7. TSD 2004: Brno, Czech Republic

Invited Papers

• Kenneth Ward Church:
  Speech and Language Processing: Can We Use the Past to Predict the Future? 3-14
  
• Patrick Hanks, James Pustejovsky:
  Common Sense About Word Meaning: Sense in Context. 15-18
  
• Jan Odijk:
  ScanSoft's Technologies. 19-22
  

Text

• Ana-Maria Barbu:
  A Positional Linguistics-Based System for Word Alignment. 23-30
  
• Akshar Bharati, Rajeev Sangal, Dipti Mishra, Sriram Venkatapathy, Papi Reddy T.:
  Handling Multi-word Expressions Without Explicit Linguistic Rules in an MT System. 31-40
  
• Dóra Csendes, János Csirik, Tibor Gyimóthy:
  The Szeged Corpus: A POS Tagged and Syntactically Annotated Hungarian Natural Language Corpus. 41-48
  
• Alberto Díaz Esteban, Pablo Gervás:
  Item Summarization in Personalisation of News Delivery Systems. 49-56
  
• Fernando Llopis, Héctor García Puigcerver, Mariano Cano, Antonio Toral, Héctor Espí:
  IR-n System, a Passage Retrieval Architecture. 57-64
  
• Cormac Flynn, John Dunnion:
  Event Clustering in the News Domain. 65-72
  
• Laszlo Havasi, Helga M. Szabó:
  HANDY: Sign Language Synthesis from Sublexical Elements Based on an XML Data Representation. 73-80
  
• Svetlana Hensman, John Dunnion:
  Using Linguistic Resources to Construct Conceptual Graph Representation of Texts. 81-88
  
• Ales Horák, Lucia Gianitsová, Mária Simková, Martin Smotlák, Radovan Garabík:
  Slovak National Corpus. 89-94
  
• Vladimír Kadlec, Pavel Smrz:
  Grammatical Heads Optimized for Parsing and Their Comparison with Linguistic Intuition. 95-102
  
• Adam Kilgarriff:
  How Dominant Is the Commonest Sense of a Word? 103-112
  
• András Kuba, András Hócza, János Csirik:
  POS Tagging of Hungarian with Combined Statistical and Rule-Based Methods. 113-120
  
• Songwook Lee, Jungyun Seo:
  Grammatical Relations Identification of Korean Parsed Texts Using Support Vector Machines. 121-128
  
• Pavel Makagonov, Mikhail Alexandrov, Alexander F. Gelbukh:
  Clustering Abstracts Instead of Full Texts. 129-136
  
• Manolis Maragoudakis, Todor Ganchev, Nikos Fakotakis:
  Bayesian Reinforcement for a Probabilistic Neural Net Part-of-Speech Tagger. 137-146
  
• Pavel Matejka, Igor Szöke, Petr Schwarz, Jan Cernocký:
  Automatic Language Identification Using Phoneme and Automatically Derived Unit Strings. 147-154
  
• Jindrich Matousek, Daniel Tihelka:
  Slovak Text-to-Speech Synthesis in ARTIC System. 155-162
  
• Paloma Moreda, Manuel Fernández, Manuel Palomar, Armando Suárez:
  Identifying Semantic Roles Using Maximum Entropy Models. 163-170
  
• Matthijs Mulder, Anton Nijholt, Marten den Uyl, Peter Terpstra:
  A Lexical Grammatical Implementation of Affect. 171-178
  
• Gordana Pavlovic-Lazetic, Dusko Vitas, Cvetana Krstev:
  Towards Full Lexical Recognition. 179-186
  
• Antoine Rozenknop, Jean-Cédric Chappelier, Martin Rajman:
  Discriminative Models of SCFG and STSG. 187-194
  
• Benoît Sagot, Adil El Ghali:
  Coupling Grammar and Knowledge Base: Range Concatenation Grammars and Description Logics. 195-202
  
• Kwangcheol Shin, Sang-Yong Han, Alexander F. Gelbukh:
  Balancing Manual and Automatic Indexing for Retrieval of Paper Abstracts. 203-210
  
• Pavel Smerk:
  Unsupervised Learning of Rules for Morphological Disambiguation. 211-216
  
• François Toussenel:
  Ambiguous Supertagging Using a Feature Structure. 217-224
  
• Yeohoon Yoon, Songwook Lee, Joochan Sohn:
  A PracticalWord Sense Disambiguation System with High Performance for Korean. 225-234
  
• Victor Zakharov, Sergei Volkov:
  Morphological Tagging of Russian Texts of the XIXth Century. 235-244
  

Speech

• Tanel Alumäe:
  Large Vocabulary Continuous Speech Recognition for Estonian Using Morphemes and Classes. 245-252
  
• Ricardo Sant Ana, Rosangela Coelho, Abraham Alcaim:
  A New Classifier for Speaker Verification Based on the Fractional Brownian Motion Process. 253
  
• Ebru Arisoy, Levent M. Arslan:
  A Universal Human Machine Speech Interaction Language for Robust Speech Recognition Applications. 261-268
  
• Tomás Beran, Vladimír Bergl, Radek Hampl, Pavel Krbec, Jan Sedivý, Borivoj Tydlitát, Josef Vopicka:
  Embedded ViaVoice. 269-274
  
• Jesús Bobadilla:
  New Speech Enhancement Approach for Formant Evolution Detection. 275-282
  
• Lukas Burget:
  Measurement of Complementarity of Recognition Systems. 283-290
  
• Peter Caky, Martin Klimo, Igor Mihálik, Radovan Mladsík:
  Text-to-Speech for Slovak Language. 291-298
  
• Todor Ganchev, Mihalis Siafarikas, Nikos Fakotakis:
  Speaker Verification Based on Wavelet Packets. 299-306
  
• Ismael García-Varea, Alberto Sanchís, Francisco Casacuberta:
  A Decoding Algorithm for Speech Input Statistical Translation. 307-314
  
• Gábor Gosztolya, András Kocsor:
  Aggregation Operators and Hypothesis Space Reductions in Speech Recognition. 315-322
  
• Frantisek Grézl:
  Combinations of TRAP Based Systems. 323-330
  
• Tino Haderlein, Stefan Steidl, Elmar Nöth, Frank Rosanowski, Maria Schuster:
  Automatic Recognition and Evaluation of Tracheoesophageal Speech. 331-338
  
• Petr Horák, Jakub Adámek, Daniel Sobe:
  Using Neural Networks to Model Prosody in Czech TTS System Epos. 339-346
  
• Ladislava Janku:
  Auditory Scene Analysis via Application of ICA in a Time-Frequency Domain. 347-354
  
• Jakub Kanis, Ludek Müller:
  Using the Lemmatization Technique for Phonetic Transcription in Text-to-Speech System. 355-362
  
• Konstantinos Koumpis:
  Automatic Categorization of Voicemail Transcripts Using Stochastic Language Models. 363-370
  
• Andrej Ljolje, Vincent Goffin, Murat Saraclar:
  Low Latency Real-Time Vocal Tract Length Normalization. 371-378
  
• Petr Motlícek, Jan Cernocký:
  Multimodal Phoneme Recognition of Meeting Data. 379-384
  
• António Moura, Diamantino Freitas, Vitor Pera:
  A New Multi-modal Database for Developing Speech Recognition Systems for an Assistive Technology Application. 385-392
  
• Eva Navas, Inma Hernáez, Amaia Castelruiz, Iker Luengo:
  Obtaining and Evaluating an Emotional Database for Prosody Modelling in Standard Basque. 393-400
  
• Jan Nouza, Jindrich Zdánský, Petr David:
  Fully Automated Approach to Broadcast News Transcription in Czech Language. 401-408
  
• Odétúnjí A. Odéjobí, Anthony J. Beaumont, Shun Ha Sylvia Wong:
  A Computational Model of Intonation for Yorùbá Text-to-Speech Synthesis: Design and Analysis. 409-416
  
• Marc Padellini, François Capman, Geneviève Baudoin:
  Dynamic Unit Selection for Very Low Bit Rate Coding at 500 bits/sec. 417-424
  
• Ales Padrta, Vlasta Radová:
  On the Background Model Construction for Speaker Verification Using GMM. 425-432
  
• Luis Javier Rodríguez, Inés Torres:
  A Speaker Clustering Algorithm for Fast Speaker Adaptation in Continuous Speech Recognition. 433-440
  
• Jan Romportl, Jindrich Matousek, Daniel Tihelka:
  Advanced Prosody Modelling. 441-448
  
• Léon J. M. Rothkrantz, Pascal Wiggers, Jan-Willem A. van Wees, Robert J. van Vark:
  Voice Stress Analysis. 449-456
  
• Milan Rusko, Marián Trnka, Sachia Darzágín, Milos Cernak:
  Slovak Speech Database for Experiments and Application Building in Unit-Selection Speech Synthesis. 457-464
  
• Petr Schwarz, Pavel Matejka, Jan Cernocký:
  Towards Lower Error Rates in Phoneme Recognition. 465-472
  
• György Szaszák, Klára Vicsi:
  Examination of Pronunciation Variation from Hand-Labelled Corpora. 473-480
  
• Abdelgawad Eb. Taher:
  New Refinement Schemes for Voice Conversion. 481-488
  
• Jianhua Tao:
  Acoustic and Linguistic Information Based Chinese Prosodic Boundary Labelling. 489-496
  
• Jianhua Tao:
  F0 Prediction Model of Speech Synthesis Based on Template and Statistical Method. 497-504
  
• Rafael M. Terol, Patricio Martínez-Barco, Manuel Palomar:
  An Architecture for Spoken Document Retrieval. 505-512
  
• Bostjan Vesnicer, France Mihelic:
  Evaluation of the Slovenian HMM-Based Speech Synthesis System. 513-520
  
• Gerasimos Xydas, Dimitris Spiliotopoulos, Georgios Kouroupetroglou:
  Modeling Prosodic Structures in Linguistically Enriched Environments. 521-528
  
• Juan-Luis García Zapata, Juan Carlos Díaz Martín, Pedro Gómez Vilda:
  Parallel Root-Finding Method for LPC Analysis of Speech. 529-536
  
• Jan Zelinka, Ludek Müller:
  Automatic General Letter-to-Sound Rules Generation for German Text-to-Speech System. 537-544
  
• Panagiotis Zervas, Nikos Fakotakis, George K. Kokkinakis:
  Pitch Accent Prediction from ToBI Annotated Corpora Based on Bayesian Learning. 545-552
  
• Pavel Zikovsky, Tom Pesina, Pavel Slavík:
  Processing of Logical Expressions for Visually Impaired Users. 553-562
  

Dialogue

• Louis ten Bosch, Nelleke Oostdijk, Jan Peter de Ruiter:
  Durational Aspects of Turn-Taking in Spontaneous Face-to-Face and Telephone Dialogues. 563-570
  
• Thomas Brey, Tomás Pavelka:
  A Speech Platform for a Bilingual City Information System. 571-578
  
• Trung H. Bui, Martin Rajman, Miroslav Melichar:
  Rapid Dialogue Prototyping Methodology. 579-586
  
• César González Ferreras, Valentín Cardeñoso-Payo:
  Building Voice Applications from Web Content. 587-594
  
• Melita Hajdinjak, France Mihelic:
  Information-Providing Dialogue Management. 595-602
  
• Zdenek Krnoul, Milos Zelezný:
  Realistic Face Animation for a Czech Talking Head. 603-610
  
• Stefan Riedel, Wolfgang Wünschmann:
  Evaluation of a Web Based Information System for Blind and Visually Impaired Students: A Descriptive Study. 611-620
  
• Léon J. M. Rothkrantz, Pascal Wiggers, Frans Flippo, Dimitri Woei-A-Jin, Robert J. van Vark:
  Multimodal Dialogue Management. 621-628
  
• Stefan Steidl, Christian Hacker, Christine Ruff, Anton Batliner, Elmar Nöth, Jürgen Haas:
  Looking at the Last Two Turns, I'd Say This Dialogue Is Doomed - Measuring Dialogue Success. 629-636
  
• Jeanne Villaneau, Jean-Yves Antoine, Olivier Ridoux:
  Logical Approach to Natural Language Understanding in a Spoken Dialogue System. 637-644
  
• Magdalena Wolska, Ivana Kruijff-Korbayová:
  Building a Dependency-Based Grammar for Parsing Informal Mathematical Discourse. 645-652