ISBN: 3-540-66494-7
TITLE: Text, Speech and Dialogue
AUTHOR: Matousek, Vaclav; Mautner, Pavel; Ocelikova, Jana; Sojka, Petr (Eds.)
TOC:

Invited Talks
Research Issues for the Next Generation Spoken Dialogue Systems 1
E. Nth, F. Gallwitz, M. Aretoulaki, J. Haas, S. Harbeck, R. Huber, H. Niemann
Data-Driven Analysis of Speech 10
Hynek Hermansky
Towards a Road Map for Machine Translation Research 19
Steven Krauwer
The Prague Dependency Treebank: Crossing the Sentence Boundary 20
Eva Hajicov
Text
Tiered Tagging and Combined Language Models Classifiers28
Dan Tufis
Syntactic Tagging 34
Alena Bhmov, Jarmila Panevov, Petr Sgall
Information, Language, Corpus and Linguistics 39
Frantiek Cermk
Prague Dependency Treebank: Restoration of Deletions 44
Eva Haji cov, Ivana Kruijff-Korbayov, Petr Sgall
Some Types of Syntactic Ambiguity 50
Jarmila Panevov, Markta Strankov
Semantic Annotation of (Czech) Corpus Texts 56
Karel Pala
The General Principles of the Diachronic Part of the Czech National Corpus 62
Karel Kucera
Performing Adaptive Morphological Analysis Using Internet Resources 66
Marek Trabalka, Mria Bielikov
Automatic Text-to-Speech Alignment: Aspects of Robustification 72
R. Schmidt, R. Neumann
Czech Translation of G. Orwell's `1984': Morphology and Syntactic Patterns in the Corpus 77
Vladimr Petkevi c
Handling Word Order in a Multilingual System for Generation of Instructions 83 

Ivana Kruijff-Korbayov, Geert-Jan M. Kruijff
Text Structuring in a Multilingual System for Generation of Instructions 89
Ivana Kruijff-Korbayov, Geert-Jan M. Kruijff
Leveraging Syntactic Information for Text Normalization 95
Deborah A. Coughlin
Automatic Structuring of Written Texts 101
Marek Veber, Ale s Hork, Rostislav Julinek, Pavel Smr
Implementation of Efficient and Portable Parser for Czech 105
Pavel Smr, Ale Hork
Word Sense Disambiguation of Czech Texts 109
Ondrej Cikhart, Jan Hajic
The Acquisition of Some Lexical Constraints from Corpora 115
Goran Nenadic, Irena Spasic
Run-Time Extensible (Semi-)Top-Down Parser 121
Michal Zemlicka, Jaroslav Krl
Enhancing Readability of Automatic Summaries by Using Schemas 127
Mariem Ellouze, Abdelmajid Ben Hamadou
Use of a Weighted Topic Hierarchy for Document Classification 133
Alexander Gelbukh, Grigori Sidorov, Adolfo Guzman-Arnas
Speech
Remarks on Sentence Prosody and Topic-Focus Articulation 139
Petr Sgall
Speech Recognition Using Elman Neural Networks 146
L.J.M. Rothkrantz, D. Nollen
Use of Hidden Markov Models for Evaluation of Russian Digits Pronunciation by the Foreigners 152
Alexei Machovikov, Iliana Machovikova
Allophone-Based Concatenative Speech Synthesis System for Russian 156
Pavel A. Skrelin
Intonation Questions in English and Armenian:
Results of the Perceptual Study 160
Nina B. Volskaya, Anna S. Grigoryan
Methods of Sentences Selection for Read-Speech Corpus Design 165
Vlasta Radov, Petr Voplka
Speaker Identification Using Discriminative Centroids Weighting  A Growing Cell Structure Approach 171
Bogdan Sabac, Inge Gavat
Speech Analysis and Recognition Synchronised by One-Quasiperiodical Segmentation 175
Taras K. Vintsiuk, Mykola M. Sazhok
Spanish Phoneme Classification by Means of a Hierarchy of Kohonen
Self-Organizing Maps 181
A. Postigo Gardon, C. Ruiz Vzquez, A. Arruti Illarramendi
Information Theoretic Based Segments for Language Identification 187
Stefan Harbeck, Uwe Ohler, Elmar Nth, Heinrich Niemann
Fast and Robust Features for Prosodic Classification 193
Jan Buckow, Volker Warnke, Richard Huber, Anton Batliner, Elmar Nth, Heinrich Niemann
A Segment Based Approach for Prosodic Boundary Detection 199
Volker Warnke, Elmar Nth, Heinrich Niemann, Georg Stemmer
Speech Recognition and Syllable Segments 203
Ivan Kopecek
Text Preprocessing for Czech Speech Synthesis 209
Robert Batuek, Jan Dvork 

MLPs and Mixture Models for the Estimation of the Posterior
Probabilities of Class Membership 215
Alexei V. Ivanov, Alexander A. Petrovsky
A Simple Spanish Part of Speech Tagger for Detection and Correction of Accentuation Error 219
S. N. Galicia-Haro, I. A. Bolshakov, A. F. Gelbukh
Slovene Interactive Text-to-Speech Evaluation Site  SITES 223
Jerneja Gros, France Miheli c, Nikola Paveic
Developing HMM-Based Recognizers with ESMERALDA 229
Gernot A. Fink
Large Vocabulary Speech Recognition for Read and Broadcast Czech 235
W. Byrne, J. Haji c, P. Ircing, F. Jelinek, S. Khudanpur, J. McDonough, N. Peterek, J. Psutka
Rules for Automatic Grapheme-to-Allophone Transcription in Slovene 241
Jerneja Gros, France Miheli c, Nikola Paveic
Speech Segmentation Aspects of Phone Transition Acoustical Modelling 248
Simon Dobri sek, France Miheli c, Nikola Paveic
Context Dependent Phoneme Recognition 252
Dusan Krokavec
State-Space Model Based Labeling of Speech Signals 258
Dusan Krokavec, Anna Filasov
Very Low Bit Rate Speech Coding: Comparison of Data-Driven Units with Syllable Segments 262
Jan Cernock, Ivan Kopecek, Genevive Baudoin, Grard Chollet
Storing Prosody Attributes of Spontaneous Speech 268
Jana Kleckov
Dialogue
An Overview of the State of the Art of Coding Schemes for Dialogue Act
Annotation 274
Marion Klein
Structural and Semantic Dialogue Filters 280
Zdenek Mikovec, Martin Klma, Pavel Slavk
A Retrieval System of Broadcast News Speech Documents through
Keyboard and Voice 286
Hiromitsu Nishizaki, Seiichi Nakagawa
Situations in Dialogs 290
Petr Hejda
Components for Building an Automatic Voice-Dialogue Telephone System 296
Miroslav Holada
Modeling of the Information Retrieval Dialogue Systems 302
Ivan Kopecek
Improvement of the Recognition Rate of Spoken Queries to the Dialogue
System 308
Vclav Matouek, Jana Ocelkov
Analysis of Different Dialog Strategies in the Slovenian Spoken Dialog System315
Ivo Ipic, France Mihelic, Nikola Paveic
Posters
Dispersion of Words in a Language Corpus 321
Jaroslava Hlavcov, Pavel Rychl
Corpus-Based Rules for Czech Verb Discontinuous Constituents 325
Eva ckov, Karel Pala
Automatic Modelling of Regional Pronunciation Variation for Russian 329
Kseniya B. Shalonova
Experiments Regarding the Superposition of Emotional Features on Neutral Korean Speech 333
Cheol-Woo Jo, Attila Ferencz, Dae-Hyun Kim
Modeling Cue Phrases in Turkish: A Case Study 337
Bilge Say
Speaker Identification Based on Vector Quantization 341
Vlasta Radov, Zdenek Svenda
Robustness in Tabular Deduction for Multimodal Logical Grammar - Part 1 345
Geert-Jan M. Kruijff
Classifying Visemes for Automatic Lipreading 349
Michiel Visser, Mannes Poel, Anton Nijholt
Semantic Inference in the HumanMachine Communication 353
Leo Hadacz
Playing with RST: Two Algorithms for the Automated Manipulation of Discourse Trees 357
Floriana Grasso
Another Step in the Modeling of Basque Intonation: Bermeo 361
Gorka Elordieta, Iaki Gaminde, Inma Hernez, Jasone Salaberria, Igor Martin de Vidales
Electronic Dictionaries: For Both Humans and Computers 365
Igor A. Bolshakov, Alexander F. Gelbukh, Sofia N. Galicia-Haro
Statistical Evaluation of Similarity Measures on Multi-lingual Text Corpora 369
R. Neumann, R. Schmidt
Document Title Patterns in Information Retrieval 372
Manuel Montes-y-Gmez, Alexander F. Gelbukh, Aurelio Lpez-Lpez
Statistical Approach to the Automatic Synthesis of Czech Speech 376
Jindrich Matouek, Josef Psutka, Zbynek Tychtl
Language Model Representations for the GOPOLIS Database 380
Janez Zibert, Jerneja Gros, Simon Dobriek, France Mihelic
Recognition of Alkohol Influence on Speech 384
Richard Menk
Recording of Czech and Slovak Telephone Databases within SpeechDat-E 388
Jan Cernock, Petr Pollk, Milan Rusko, Vclav Hanl, Marin Trnka
Pragmatic Features of the Electronic Discourse in the Internet 392
Irina Potashova
Author Index 395
END
