The Programme
Last update: September 22, 1998
Wednesday, September 23
8:15 - 8:30
Opening the Workshop
Plenary Section (8:30 - 12:30)
8:30 - 9:00
Frederick Jelinek
A Structured Language Model
9:00 - 9:30
Giulia Bernardis, Herve Bourlard
Confidence Measures in Hybrid HMM/ANN Speech Recognition
9:30 - 10:00
Hynek Hermansky
Data-Driven Speech Analysis For ASR
10:00 - 10:30
Coffee Break
10:30 - 11:00
Frantisek Cermak
Czech National Corpus: Its Character, Goal and Background
11:00 - 11:30
Stefan Harbeck, Elmar Noeth and Heinrich Niemann
Multilingual Speech Recognition in the Context of Multilingual Information Retrieval Dialogues
11:30 - 12:00
Evangelos Dermatas, George Kokkinakis
Lexithiras: Multi-lingual Corpus Lexicography on PCs
12:00 - 12:30
Ivan Kopecek
Dialog Based Programming
Section Speech (14:30 - 18:30)
room A
14:30 - 15:00
J. Cernocky, G. Baudoin, D. Petrovska-Delacretaz, J. Hennebert, G. Chollet
Automatically Derived Speech Units: Applications to Very Low Rate Coding and Speaker Verification
15:00 - 15:30
T. Dutoit, F. Malfrere, V. Pagel, P. Mertens, M. Bagein, A. Ruelle, A. Gilman
EULER: Multi-Lingual Text-to-Speech Project
15:30 - 16:00
F. Gallwitz, A. Batliner, J. Buckow, R.Huber, H.Niemann, E.Noeth
Pushing forward the Interface between Recognition and Understanding - How to Integrate Syntactic Structure into the Output of a Word Recognizer
16:00 - 16:30
Attila Ferencz, Istvan Nagy, Tunde-Csilla Kovacs, Maria Ferencz, Teodora Ratiu, Diana Zaiu
The Romanian ROMVOX Text-to-Speech Synthesis System Using a Mixed Time Domain-LPC Pitch Alteration Technique
16:30 - 17:00
Coffee break
17:00 - 17:30
Ivan Kopecek
Speech Synthesis Based on the Composed Syllable Segments
17:30 - 18:00
Dragos Burileanu, Mihai Sima, Corneliu Burileanu, Victor Croitoru
A Neural Network-Based Speaker-Independent System for Word Recognition in Romanian Language
18:00 - 18:30
R. Huber, E. Noeth, A. Batliner, J. Buckow, V. Warnke, H. Niemann
You BEEP Machine - Emotion in Automatic Speech Understanding Systems
Section Text (14:30 - 18:30)
room B
14:30 - 15:00
Milena Slavcheva, Boyanka Zaharieva
TENCO - Automatic Text Encoder
15:00 - 15:30
Jaroslava Hlavacova
Technical Insights into the Birth of the Czech National Corpus
15:30 - 16:00
Karel Pala, Pavel Rychly
Mutual Information in Czech Corpus ESO
16:00 - 16:30
Viatcheslav Iatsko
Textual Deep Structure
16:30 - 17:00
Coffee break
17:00 - 17:30
J. Gareth Evans
Developing a Language Independent Interactive Bible Concordance on the World Wide Web
17:30 - 18:00
Marcelo Finger
Tagging a Morphologically Rich Language
18:00 - 18:30
L. Alfonso Urena, M. De Buenaga, M. Garcia, J. M. Gomez
Adaptation of a Lexical Database in Text Categorization Task
19:30
Welcome Dinner
Thursday, September 24
Section Speech (8:30 - 12:30)
room A
8:30 - 9:00
J. Schalken, L.J.M. Rothkrantz
Dutch Automatic Speech Recognition
9:00 - 9:30
Tomaz Sef, Ales Dobnikar, Matjaz Gams, Zeljko Khermayer
Recent Improvements in Slovene Text-to-Speech System
9:30 - 10:00
Hannes Pirker, Erhard Rank, Harald Trost
Generating Intonation Contours Using Tonal Specifications
10:00 - 10:30
Coffee break
10:30 - 11:00
Zhang Bo
Harmonics Tracking and Sieving-Integrating Algorithm for Robust Speech Recognition
11:00 - 11:30
Petr Horak
The LPC Analysis and Synthesis of F0 Contour
11:30 - 12:00
Pierre Larrey, Nadine Vigouroux, Guy Perennou
Generating Spoken Utterances from Concepts and Prosodic Schemes
Section Dialogue (8:30 - 12:30)
room B
8:30 - 9:00
Jana Krutisova, Vaclav Matousek, Jana Ocelikova
Design and Implementation of a Dialog Manager
9:00 - 9:30
Violeta Quental, Maria Carmelita Padua Dias, Laura Sanchez Garcia
An Interface Language for Dialogues
9:30 - 10:00
Ivo Ipsic, France Mihelic, Simon Dobrisek, Jerneja Gros, Nikola Pavesic
An Overview of the Slovenian Spoken Dialog System
10:00 - 10:30
Coffee break
10:30 - 11:00
Guylaine Gonel, Bernard Levrat
An Approach of Relevance Theory Modeling in Question Answering Systems
11:00 - 11:30
Anton Nijholt Mathieu van den Berk, Arjan van Hessen
A Natural Language Web-based Dialogue System with a Talking Face
11:30 - 12:00
Mare Koit
Developing a Model of Dialog Strategy
12:00 - 12:30
Carine-Alexia Lavelle, Martine de Calmes, Guy Perennou
Users' Behaviours in Spontaneous Oral Dialogue Strategy Design
Section Speech (14:30 - 18:30)
room A
14:30 - 15:00
Hervé Glotin, Frédéric Berthommier, Emmanuel Tessier, Hervé Bourlard
Interfacing of CASA and Multistream Recognition
15:00 - 15:30
Eugen Lupu, Petre Pop and Gavril Toderean
Speaker verification using Vector Quantisation
15:30 - 16:00
L.J.M. Rothkrantz, F. Mohamed-Hoesein, A. Shirzad
An Automated Speech Recognition System for Fast-food Restaurant Applications
16:00 - 16:30
Itshak Voitovetsky, Hugo Guterman, Arnon Cohen
Validity Criterion for Unsupervised Speaker Recognition
16:30 - 17:00
Coffee break
17:00 - 17:30
Ludek Muller and Josef Psutka
Recognition of a Weather Forecast Transmitted by the Czech Radio Broadcasting
17:30 - 18:00
Tanja Schultz and Alex Waibel
Development of Multilingual Acoustic Models in the Global-Phone Project
Section Text (14:30 - 18:30)
room B
14:30 - 15:00
Patrice Lopez
Connection driven parsing of Lexicalized TAG
15:00 - 15:30
Maciej Piasecki, Jerzy Sas
Partial Parsing Method Applied to Rules Acquisition for Medical Expert System
15:30 - 16:00
Eva Hajicova
Prague Dependency Treebank: From analytic to tectogrammatical annotations
16:00 - 16:30
Leo Hadacz
Using TIL for Semantic Analysis of Text
16:30 - 17:00
Coffee break
17:00 - 17:30
Goran Nenadic, Dusko Vitas
Using Local Grammars for Agreement Modeling in Highly Inflective Languages
17:30 - 18:00
Natalia V. Loukachevitch, Boris V. Dobrov
Construction of Structural Thematic Summary of Text
18:00 - 18:30
Pavel Smrz, Ales Horak
Partial Syntactic Analysis as a Tool for Semiautomatic Verb Valencies Acquisition And Checking
20:00
Program Committee meeting
Friday, September 25
Section Speech and Dialogue (8:30 - 10:00)
room A
8:30 - 9:00
Balint Luko
A Voice Dialing System for Mobile Phones
9:00 - 9:30
Ludek Bartek, Robert Batusek, Marek Fikera, Ivan Kopecek
Using Dialog Programming for Developing the
Speech Oriented Hypertext System AUDIS
9:30 - 10:00
Athanasios Koutras, Evangelos Dermatas and George Kokkinakis
Speech Recognition in a Real Room and
Multi-Simultaneous-Speaker environment
Section Text (8:30 - 10:00)
room B
8:30 - 9:00
Petr Sgall
Remarks on Parsing Written and Spoken Discourse
9:00 - 9:30
Pavel Rychly
The Improvement of Common Statistical Measure
9:30 - 10:00
Jan Zizka, Ales Bourek
Classification of Medical Unstructured Text Documents Using the Naive Bayes Algorithm
10:30 - 19:00
Conference trip
10:30 arrival from the hotel Myslivna to the village Krtiny
11:30 excursion to the church in Krtiny and organ concert in the church
12:30 lunch in the hotel Santini
15:00 excursion to the Moravian Karst including visit of one caves system
and visit of the Macocha Ravine
First group - visit of the Punkva caves (the capacity is limited)
Second group - visit of the Catherine cave
19:00 arrival to the hotel Myslivna
19:30
Conference Banquet
Saturday, September 26 (sessions are at the
Faculty of Informatics, MU)
Section Text and Speech (9:00 - 12:00)
room A
9:00 - 9:30
Pavel Smrz, Eva Zackova
New Tools for Disambiguation of Czech Texts
9:30 - 10:00
Ivana Kruijff-Korbayova
Automatic Generation of Instructions in a Multilingual Environment
10:00 - 10:30
Ales Horak
Verb Valency and Semantic Classification of Verbs
10:30 - 11:00
Coffee break
11:00 - 11:30
Dan-Hee Yang, Mansuk Song
How Much Training Data Is Required to
Remove Data Sparseness in Statistical Language Learning?
11:30 - 12:00
Henrique F. Nunes, Edson J. Nagle,
Cairo H. da Silva, Fernando Runstein
Automatic Phonemic Segmentation of Brazilian Portugese Speech Databases
12:00 - 12:30
Vladimir Bergl, Ken Davies, Abraham Ittycheriah, Andrzej Sakrajda
Experience from the Field - Name Dialing en Masse
12:30 - 13:00
Ralf Vollman
The Structure of the Multimedia Database STDB
Section Speech (9:00 - 13:00)
room B
9:00 - 9:30
Jana Kleckova, Vaclav Matousek
Detection of Sentence Types by the Integrated Prosody Module
9:30 - 10:00
Bertjan Busser
TreeTalk-D: a Machine Learning Approach to Dutch Word Pronunciation
10:00 - 10:30
Robert Batusek
Statistics of the Syllable Segments for Speech Synthesis of the Czech Language
10:30 - 11:00
Coffee break
11:00 - 11:30
Jan Zizka, Zdenek Kratochvil, Lubos Popelinsky
Simple Speech Classification Using Automatically Generated Rules
11:30 - 12:00
Vlasta Radova
Design of the Czech National Speech Corpus for Speech Recognition Applications with a Large Vocabulary
12:00 - 12:30
Jiri Hanika, Petr Horak
Epos - A New Approach to the Speech Synthesis
12:30 - 13:00
George Nokas, Evangelos Dermatas and George Kokkinakis
Speech Recognition in Noisy Reverberant Rooms Using Frequency Domain Adaptive Filtering
Section Speech and Dialogue (9:00 - 13:00)
room C
9:00 - 9:30
Juergen Haas, Manuela Boros, Elmar Noeth,
Volker Warnke, Heinrich Niemann
A Concept for a Prosodically and Statistically
Driven Chunky Semantic Parser
9:30 - 10:00
Rachada Kongkachandra, Kreingsak Tamee, Chom Kimpan
Extraction of Intonation in Thai Language
by Karhunen-Loeve Transformation
10:00 - 10:30
Jana Krutisova, Jana Ocelikova, Vaclav Matousek, Pavel Mautner
"Natural Speaking" Information Retrieval Dialog System
10:30 - 11:00
Coffee break
11:00 - 11:30
Pavel Zikovsky, Pavel Slavik
Diphon Voice Synthesis using Fast Fourier Transformation
11:30 - 12:00
Ariane Halber
Partial Parsing and Repairs for Spoken Input
12:00 - 12:30
Tibor Fegyo, Peter Tatai
Cepstral Trajectory Transformation for Subword Recognition
12:30 - 13:00
Taras K. Vintsiuk
Optimal Joint Procedure for Current Pitch
Period Discrimination and Speech Signal
Partition into Quasi-Periodic and Non-Periodic Segments
13:00 - 13:15
Closing of the Workshop
14:30 - 19.00
Program for the participants who will stay until
Sunday (will be specified later).
