Invited Talks -- Combating the Sparse Data Problem of Language Modelling -- Toward Robust Speech Recognition and Understanding -- Text -- A Pilot Study of English Selectional Preferences and Their Cross-Lingual Compatibility with Basque -- Auto-tagging of Text Documents into XML -- Stable Coordinated Pairs in Text Processing -- Backoff DOP: Parameter Estimation by Backoff -- Document Clustering into an Unknown Number of Clusters Using a Genetic Algorithm -- Experiments in German Treebank Parsing -- A Theoretical Basis of an Architecture of a Shell of a Reasonably Robust Syntactic Analyser -- Si3Trenn and Si3Silb: Using the SiSiSi Word Analysis System for Pre-hyphenation and Syllable Counting in German Documents -- Detecting Annotation Errors in a Corpus by Induction of Syntactic Patterns -- The Computational Complexity of Rule-Based Part-of-Speech Tagging -- Text Corpus with Errors -- Identification of Multiwords as Preprocessing for Automatic Extraction of Lexical Similarities -- Build a Large-Scale Syntactically Annotated Chinese Corpus -- Computational Benefits of a Totally Lexicalist Grammar -- Using a Czech Valency Lexicon for Annotation Support -- On Concept Based Approach for Determining Semantic Index Terms -- Corpora Issues in Validation of Serbian Wordnet -- Optimising Attribute Selection in Conversational Search -- Russian Corpus of the 19th Century -- Speech -- On Homogeneous Segments -- Advances in Automatic Speech Recognition by Imitating Spreading Activation -- The Incorporation of Confidence Measures to Language Understanding -- Speech Recognition with ? -Law Companded Features on Reverberated Signals -- Understanding Speech Based on a Bayesian Concept Extraction Method -- A Data-Driven Framework for Intonational Phrase Break Prediction -- Phoneme Recognition Using Temporal Patterns -- Multi-array Multi-speaker Tracking -- Towards Automatic Transcription of Spontaneous Czech Speech in the MALACH Project -- TERSEO: Temporal Expression Resolution System Applied to Event Ordering -- Non-native Pronunciation Variants of City Names as a Problem for Speech Technology Applications -- Improving Speech Recognition by Utilizing Domain Knowledge and Confidence Measures -- Comparison of Acoustic Adaptation Methods in Multilingual Speech Recognition Environment -- A Comparison of Unit Selection Techniques in Limited Domain Speech Synthesis -- Recognition of Speech with Non-random Attributes -- Text-Independent Speaker Verification: The WCL-1 System -- Local Time-Frequency Operators in TRAPs for Speech Recognition -- Entropy and Dynamism Criteria for Speech and Audio Classification Applications -- Speech Production: Phonetic Encoding of Real and Non-words -- Experiments with Automatic Segmentation for Czech Speech Synthesis -- All-Pole Modeling for Definition of Speech Features in Aurora3 DSR Task -- Building of a Vocabulary for the Automatic Voice-Dictation System -- Real-Time Vocal Tract Length Normalization in a Phonological Awareness Teaching System -- Hard-Testing the Multi-stream Approach to Automatic Speech Recognition -- Pitch-Synchronous Speech Signal Segmentation and Its Applications -- Building LVCSR System for Transcription of Spontaneously Pronounced Russian Testimonies in the MALACH Project: Initial Steps and First Results -- The Phase Substitutions in Czech Harmonic Concatenative Speech Synthesis -- Dialogue -- Combining Task Descriptions and Ontological Knowledge for Adaptive Dialogue -- Large Text and Audio Data Alignment for Multimedia Applications -- Building Multilingual Speech Corpora from Interpreted Spontaneous Dialogues on the Net -- Multi-modal Voice Application Design in a Multi-client Environment -- User Modeling and Plan Recognition under Conditions of Uncertainty -- Bilingual Speech Recognition for a Weather Information Retrieval Dialogue System -- On the Use of Prosodic Labelling in Corpus-Based Linguistic Studies of Spontaneous Speech -- A Multi-modal Eliza Using Natural Language Processing and Emotion Recognition -- The Wizard of Oz System for Weather Information Retrieval -- Directives in Estonian Information Dialogues -- SpeechDat-Like Estonian Database -- Dialogue Experiment for Elderly People in Home Health Care System.