo Sa Marta; Luis Vieira de Sa; COIMBRA UNIV (PORTUGAL) CENTRO DE ELECTROTECNIA
|
| For some phonemic distinctions human listeners exhibit a marked cross-language capability, in that they are capable of highly correct classification in relation to sounds (like CVs or VCVs) uttered by speakers of another language. This is particularly true regarding distinctions that are perceived in a more categorical fashion, like that of 3-way PLACE discrimination in stop consonants. It is plausible that the reason for this is a mostly common (across ... |
|
| Uses of the Diagnostic Rhyme Test (English Version) for Predicting the Effects of Communicators' Linguistic Backgrounds on Voice Communications in English: An Exploratory Study |
AUG 2000 |
7 pages |
| Authors:
William D. Voiers; DYNASTAT INC AUSTIN TX
|
| Recordings of Diagnostic Rhyme Test (DRT) materials by native talkers of English (American), German and French were presented under undegraded and degraded conditions to English speaking listening crews of three national origins: American, German and French. The results were analyzed for the effects of the talker's native language, the listener's native language and all permutations of the two on scores yielded by the DRT. With undegraded speech, the total number ... |
|
| Speech Intelligibility of Native and Non-Native Speech |
AUG 2000 |
|
| Authors:
Sander J. van Wijngaarden; HUMAN FACTORS RESEARCH INST TNO SOESTERBERG (NETHERLANDS)
|
| The intelligibility of speech is known to be lower if the talker is non-native instead of native for the given language. This study is aimed at quantifying the overall degradation due to acoustic-phonetic limitations of non- native talkers of Dutch, specifically of Dutch-speaking Americans who have lived in the Netherlands 1-3 years. Experiments were performed using phoneme intelligibility and sentence intelligibility tests, using additive noise as a means of degrading ... |
|
| Towards Multilingual Interoperability in Automatic Speech Recognition |
AUG 2000 |
9 pages |
| Authors:
Martine Adda-Decker; SPOKEN LANGUAGE PROCESSING GROUP LIMSI-CNRS CEDEX (FRANCE)
|
| In this communication, we address multilingual interoperability aspects in speech recognition. After giving a tentative definition of multilingual interoperability, we discuss speech recognition components and their language-specific aspects. We give a sample overview of past multilingual speech recognition research and development across different speaking styles (read, prepared and conversational). The problem of adaptation to new languages is addressed. Language-independent and cross- language techniques for acoustic modeling provide a means to ... |
|
| Multilingual Vocabularies in Automatic Speech Recognition |
AUG 2000 |
5 pages |
| Authors:
Giorgio Micca; Enrico Palme; Alessandra Frasca; CENTRO STUDI E LAB TELECOMUNICAZIONI S P A TURIN (ITALY)
|
| The paper describes a method for dealing with multilingual vocabularies in speech recognition tasks. We present an approach that combines acoustic descriptive precision and capability of generalization to multiple languages. The approach is based on the concept of classes of transitions between phones. The classes are defined by means of objective measures on acoustic similarities among sounds of different languages. This procedure stems from the definition of a general language-independent ... |
|
| Speech Recognition in 7 Languages |
AUG 2000 |
7 pages |
| Authors:
Ulla Uebler; BAVARIAN RESEARCH CENTER FOR KNOWLEDGE BASED SYSTEMS ERLANGEN (GERMANY) RESEARCH GROUP FOR KNOWLEDGE PROCESSING
|
| In this study we present approaches to multilingual speech recognition. We first define different approaches, namely portation, cross-lingual and simultaneous multilingual speech recognition and present results in these approaches. In recent years we have ported our recognizer to other languages than German. Some experiments presented here show the performance of cross-lingual speech recognition of an untrained language with a recognizer trained with other languages. Our results show that some languages ... |
|
| A Military Operational Automatic Interpreting System |
AUG 2000 |
5 pages |
| Authors:
Melvyn Hunt; Paul Bamberg; Jay Tucker; Steven Anderson; DRAGON SYSTEMS INC NEWTON MA
|
| This paper describes a real-time interpreting system in which the operator speaks one of around 4000 phrases in one language, which is automatically recognized and the corresponding spoken phrase in the target language is played through a loudspeaker. This system has been used operationally by NATO forces. The basic system is first described, followed by an account of the wide range of uses to which this relatively simple one-way interpreting ... |
|
| Comparing Three Methods to Create Multilingual Phone Models for Vocabulary Independent Speech Recognition Tasks |
AUG 2000 |
7 pages |
| Authors:
Joachim Koehler; GERMAN NATIONAL RESEARCH CENTER FOR INFO TECHNOLOGY (SANKT AUGUSTIN) INST FOR MEDIA COMMUNICATIONS
|
| This paper presents three different methods to develop multilingual phone models for flexible speech recognition tasks. The main goal of our investigations is to find multilingual speech units which work equally well in many languages. With this universal set it is possible to build speech recognition systems for a variety of languages. One advantage of this approach is to share acoustic-phonetic parameters in a HMM based speech recognition system. The ... |
|
| Language Adaptive LVCSR Through Polyphone Decision Tree Specialization |
AUG 2000 |
7 pages |
| Authors:
T. Schultz; A. Waibel; KARLSRUHE UNIV (GERMANY F R)
|
| With the distribution of speech technology products all over the world, the fast and efficient portability to new target languages be comes a practical concern. In this paper we explore the relative effectiveness of porting multilingual recognition systems to new target languages with very limited adaptation data. For this purpose we introduce a polyphone decision tree specialization method. Several recognition results are presented based on mono- and multilingual recognizers developed ... |
|
| Automatic Language Identification |
AUG 2000 |
|
| Authors:
Marc A. Zissman; Kay M. Berkling; MASSACHUSETTS INST OF TECH LEXINGTON LINCOLN LAB
|
| Automatic language identification is the process by which the language of a digitized speech utterance is recognized by a computer. In this paper, we will describe the set of available cues for language identification and discuss the different approaches to building working systems. This overview includes a range of historic approaches, con- temporary systems that have been evaluated on standard databases, as well as promising future approaches. Com- parative results ... |
|
| Multilingual Text-Independent Speaker Identification |
AUG 2000 |
5 pages |
| Authors:
Geoffrey Durou; FACULTE POLYTECHNIQUE DE MONS (BELGIUM)
|
| In this paper, we investigate two facets of speaker recognition : cross-language speaker identification and same language non-native text-independent speaker identification. In this context, experiments have been conducted, using standard multi-gaussian modeling, on the brand new multi-language TNO corpus. Our results indicate how speaker identification performance might be affected when speakers do not use the same language during the training and testing, or when the population is composed of non-native ... |
|
| Vowel System Modeling: A Complement to Phonetic Modeling in Language Identification |
AUG 2000 |
7 pages |
| Authors:
Francois Pellegrino; Jerome Farinas; Regine Andre-Obrechi; TOULOUSE-3 UNIV (FRANCE)
|
| Most systems of Automatic Language Identification are based on phonotactic approaches. However, it is more and more evident that taking other features (phonetic, phonological, prosodic, etc.) into account will improve performances. This paper presents an unsupervised phonetic approach that aims to consider phonological cues related to the structure of vocalic and consonantal systems. In this approach, unsupervised vowel/non vowel detection is used to model separately vocalic and consonantal systems. These ... |
|
| SCoPE, Syllable Core and Periphery Evaluation: Automatic Syllabification and Application to Foreign Accent Identification |
AUG 2000 |
|
| Authors:
Kay Berkling; Julie Vonwiller; Chris Cleirigh; MASSACHUSETTS INST OF TECH LEXINGTON LINCOLN LAB
|
| In this paper we apply a study of the structure of the English language towards an automatic syllabification algorithm. Elements of syllable structure are defined according to both their position in the syllable and to the position of the syllable within word structure. Elements of syllable structure that only occur at morpheme boundaries or that extend for the duration of morphemes are identified as peripheral elements; those that can occur ... |
|
| The Effect of Wearing Night Vision Goggles on Voice Level During a Visual Target Acquisition Task |
MAR 2000 |
37 pages |
| Authors:
Robert Karsh; Tomasz R. Letowski; V. CuQlock-Knopp; John O. Merritt; ARMY RESEARCH LAB ABERDEEN PROVING GROUND MD
|
| There have been numerous undocumented reports that military users of night vision goggles (NVGs) tend to talk louder than usual when they wear the viewing device. Increased voice level in response to using the night vision aid could seriously compromise the security of military missions that depend upon stealth for their success. The goal of this study was to investigate the effects of characteristics of the ... |
|
| The Impact of Speech Under "Stress" on Military Speech Technology. (l'Impact de la parole en condition de "stress" sur less technologies vocales militaries) |
MAR 2000 |
|
| Authors:
Claude Vloeberghs; Patrick Verlinde; Carl Swail; Herman Steeneken; Allan South; NATO RESEARCH AND TECHNOLOGY ORGANIZATION NEUILLY-SUR-SEINE (FRANCE)
|
| Military operations are often conducted under conditions of stress induced by high workload, sleep deprivation, fear and emotion, confusion due to conflicting information, psychological tension, pain, and other typical conditions encountered in the modern battlefield context. These conditions are known to affect the physical and cognitive abilities of human speech characteristics, and this study was intended to determine the actual effects of stress on ... |
|
| Databases for Assessment of Military Speech Technology Equipment. (les Bases de donnees pout l'evaluation des equipements de technologie vocale militaire) |
MAR 2000 |
|
| Authors:
NATO RESEARCH AND TECHNOLOGY ORGANIZATION NEUILLY-SUR-SEINE (FRANCE)
|
| A NATO research group carried out collaborative studies on military applications of speech processing. A major requirement in this area of work is for large quantities of speech recordings made in military environments, which are often expensive and difficult to obtain. Research and development in this area will benefit from sharing such data as widely as possible among the NATO research community. The cost of ... |
|
Voice Communications
