Text, Speech and Dialogue: Second International Workshop, TSD’99 Plzen, Czech Republic, September 13–17, 1999 Proceedings

Research Issues for the Next Generation Spoken Dialogue Systems....Pages 1-9
Data-Driven Analysis of Speech....Pages 10-18
Towards a Road Map for Machine Translation Research....Pages 19-19
The Prague Dependency Treebank: Crossing the Sentence Boundary....Pages 20-27
Tiered Tagging and Combined Language Models Classifiers....Pages 28-33
Syntactic Tagging: Procedure for the Transition from the Analytic to the Tectogrammatical Tree Structures....Pages 34-38
Information, Language, Corpus and Linguistics....Pages 39-43
Prague Dependency Treebank: Restoration of Deletions....Pages 44-49
Some Types of Syntactic Ambiguity; How to Treat Them in an Automatic Procedure....Pages 50-55
Semantic Annotation of (Czech) Corpus Texts....Pages 56-61
The General Principles of the Diachronic Part of the Czech National Corpus....Pages 62-65
Performing Adaptive Morphological Analysis Using Internet Resources....Pages 66-71
Automatic Text-to-Speech Alignment: Aspects of Robustification....Pages 72-76
Czech Translation of G. Orwell’s ‘1984’: Morphology and Syntactic Patterns in the Corpus....Pages 77-82
Handling Word Order in a Multilingual System for Generation of Instructions....Pages 83-88
Text Structuring in a Multilingual System for Generation of Instructions....Pages 89-94
Leveraging Syntactic Information for Text Normalization....Pages 95-100
Automatic Structuring of Written Texts....Pages 101-104
Implementation of Efficient and Portable Parser for Czech....Pages 105-108
Word Sense Disambiguation of Czech Texts....Pages 109-114
The Acquisition of Some Lexical Constraints from Corpora....Pages 115-120
Run-Time Extensible (Semi-)Top-Down Parser....Pages 121-126
Enhancing Readability of Automatic Summaries by Using Schemas....Pages 127-132
Use of a Weighted Topic Hierarchy for Document Classification....Pages 133-138
Remarks on Sentence Prosody and Topic-Focus Articulation....Pages 139-145
Speech Recognition Using Elman Neural Networks....Pages 146-151
Use of Hidden Markov Models for Evaluation of Russian Digits Pronunciation by the Foreigners....Pages 152-155
Allophone-Based Concatenative Speech Synthesis System for Russian....Pages 156-159
Intonation Questions in English and Armenian: Results of the Perceptual Study....Pages 160-164
Methods of Sentences Selection for Read-Speech Corpus Design....Pages 165-170
Speaker Identification Using Discriminative Centroids Weighting — A Growing Cell Structure Approach....Pages 171-174
Speech Analysis and Recognition Synchronised by One-Quasiperiodical Segmentation....Pages 175-180
Spanish Phoneme Classification by Means of a Hierarchy of Kohonen Self-Organizing Maps....Pages 181-186
Information Theoretic Based Segments for Language Identification....Pages 187-192
Fast and Robust Features for Prosodic Classification?....Pages 193-198
A Segment Based Approach for Prosodic Boundary Detection?....Pages 199-202
Speech Recognition and Syllable Segments....Pages 203-208
Text Preprocessing for Czech Speech Synthesis....Pages 209-214
MLPs and Mixture Models for the Estimation of the Posterior Probabilities of Class Membership....Pages 215-218
A Simple Spanish Part of Speech Tagger for Detection and Correction of Accentuation Error....Pages 219-222
Slovene Interactive Text-to-Speech Evaluation Site — SITES....Pages 223-228
Developing HMM-Based Recognizers with ESMERALDA....Pages 229-234
Large Vocabulary Speech Recognition for Read and Broadcast Czech....Pages 235-240
Rules for Automatic Grapheme-to-Allophone Transcription in Slovene....Pages 241-247
Speech Segmentation Aspects of Phone Transition Acoustical Modelling....Pages 248-251
Context Dependent Phoneme Recognition....Pages 252-257
State-Space Model Based Labeling of Speech Signals....Pages 258-261
Very Low Bit Rate Speech Coding: Comparison of Data-Driven Units with Syllable Segments....Pages 262-267
Storing Prosody Attributes of Spontaneous Speech....Pages 268-273
An Overview of the State of the Art of Coding Schemes for Dialogue Act Annotation....Pages 274-279
Structural and Semantic Dialogue Filters....Pages 280-285
A Retrieval System of Broadcast News Speech Documents through Keyboard and Voice....Pages 286-289
Situations in Dialogs....Pages 290-295
Components for Building an Automatic Voice-Dialogue Telephone System....Pages 296-301
Modeling of the Information Retrieval Dialogue Systems....Pages 302-307
Improvement of the Recognition Rate of Spoken Queries to the Dialogue System....Pages 308-314
Analysis of Different Dialog Strategies in the Slovenian Spoken Dialog System....Pages 315-320
Dispersion of Words in a Language Corpus....Pages 321-324
Corpus-Based Rules for Czech Verb Discontinuous Constituents....Pages 325-328
Automatic Modelling of Regional Pronunciation Variation for Russian....Pages 329-332
Experiments Regarding the Superposition of Emotional Features on Neutral Korean Speech....Pages 333-336
Modeling Cue Phrases in Turkish: A Case Study....Pages 337-340
Speaker Identification Based on Vector Quantization....Pages 341-344
Robustness in Tabular Deduction for Multimodal Logical Grammar — Part 1....Pages 345-348
Classifying Visemes for Automatic Lipreading....Pages 349-352
Semantic Inference in the Human-Machine Communication....Pages 353-356
Playing with RST: Two Algorithms for the Automated Manipulation of Discourse Trees....Pages 357-360
Another Step in the Modeling of Basque Intonation: Bermeo....Pages 361-364
Electronic Dictionaries: For Both Humans and Computers....Pages 365-368
Statistical Evaluation of Similarity Measures on Multi-lingual Text Corpora....Pages 369-371
Document Title Patterns in Information Retrieval....Pages 372-375
Statistical Approach to the Automatic Synthesis of Czech Speech....Pages 376-379
Language Model Representations for the GOPOLIS Database....Pages 380-383
Recognition of Alkohol Influence on Speech....Pages 384-387
Recording of Czech and Slovak Telephone Databases within SpeechDat-E....Pages 388-391
Pragmatic Features of the Electronic Discourse in the Internet....Pages 392-394