TSD logo separator  TSD 2004 Proceedings  O  Invited Speakers  O  TSD 2004 Program  O  Conference Trip  O  Available Equipment  TSD logo separator 

TSD 2004 Conference Program

For technical details see equipment list.

Tuesday, September 7, 200417:00 - 19:00RegistrationHall
Wednesday, September 8, 20048:00 - 9:00RegistrationHall
9:00 - 9:30Opening Session - Frederick JelinekD3
9:30 - 10:30Kenneth Church - invited speechD3
10:30 - 11:00Coffee BreakHall
11:00 - 12:30Parallel Sessions (2 x 3)D1, D3
12:30 - 13:30Lunch BreakUniversity Canteen
13:30 - 14:30Poster Session (11)Hall
14:30 - 16:00Parallel Sessions (2 x 3)D1, D3
16:00 - 16:30Coffee BreakHall
16:30 - 17:30Parallel Sessions (2 x 2)D1, D3
17:30 - 18:30Demo SessionB116
18:30 - 22:30Welcome ReceptionHall
Thursday, September 9, 20049:00 - 10:00Jan Odijk - invited speechD3
10:00 - 10:30Coffee BreakHall
10:30 - 12:30Parallel Sessions (2 x 4)D1, D3
12:30 - 13:30Lunch BreakUniversity Canteen
13:30 - 14:30Poster Session (12)Hall
14:30 - 16:00Parallel Sessions (2 x 3)D1, D3
16:00 - 16:30Coffee BreakHall
16:30 - 18:00Parallel Sessions (2 x 3)D1, D3
18:00 - 19:00Program Committee MeetingB011
Friday, September 10, 20049:00 - 10:00Patrick Hanks and James Pustejovsky - invited speechD3
10:00 - 10:30Coffee BreakHall
10:30 - 12:30Parallel Sessions (2 x 4)D1, D3
12:30 - 13:30Lunch BreakUniversity Canteen
13:30 - 24:00Trip and Conference Dinner
Saturday, September 11, 200410:00 - 12:00Parallel Sessions (2 x 4)D1, D3
12:00 - 12:30Closing CeremonyD3
12:30 - 14:00Lunch BreakUniversity Canteen

Wednesday, September 8, 2004
8:00Registration (Hall)
9:00Opening Session - Frederick Jelinek (D3)
9:30Kenneth Church - invited speech (D3)
chair: Frederick Jelinek
10:30Coffee Break (Hall)
Parallel Sessions (2 x 3)
Section Text (D1)
chair: Adam Kilgariff
Section Speech (D3)
chair: Jan Cernocky
11:00Dora Csendes and Janos Csirik and Tibor Gyimothy:
The Szeged Corpus: A POS Tagged and Syntactically Annotated Hungarian Natural Language Corpus
11:30Ana-Maria Barbu:
A Positional Linguistics-Based System for Word Alignment
Tomas Beran, Vladimir Bergl, Radek Hampl, Pavel Krbec, Jan Sedivy, Borivoj Tydlitat, Josef Vopicka:
Embedded ViaVoice
12:00Gordana Pavlovic-Lazetic and Dusko Vitas and Cvetana Krstev:
Towards Full Lexical Recognition
Lukas Burget:
Measurement of Complementarity of Recognition Systems
12:30Lunch Break (University Canteen)
13:30Poster Session (11) (Hall)
chair: Ivan Kopecek
Tanel Alumae:
Large Vocabulary Continuous Speech Recognition for Estonian Using Morphemes and Classes
Ebru Arisoy, Levent M. Arslan:
A Universal Human Machine Speech Interaction Language for Robust Speech Recognition Applications
Jesus Bobadilla:
New Speech Enhancement Approach for Formant Evolution Detection
Peter Caky and Martin Klimo and Igor Mihalik and Radovan Mladsik:
Text-to-Speech for Slovak Language
Frantisek Grezl:
Combinations of TRAP Based Systems
Petr Horak and Jakub Adamek and Daniel Sobe:
Using Neural Networks to Model Prosody in Czech TTS System Epos
Jakub Kanis, Ludek Muller:
Using the Lemmatization Technique for Phonetic Transcription in Text-to-Speech System
Andrej Ljolje and Vincent Goffin and Murat Saraclar:
Low Latency Real-Time Vocal Tract Length Normalization
Petr Motlicek and Jan Cernocky:
Multimodal Phoneme Recognition of Meeting Data
Milan Rusko and Marian Trnka and Sachia Darzagin and Milos Cernak:
Slovak Speech Database for Experiments and Application Building in Unit-Selection Speech Synthesis
Juan-Luis Garcia Zapata, Juan Carlos Diaz Martin and Pedro Gomez Vilda:
Parallel Root-Finding Method for LPC Analysis of Speech
Parallel Sessions (2 x 3)
Section Text (D1)
chair: Patrick Hanks
Section Speech (D3)
chair: Vaclav Matousek
14:30Cormac Flynn and John Dunnion:
Event Clustering in the News Domain
Todor Ganchev and Mihalis Siafarikas and Nikos Fakotakis:
Speaker Verification Based on Wavelet Packets
15:00Svetlana Hensman and John Dunnion:
Using Linguistic Resources to Construct Conceptual Graph Representation of Texts
Ismael Garcia-Varea and Alberto Sanchis and Francisco Casacuberta:
A Decoding Algorithm for Speech Input Statistical Translation
15:30Vladimir Kadlec and Pavel Smrz:
Grammatical Heads Optimized for Parsing and Their Comparison with Linguistic Intuition
Gabor Gosztolya, Andras Kocsor:
Aggregation Operators and Hypothesis Space Reductions in Speech Recognition
16:00Coffee Break (Hall)
Parallel Sessions (2 x 2)
Section Text (D1)
chair: Kenneth Church
Section Speech (D3)
chair: Martin Rajman
16:30Adam Kilgarriff:
How Dominant is the Commonest Sense of a Word?
Tino Haderlein and Stefan Steidl and Elmar Noeth and Frank Rosanowski and Maria Schuster :
Automatic Recognition and Evaluation of Tracheoesophageal Speech
17:00Pavel Smerk:
Unsupervised Learning of Rules for Morphological Disambiguation
Ladislava Janku:
Auditory Scene Analysis via Application of ICA in a Time-Frequency Domain
17:30Demo Session (B116)
G. Totkov, D. Blagoev, V. Angelova
SLOG 1.0: Bulgarian text to speech transformation system

Sayed Kamal-Aldin Ghiathi Saeed Bagheri Shouraki
An interactive tool for extracting human knowledge in speech recognition

Leonid Kof
Heuristics for Extraction of Predicates and their Arguments

Z. Alexin, J. Csirik, R. Farkas, T. Gyimóthy, A. Hócza, A. Kuba, Gy. Szarvas
An Information Extraction Framework

Dan Bohus, Jahanzeb Sherwani
Conversational Strategies in the RavenClaw Dialogue Management Framework
Alexander Troussov, Mayo Takeuchi, D.J.McCloskey
Written Language Identification Using Word Fragments of Variable Length

Juan Luis García Zapata, Juan Carlos Díaz Martín, Juan Antonio Rico Gallego
Handy Speech Recognition Development on DSK Platforms

Francis Chantree, Alistair Willis, Anne De Roeck
A "Flexible Chunker" that Segments Text for Ambiguity Analysis

Ludwig Hitzenberger et al, Vaclav Matousek et al
Multilingual municipal information retrieval dialogue system

Elmar Noeth:
Speech Controlled Analysis of Stenoses
18:30Welcome Reception (Hall)

Thursday, September 9, 2004
9:00Jan Odijk - invited speech (D3)
chair: Josef Psutka
10:00Coffee Break (Hall)
Parallel Sessions (2 x 4)
Section Dialogue (D1)
chair: Leon Rothkranz
Section Speech (D3)
chair: France Mihelic
10:30Louis ten Bosch and Nelleke Oostdijk and Jan Peter de Ruiter:
Durational Aspects of Turn-Taking in Spontaneous Face-to-Face and Telephone Dialogues
Konstantinos Koumpis:
Automatic Categorization of Voicemail Transcripts Using Stochastic Language Models
11:00Thomas Brey and Tomas Pavelka:
A Speech Platform for a Bilingual City Information System
Antonio Moura and Diamantino Freitas and Vitor Pera :
A New Multi-Modal Database for Developing Speech Recognition Systems for an Assistive Technology Application
11:30Trung H. Bui and Martin Rajman and Miroslav Melichar:
Rapid Dialogue Prototyping Methodology
Eva Navas and Inmaculada Hernaez and Amaia Castelruiz and Iker Luengo:
Obtaining and Evaluating an Emotional Database for Prosody Modelling in Standard Basque
12:00Stefan Steidl and Christian Hacker and Christine Ruff and Anton Batliner and Elmar Noeth and Jurgen Haas :
Looking at the Last Two Turns, I'd Say This Dialogue Is Doomed - Measuring Dialogue Success
Jan Nouza and Jindrich Zdansky and Petr David:
Fully Automated Approach to Broadcast News Transcription in Czech Language
12:30Lunch Break (University Canteen)
13:30Poster Session (12) (Hall)
chair: Ales Horak
Alberto Diaz and Pablo Gervas:
Item Summarization in Personalisation of News Delivery Systems
Hector Garcia-Puigcerver and Fernando Llopis and Mariano Cano and Antonio Toral and Hector Espi:
IR-n System, a Passage Retrieval Architecture
Alexander Horak and Lucia Gianitsova and Maria Simkova and Martin Smotlak and Radovan Garabik:
Slovak National Corpus
Andras Kuba and Andras Hocza and Janos Csirik:
POS Tagging of Hungarian with Combined Statistical and Rule-Based Methods
Songwook Lee and Jungyun Seo:
Grammatical Relations Identification of Korean Parsed Texts Using Support Vector Machines
Pavel Matejka and Igor Szoeke and Petr Schwarz and Jan Cernocky:
Automatic Language Identification Using Phoneme and Automatically Derived Unit Strings
Maria Paloma Moreda Pozo, Manuel Fernandez Ba nos, Manuel Palomar Sanz, Armando Suarez Cueto:
Identifying Semantic Roles Using Maximum Entropy Models
Benoit Sagot and Adil El Ghali:
Coupling Grammar and Knowledge Base: Range Concatenation Grammars and Description Logics
Victor Zakharov and Sergei Volkov:
Morphological Tagging of Russian Texts of the XIX\nth Century
Cesar Gonzalez-Ferreras and Valentin Carde noso-Payo:
Building Voice Applications from Web Content
Stefan Riedel and Wolfgang Wunschmann:
Evaluation of a Web Based Information System for Blind and Visually Impaired Students: A Descriptive Study
L.J.M. Rothkrantz and P. Wiggers and F. Flippo and D. Woei-A-Jin and R.J. van Vark:
Multimodal Dialogue Management
Parallel Sessions (2 x 3)
Section Speech (D1)
chair: Genevieve Baudoin
Section Speech (D3)
chair: Jan Nouza
14:30Luis Javier Rodriguez Fuentes and M. Ines Torres:
A Speaker Clustering Algorithm for Fast Speaker Adaptation in Continuous Speech Recognition
Panagiotis Zervas and Nikos Fakotakis and George Kokkinakis:
Pitch Accent Prediction from ToBI Annotated Corpora Based on Bayesian Learning
15:00Jan Romportl, Jindrich Matousek, Daniel Tihelka:
Advanced Prosody Modelling
Rafael M. Terol and Patricio Martinez-Barco and Manuel Palomar:
An Architecture for Spoken Document Retrieval
15:30L.J.M. Rothkrantz and P. Wiggers and J.W.A. van Wees and R.J. van Vark:
Voice Stress Analysis
Bostjan Vesnicer and France Mihelic:
Evaluation of the Slovenian HMM-Based Speech Synthesis System
16:00Coffee Break (Hall)
Parallel Sessions (2 x 3)
Section Text (D1)
chair: Jan Hajic
Section Speech (D3)
chair: Ivo Ipsic
16:30Manolis Maragoudakis and Todor Ganchev and Nikos Fakotakis:
Bayesian Reinforcement for a Probabilistic Neural Net Part-of-Speech Tagger
Odetunji A. Odejobi, Anthony J. Beaumont and Shun Ha Sylvia Wong:
A Computational Model of Intonation for Yoruba Text-to-Speech Synthesis: Design and Analysis
17:00Kwangcheol Shin and Sang-Yong Han and Alexander Gelbukh:
Balancing Manual and Automatic Indexing for Retrieval of Paper Abstracts
Marc Padellini and Francois Capman and Genevieve Baudoin:
Dynamic Unit Selection for Very Low Bit Rate Coding at 500 bits/sec
17:30Matthijs Mulder and Anton Nijholt and Marten den Uyl and Peter Terpstra:
A Lexical Grammatical Implementation of Affect
Ales Padrta and Vlasta Radova:
On the Background Model Construction for Speaker Verification Using GMM
18:00Program Committee Meeting (B011)

Friday, September 10, 2004
9:00Patrick Hanks and James Pustejovsky - invited speech (D3)
chair: Karel Pala
10:00Coffee Break (Hall)
Parallel Sessions (2 x 4)
Section Dialogue (D1)
chair: Pavel Smrz
Section Speech (D3)
chair: Jan Odijk
10:30Melita Hajdinjak and France Mihelic:
Information-Providing Dialogue Management
Petr Schwarz and Pavel Matejka and Jan Cernocky:
Towards Lower Error Rates in Phoneme Recognition
11:00Zdenek Krnoul and Milos Zelezny:
Realistic Face Animation for a Czech Talking Head
Gyoergy Szaszak and Klara Vicsi:
Examination of Pronunciation Variation from Hand-Labelled Corpora
11:30Jeanne Villaneau and Jean-Yves Antoine and Olivier Ridoux:
Logical Approach to Natural Language Understanding in a Spoken Dialogue System
Abdelgawad Eb. Taher:
New Refinement Schemes for Voice Conversion
12:00Magdalena Wolska and Ivana Kruijff-Korbayova:
Building a Dependency-Based Grammar for Parsing Informal Mathematical Discourse
12:30Lunch Break (University Canteen)
13:30Trip and Conference Dinner

Saturday, September 11, 2004
TimeParallel Sessions (2 x 4)
Section Text (D1)
chair: Viktor Zakharov
Section Speech (D3)
chair: Ivan Kopecek
10:00Pavel Makagonov and Mikhail Alexandrov and Alexander Gelbukh:
Clustering Abstracts instead of Full Texts
Jindrich Matousek and Daniel Tihelka:
Slovak Text-to-Speech Synthesis in ARTIC System
10:30Francois Toussenel:
Ambiguous Supertagging Using a Feature Structure
Gerasimos Xydas and Dimitris Spiliotopoulos and Georgios Kouroupetroglou:
Modeling Prosodic Structures in Linguistically Enriched Environments
11:00Yeohoon Yoon and Songwook Lee and Joochan Sohn:
A Practical Word Sense Disambiguation System with High Performance for Korean
Jan Zelinka and Ludek Muller:
Automatic General Letter-to-Sound Rules Generation for German Text-to-Speech System
11:30Laszlo Havasi and Helga M. Szabo:
HANDY: Sign Language Synthesis from Sublexical Elements Based on an XML Data Representation
Pavel Zikovsky and Tom Pesina and Pavel Slavik :
Processing of Logical Expressions for Visually Impaired Users
12:00Closing Ceremony (D3)
12:30Lunch Break (University Canteen)


Faculty of Informatics International Speech Communication Association Faculty of Applied Sciences