Text -- The Linguistic Basis of a Rule-Based Tagger of Czech -- Harnessing the Lexicographer in the Quest for Accurate Word Sense Disambiguation -- An Integrated Statistical Model for Tagging and Chunking Unrestricted Text -- Extending Bidirectional Chart Parsing with a Stochastic Model -- Ensemble of Classifiers for Noise Detection in PoS Tagged Corpora -- Towards a Dynamic Syntax for Language Modelling -- A Word Analysis System for German Hyphenation, Full Text Search, and Spell Checking, with Regard to the Latest Reform of German Orthography -- Automatic Functor Assignment in the Prague Dependency Treebank -- Categories, Constructions, and Dependency Relations -- Local Grammars and Parsing Coordination of Nouns in Serbo-Croatian -- Realization of Syntactic Parser for Inflectional Language Using XML and Regular Expressions -- A Rigoristic and Automated Analysis of Texts Applied to a Scientific Abstract by Mark Sergot and Others -- Evaluation of Tectogrammatical Annotation of PDT -- Probabilistic Head-Driven Chart Parsing of Czech Sentences -- Aggregation and Contextual Reference in Automatically Generated Instructions -- Information Retrieval by Means of Word Sense Disambiguation -- Statistical Parameterisation of Text Corpora -- An Efficient Algorithm for Japanese Sentence Compaction Based on Phrase Importance and Inter-Phrase Dependency -- Word Senses and Semantic Representations Can We Have Both? -- Automatic Tagging of Compound Verb Groups in Czech Corpora -- Sensitive Words and Their Application to Chinese Processing -- Testing a Word Analysis System for Reliable and Sense-Conveying Hyphenation and Other Applications -- The Challenge of Parallel Text Processing -- Selected Types of Pg-Ambiguity: Processing Based on Analysis by Reduction -- Cohesive Generation of Syntactically Simplified Newspaper Text -- TEA: A Text Analysis Tool for the Intelligent Text Document Filtering -- Competing Patterns for Language Engineering -- Speech -- Recognition and Labelling of Prosodic Events in Slovenian Speech -- Rules for Automatic Grapheme-to-Allophone Transcription in Slovene -- An Adaptive and Fast Speech Detection Algorithm -- Optimal Pitch Path Tracking for More Reliable Pitch Detection -- FlexVoice: A Parametric Approach to High-Quality Speech Synthesis -- The Continuous and Discontinuous Styles in Czech TTS -- Automatic Speech Segmentation with the Application of the Czech TTS System -- Speaker Identification Using Autoregressive Hidden Markov Models and Adaptive Vector Quantisation -- Morpheme Based Language Models for Speech Recognition of Czech -- A Large Czech Vocabulary Recognition System for Real-Time Applications -- Building a New Czech Text-to-Speech System Using Triphone-Based Speech Units -- Acoustic and Perceptual Properties of Syllables in Continuous Speech as a Function of Speaking Rate -- NL-Processor and Linguistic Knowledge Base in a Speech Recognition System -- Russian Phonetic Variability and Connected Speech Transcription -- Database Processing for Spanish Text-to-Speech Synthesis -- Topic-Sensitive Language Modelling -- Design of Speech Recognition Engine -- Combining Multi-band and Frequency-Filtering Techniques for Speech Recognition in Noisy Environments -- Allophone- and Suballophone-Based Speech Synthesis System for Russian -- Diphone-Based Unit Selection for Catalan Text-to-Speech Synthesis -- Analysis of Information in Speech and Its Application in Speech Recognition -- What Textual Relationships Demand Phonetic Focus? -- Speaker Identification Using Kalman Cepstral Coefficients -- Belarussian Speech Recognition Using Genetic Algorithms -- A Discriminative Segmental Speech Model and Its Application to Hungarian Number Recognition -- Comparison of Frequency Bands in Closed Set Speaker Identification Performance -- Recording and Annotation of the Czech Speech Corpus -- Dialogue -- A Text Based Talking Face -- Dialogue Control in the Alparon System -- ISIS: Interaction through Speech with Information Systems -- Centering-Based Anaphora Resolution in Danish Dialogues -- Some Improvements on the IRST Mixed Initiative Dialogue Technology -- Dictionary-Based Method for Coherence Maintenance in Man-Machine Dialogue with Indirect Antecedents and Ellipses -- Reconstructing Conversational Games in an Obligation-Driven Dialogue Model -- Prosody Prediction from Tree-Like Structure Similarities -- A Speaker Authentication Module in TelCorreo -- TelCorreo: A Bilingual E-mail Client over the Telephone -- A Syntactical Model of Prosody as an Aid to Spoken Dialogue Systems in Italian Language -- What Do You Mean by “What Do You Mean”? -- Simplified Processing of Elliptic and Anaphoric Utterances in a Train Timetable Information Retrieval Dialogue System -- Pragmatic and Grammatical Aspects of the Development of Dialogue Strategies -- An Annotation Scheme for Dialogues Applied to Anaphora Resolution Algorithms -- Cooperative Information Retrieval Dialogues through Clustering -- Acoustic Cues for Classifying Communicative Intentions in Dialogue Systems -- Active and Passive Strategies in Dialogue Program Generation -- Architecture of Multi-modal Dialogue System -- The Utility of Semantic-Pragmatic Information and Dialogue-State for Speech Recognition in Spoken Dialogue Systems -- Word Concept Model for Intelligent Dialogue Agents.

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.