Text, Speech and Dialogue: Third International Workshop, TSD 2000 Brno, Czech Republic, September 13-16, 2000 Proceedings (Lecture Notes in Computer Science / Lecture Notes in Artificial Intelligence)

The workshop series on Text, Speech and Dialogue originated in 1998 with the ?rst TSD1998 held in Brno, Czech Republic. This year’s TSD2000, already the third in the series, returns to Brno and to its organizers from the Faculty of Informatics at the Masaryk University. As shown by the ever growing interest in TSD series, this annual workshop developed into the prime meeting of speech and language researchers from both sides of the former Iron Curtain, which provides a unique opportunity to get acquainted with the current activities in all aspects of language communication and to witness the amazing vitality of researchers from the former East Block countries. Thanks need to be extended to all who continue to make the TSD workshop series such a success: ?rst, to the authors themselves, without whom TSD2000 would not exist; next, to all organizations that support TSD2000, among them the International Speech Communication Association, the Faculty of Informatics at the Masaryk University in Brno and the Faculty of Applied Sciences, West Bohemia University in Plzen; ? and last but not least,to the organizers and members of the Program Committee who spentmuch effort to make TSD2000 success and who reviewed 131 contributions submitted from all corners of the world and accepted 75 out of them for presentation at the workshop. This book is evidence of the success of all involved. The Linguistic Basis of a Rule-Based Tagger of Czech....Pages 3-8 Harnessing the Lexicographer in the Quest for Accurate Word Sense Disambiguation....Pages 9-14 An Integrated Statistical Model for Tagging and Chunking Unrestricted Text....Pages 15-20 Extending Bidirectional Chart Parsing with a Stochastic Model....Pages 21-26 Ensemble of Classifiers for Noise Detection in PoS Tagged Corpora....Pages 27-32 Towards a Dynamic Syntax for Language Modelling....Pages 33-38 A Word Analysis System for German Hyphenation, Full Text Search, and Spell Checking, with Regard to the Latest Reform of German Orthography....Pages 39-44 Automatic Functor Assignment in the Prague Dependency Treebank....Pages 45-50 Categories, Constructions, and Dependency Relations....Pages 51-56 Local Grammars and Parsing Coordination of Nouns in Serbo-Croatian....Pages 57-62 Realization of Syntactic Parser for Inflectional Language Using XML and Regular Expressions....Pages 63-68 A Rigoristic and Automated Analysis of Texts Applied to a Scientific Abstract by Mark Sergot and Others....Pages 69-74 Evaluation of Tectogrammatical Annotation of PDT....Pages 75-80 Probabilistic Head-Driven Chart Parsing of Czech Sentences....Pages 81-86 Aggregation and Contextual Reference in Automatically Generated Instructions....Pages 87-92 Information Retrieval by Means of Word Sense Disambiguation....Pages 93-98 Statistical Parameterisation of Text Corpora....Pages 99-102 An Efficient Algorithm for Japanese Sentence Compaction Based on Phrase Importance and Inter-Phrase Dependency....Pages 103-108 Word Senses and Semantic Representations Can We Have Both?....Pages 109-114 Automatic Tagging of Compound Verb Groups in Czech Corpora....Pages 115-120 Sensitive Words and Their Application to Chinese Processing....Pages 121-126 Testing a Word Analysis System for Reliable and Sense-Conveying Hyphenation and Other Applications....Pages 127-132 The Challenge of Parallel Text Processing....Pages 133-138 Selected Types of Pg-Ambiguity: Processing Based on Analysis by Reduction....Pages 139-144 Cohesive Generation of Syntactically Simplified Newspaper Text....Pages 145-150 TEA: A Text Analysis Tool for the Intelligent Text Document Filtering....Pages 151-156 Competing Patterns for Language Engineering....Pages 157-162 Recognition and Labelling of Prosodic Events in Slovenian Speech....Pages 165-170 Rules for Automatic Grapheme-to-Allophone Transcription in Slovene....Pages 171-176 An Adaptive and Fast Speech Detection Algorithm....Pages 177-182 Optimal Pitch Path Tracking for More Reliable Pitch Detection....Pages 183-188 FlexVoice: A Parametric Approach to High-Quality Speech Synthesis....Pages 189-194 The Continuous and Discontinuous Styles in Czech TTS....Pages 195-200 Automatic Speech Segmentation with the Application of the Czech TTS System....Pages 201-206 Speaker Identification Using Autoregressive Hidden Markov Models and Adaptive Vector Quantisation....Pages 207-210 Morpheme Based Language Models for Speech Recognition of Czech....Pages 211-216 A Large Czech Vocabulary Recognition System for Real-Time Applications....Pages 217-222 Building a New Czech Text-to-Speech System Using Triphone-Based Speech Units....Pages 223-228 Acoustic and Perceptual Properties of Syllables in Continuous Speech as a Function of Speaking Rate....Pages 229-236 NL-Processor and Linguistic Knowledge Base in a Speech Recognition System....Pages 237-242 Russian Phonetic Variability and Connected Speech Transcription....Pages 243-247 Database Processing for Spanish Text-to-Speech Synthesis....Pages 248-252 Topic-Sensitive Language Modelling....Pages 253-258 Design of Speech Recognition Engine....Pages 259-264 Combining Multi-band and Frequency-Filtering Techniques for Speech Recognition in Noisy Environments....Pages 265-270 Allophone- and Suballophone-Based Speech Synthesis System for Russian....Pages 271-276 Diphone-Based Unit Selection for Catalan Text-to-Speech Synthesis....Pages 277-282 Analysis of Information in Speech and Its Application in Speech Recognition....Pages 283-288 What Textual Relationships Demand Phonetic Focus?....Pages 289-294 Speaker Identification Using Kalman Cepstral Coefficients....Pages 295-300 Belarussian Speech Recognition Using Genetic Algorithms....Pages 301-306 A Discriminative Segmental Speech Model and Its Application to Hungarian Number Recognition....Pages 307-313 Comparison of Frequency Bands in Closed Set Speaker Identification Performance....Pages 314-318 Recording and Annotation of the Czech Speech Corpus....Pages 319-323 A Text Based Talking Face....Pages 327-332 Dialogue Control in the Alparon System....Pages 333-338 ISIS: Interaction through Speech with Information Systems....Pages 339-344 Centering-Based Anaphora Resolution in Danish Dialogues....Pages 345-350 Some Improvements on the IRST Mixed Initiative Dialogue Technology....Pages 351-356 Dictionary-Based Method for Coherence Maintenance in Man-Machine Dialogue with Indirect Antecedents and Ellipses....Pages 357-362 Reconstructing Conversational Games in an Obligation-Driven Dialogue Model....Pages 363-368 Prosody Prediction from Tree-Like Structure Similarities....Pages 369-374 A Speaker Authentication Module in TelCorreo....Pages 375-380 TelCorreo: A Bilingual E-mail Client over the Telephone....Pages 381-386 A Syntactical Model of Prosody as an Aid to Spoken Dialogue Systems in Italian Language....Pages 387-392 What Do You Mean by “What Do You Mean”?....Pages 393-398 Simplified Processing of Elliptic and Anaphoric Utterances in a Train Timetable Information Retrieval Dialogue System....Pages 399-404 Pragmatic and Grammatical Aspects of the Development of Dialogue Strategies....Pages 405-409 An Annotation Scheme for Dialogues Applied to Anaphora Resolution Algorithms....Pages 410-414 Cooperative Information Retrieval Dialogues through Clustering....Pages 415-420 Acoustic Cues for Classifying Communicative Intentions in Dialogue Systems....Pages 421-426 Active and Passive Strategies in Dialogue Program Generation....Pages 427-432 Architecture of Multi-modal Dialogue System....Pages 433-438 The Utility of Semantic-Pragmatic Information and Dialogue-State for Speech Recognition in Spoken Dialogue Systems....Pages 439-444 Word Concept Model for Intelligent Dialogue Agents....Pages 445-449 The workshop series on Text, Speech and Dialogue originated in 1998 with the?rst TSD1998 held in Brno, Czech Republic. This year's TSD2000, already the third in the series, returns to Brno and to its organizers from the Faculty of Informatics at the Masaryk University. As shown by the ever growing interest in TSD series, this annual workshop developed into the prime meeting of speech and language researchers from both sides of the former Iron Curtain, which provides a unique opportunity to get acquainted with the current activities in all aspects of language communication and to witness the amazing vitality of researchers from the former East Block countries. Thanks need to be extended to all who continue to make the TSD workshop series such a success:?rst, to the authors themselves, without whom TSD2000 would not exist; next, to all organizations that support TSD2000, among them the International Speech Communication Association, the Faculty of Informatics at the Masaryk University in Brno and the Faculty of Applied Sciences, West Bohemia University in Plzen;? and last but not least, to the organizers and members of the Program Committee who spentmuch effort to make TSD2000 success and who reviewed 131 contributions submitted from all corners of the world and accepted 75 out of them for presentation at the workshop. This book is evidence of the success of all involved

This book constitutes the refereed proceedings of the 9th International Conference on Text, Speech and Dialogue, TSD 2006, held in Brno, Czech Republic, in September 2006.

The 87 revised full papers presented together with 2 invited papers were carefully reviewed and selected from 175 submissions. The papers present a wealth of state-of-the-art research results in the field of natural language processing with an emphasis on text, speech, and spoken dialogue ranging from theoretical and methodological issues to applications in various fields and with special focus on corpora, texts and transcription, speech analysis, recognition and synthesis, as well as their intertwining within NL dialogue systems.

This book constitutes the refereed proceedings of the Third International Workshop on Text, Speech and Dialogue, TSD 2000, held in Brno, Czech Republic in September 2000. The 75 papers presented were carefully reviewed and selected from 131 submissions. The book presents a wealth of state-of-the-art research and development results from the field of natural language processing with emphasis on text, speech and spoken language