13th International Conference on Text, Speech and Dialogue
TSD 2010, Brno, Czech Republic, September 6–10 2010
Topics | Committees | Important Dates | Contact info | Call for Papers
Conference Program

The list of accepted papers with abstracts is available here.

The conference will be held in Hotel Continental, Brno (see the Conference Location page). For technical details see the equipment list.

Monday, September 6, 201015:00 - 17:00RegistrationLounge
Tuesday, September 7, 20108:00 - 9:00RegistrationLounge
9:00 - 9:20Opening SessionHall II
9:20 - 9:45Anoop Deoras and Frederick Jelinek:
Iterative Decoding for Speech Recognition
Hall II
9:45 - 10:45John Carroll:
Parsing and Real-World Applications - invited talk
Hall II
10:45 - 11:15Coffee BreakLounge
11:15 - 12:45Parallel Sessions (2 x 3)Hall II, Hall III
12:45 - 13:45Lunch BreakRestaurant
13:45 - 15:00Poster Session (14)Lounge
15:00 - 16:30Parallel Sessions (2 x 3)Hall II, Hall III
16:30 - 17:00Coffee BreakLounge
17:00 - 18:00Demo SessionComputer Room
19:00 - 21:00Welcome ReceptionRestaurant
Wednesday, September 8, 20109:00 - 10:00Christiane Fellbaum:
Knowledge for Everyman - invited talk
Hall II
10:00 - 10:30Coffee BreakLounge
10:30 - 12:30Parallel Sessions (2 x 4)Hall II, Hall III
12:30 - 13:30Lunch BreakRestaurant
13:30 - 14:30Poster Session (13)Lounge
14:30 - 16:00Parallel Sessions (2 x 3)Hall II, Hall III
16:00 - 16:30Coffee BreakLounge
16:30 - 18:00Program Committee MeetingComputer Room
18:00 - 22:00Guided Tour to Brno (info at Registration)
Thursday, September 9, 201009:00 - 10:30Parallel Sessions (2 x 3)Hall II, Hall III
10:30 - 11:00Coffee BreakLounge
11:00 - 12:30Parallel Sessions (2 x 3)Hall II, Hall III
12:30 - 13:30Lunch BreakRestaurant
13:30 - 24:00Trip and Conference Dinner
Friday, September 10, 20109:30 - 10:30Miroslav Novak:
Evolution of the ASR Decoder Design - invited talk
Hall II
10:30 - 11:00Coffee BreakLounge
11:00 - 12:30Parallel Sessions (2 x 3)Hall III, Hall II
12:30 - 12:45Closing CeremonyHall II
12:45 - 14:00Lunch BreakRestaurant

Tuesday, September 7, 2010
8:00Registration (Lounge)
9:00Opening Session (Hall II)
9:20Anoop Deoras and Frederick Jelinek:
Iterative Decoding for Speech Recognition (Hall II)
chair: Karel Pala
9:45John Carroll:
Parsing and Real-World Applications - invited talk
(Hall II)
chair: Karel Pala
10:45Coffee Break (Lounge)
Parallel Sessions (2 x 3)
Section Text (Hall II)
chair: John Carroll
Section Speech (Hall III)
chair: Frederick Jelinek
11:15Marek Swidzinski and Marcin Wolinski:
Towards a Bank of Constituent Parse Trees for Polish
Zbyněk Zajíc and Lukáš Machlica and Luděk Müller:
Robust Statistic Estimates for Adaptation in the Task of Speech Recognition
11:45Miguel Ballesteros and Jesús Herrera and Virginia Francisco and Pablo Gervás:
Towards an N-version Dependency Parser
Simon Dobrišek and Janez Žibert and France Mihelič:
Towards the Optimal Minimization of a Pronunciation Dictionary Model
12:15Laura Plaza and Elena Lloret and Ahmet Aker:
Improving Automatic Image Captioning Using Text Summarization Techniques
Karel Veselý and Lukáš Burget and František Grézl:
Parallel Training of Neural Networks for Speech Recognition
12:45Lunch Break (Restaurant)
13:45Poster Session (14) (Lounge)
chair: Ales Horak
Raquel Amaro and Sara Mendes and Palmira Marrafa:
Lexical-Conceptual Relations as Qualia Role Encoders
Alin Gavril Chitu and Karin Driel and Leon J. M. Rothkrantz:
Automatic Lip Reading in the Dutch Language Using Active Appearance Models on High Speed Recordings
Amaria Adila Bouabdallah and Tassadit Amghar and Bernard Levrat:
These Nouns that Hide Events: an Initial Detection
Stefan Kombrink and Mirko Hannemann and Lukáš Burget and Hynek Heřmanský:
Recovery of Rare Words in Lecture Speech
Jan Žižka and František Dařena:
Automatic Sentiment Analysis Using the Textual Pattern Content Similarity in Natural Language
Jan Trmal and Aleš Pražák and Zdeněk Loose and Josef Psutka :
Online TV Captioning of Czech Parliamentary Sessions
Vít Baisa:
Towards Disambiguation of Word Sketches
Jan Zelinka and Luboš Šmídl and Jan Trmal and Luděk Müller:
Posterior Estimates and Transforms for Speech Recognition
Sven Hartrumpf and Tim vor der Brück and Christian Eichhorn:
Semantic Duplicate Identification with Parsing and Machine Learning
Jan Švec and Luboš Šmídl:
Prototype of Czech Spoken Dialog System with Mixed Initiative for Railway Information Service
Vladimir Robles and Antonio Molina and Paolo Rosso:
Borda-Based Voting Schemes for Semantic Role Labeling
Andrey Ronzhin and Alexey Karpov and Irina Kipyatkova and Miloš Železný:
Client and Speech Detection System for Intelligent Infokiosk
Alistair Kennedy and Stan Szpakowicz:
Evaluation of a Sentence Ranker for Text Summarization Based on Roget's Thesaurus
Justyna Walkowska:
An NLP-Oriented Analysis of the Instant Messaging Discourse
Parallel Sessions (2 x 3)
Section Speech (Hall II)
chair: Simon Dobrišek
Section Dialogue (Hall III)
chair: Jan Cernocky
15:00Miloš Cerňak:
Diagnostics for Debugging Speech Recognition Systems
Masafumi Nishida and Yasuo Horiuchi and Shingo Kuroiwa and Akira Ichikawa:
Automatic Speech Recognition Based on Multiple Level Units in Spoken Dialogue System for In-Vehicle Appliances
15:30Jozef Ivanecký and Radek Hampl:
Embedded Speech Recognition in UPnP (DLNA) Environment
Ramón López-Cózar and Zoraida Callejas and Nieves Ábalos and Gonzalo Espejo and David Griol:
Using Knowledge about Misunderstandings to Increase the Robustness of Spoken Dialogue Systems
16:00Martin Karafiát and Igor Szoeke and Jan Černocký:
Using Gradient Descent Optimization for Acoustics Training from Heterogeneous Data
Marie Nilsenová and Palesa Nolting:
Linguistic Adaptation in Semi-natural Dialogues: Age Comparison
16:30Coffee Break (Lounge)
17:00Demo Session (Computer Room)
chair: Ales Horak
Polina Ilugdina, Eugene Pakhomov:
ABBYY Lingvo Pro - a global network for building collaborative multilingual tools and resources
Barbora Hladka, Jiri Mirovsky, Pavel Schlesinger:
An On-Line Game Instead of the Annotation Editor
Zuzana Neverilova:
Visualization of VerbaLex Semantic Role Patterns
Ales Horak, Adam Rambousek:
DEB System - Platform for Storage of Digital Knowledge
Vojtech Kovar:
Advanced Features of the Sketch Engine Corpus System
Patrick Hanks:
Corpus Pattern Analysis: new light on words and meanings
Karel Pala, Pavel Smerk:
Internet Language Service
Maciej Piasecki, Michał Marcinzuk, Adam Musiał, Radosław Ramocki, Marek Maziarz:
WordnetLoom: a Graph-based Visual Wordnet Development Framework
Milos Jakubicek, Ales Horak:
Synt - a robust web-enabled parser for Czech
Josef Zizka:
Web-Based Lecture Browser
19:00Welcome Reception (Restaurant)

Wednesday, September 8, 2010
9:00Christiane Fellbaum:
Knowledge for Everyman - invited talk
(Hall II)
chair: Maciej Piasecki
10:00Coffee Break (Lounge)
Parallel Sessions (2 x 4)
Section Speech (Hall II)
chair: Jindrich Matousek
Section Text (Hall III)
chair: Christiane Fellbaum
10:30Marc Le Tallec and Jeanne Villaneau and Jean-Yves Antoine and Agata Savary and Arielle Syssau:
Emologus-A Compositional Model of Emotion Detection Based on the Propositional Content of Spoken Utterances
Róbert Ormándi and István Hegedüs and Richárd Farkas:
Opinion Mining by Transformation-Based Domain Adaptation
11:00Rok Gajšek and Vitomir Štruc and France Mihelič:
Multimodal Emotion Recognition Based on the Decoupling of Emotion and Speaker Information
Miloslav Konopík and Ondřej Rohlík:
Question Answering for Not Yet Semantic Web
11:30Theodoros Kostoulas and Todor Ganchev and Alexandros Lazaridis and Nikos Fakotakis:
Enhancing Emotion Recognition from Speech through Feature Selection
Eduard Bejček and Václava Kettnerová and Markéta Lopatková:
Advanced Searching in the Valency Lexicons Using PML-TQ Search Engine
12:00Iulia Lefter and Leon J. M. Rothkrantz and Pascal Wiggers and David. A. van Leeuwen:
Emotion Recognition from Speech by Combining Databases and Fusion of Classifiers
Silvie Cinková and Martin Holub and Pavel Rychlý and Lenka Smejkalová and Jana Šindlerová:
Can Corpus Pattern Analysis Be Used in NLP?
12:30Lunch Break (Restaurant)
13:30Poster Session (13) (Lounge)
chair: Ivan Kopecek
Raquel Amaro and Sara Mendes and Palmira Marrafa:
Encoding Event and Argument Structures in Wordnets
Selma Yilmazyildiz and Lukas Latacz and Wesley Mattheyses and Werner Verhelst:
Expressive Gibberish Speech Synthesis for Affective Human-Computer Interaction
Zuzana Nevěřilová:
Semantic Role Patterns and Verb Classes in Verb Valency Lexicon
Tiit Hennoste and Olga Gerassimenko and Riina Kasterpalu and Mare Koit and Kirsi Laanesoo and Anni Oja and Andriela Rääbis and Krista Strandson:
The Structure of a Discontinuous Dialogue Formed by Internet Comments
Sofia N. Galicia-Haro and Alexander F. Gelbukh:
Extracting Human Spanish Nouns
Javier Mikel Olaso and María Inés Torres:
Dialogue System Based on EDECÁN Architecture
Michał Marcinczuk and Maciej Piasecki:
Study on Named Entity Recognition for Polish Based on Hidden Markov Models
Nieves Ábalos and Gonzalo Espejo and Ramón López-Cózar and Zoraida Callejas and David Griol :
A Multimodal Dialogue System for an Ambient Intelligent Application in Home Environments
Jan Zelinka and Jan Romportl and Luděk Müller:
A Priori and A Posteriori Machine Learning and Nonlinear Artificial Neural Networks
Josef Psutka and Jan Švec and Josef V. Psutka and Jan Vaněk and Aleš Pražák and Luboš Šmídl:
Fast Phonetic/Lexical Searching in the Archives of the Czech Holocaust Testimonies: Advancing Towards the MALACH Project Visions
Pavel Skrelin and Nina Volskaya and Daniil Kocharov and Karina Evgrafova and Olga Glotova and Vera Evdokimova:
Mari-Liis Kalvik and Meelis Mihkla and Indrek Kiissel and Indrek Hein:
Estonian: Some Findings for Modelling Speech Rhythmicity and Perception of Speech Rate
Jan Hejtmánek :
Using Syllables as Acoustic Units for Spontaneous Speech Recognition
Parallel Sessions (2 x 3)
Section Text (Hall II)
chair: Marketa Lopatkova
Section Speech (Hall III)
chair: Tino Haderlein
14:30Manfred Klenner and Angela Fahrni and Rico Sennrich:
Real Anaphora Resolution is Hard
Jan Vaněk and Josef V. Psutka:
Gender-Dependent Acoustic Models Fusion Developed for Automatic Subtitling of Parliament Meetings Broadcasted by the Czech TV
15:00Martin Popel and David Mareček:
Perplexity of n-gram and Dependency Language Models
Andreas Beschorner and Dietrich Klakow:
Correlation Features and a Linear Transform Specific Reproducing Kernel
15:30Jan Nouza and Jan Silovský:
Adapting Lexical and Language Models for Transcription of Highly Spontaneous Spoken Czech
Yang Sun and Louis ten Bosch and Lou Boves:
Hybrid HMM/BLSTM-RNN for Robust Speech Recognition
16:00Coffee Break (Lounge)
16:30Program Committee Meeting (Computer Room)
18:00Guided Tour to Brno (info at Registration)

Thursday, September 9, 2010
TimeParallel Sessions (2 x 3)
Section Text (Hall II)
chair: Petr Sojka
Section Speech (Hall III)
chair: Miloslav Konopík
09:00Daniel Zeman:
Using TectoMT as a Preprocessing Tool for Phrase-Based Statistical Machine Translation
Jan Trmal and Jan Zelinka and Luděk Müller:
Adaptation of a Feedforward Artificial Neural Network Using a Linear Transform
09:30Václav Procházka and Petr Pollák:
Analysis of Czech Web 1T 5-gram Corpus and its Comparison with Czech National Corpus Data
Pascal Wiggers and Leon J. M. Rothkrantz and Rob van de Lisdonk:
Design and Implementation of a Bayesian Network Speech Recognizer
10:00Roman Kurc and Maciej Piasecki and Stan Szpakowicz:
Automatic Acquisition of Wordnet Relations by Distributionally Supported Morphological Patterns Extracted from Polish Corpora
Tobias Bocklet and Florian Hönig and Tino Haderlein and Florian Stelzle and Christian Knipfer and Elmar Nöth:
Automatic Detection and Evaluation of Edentulous Speakers with Insufficient Dentures
10:30Coffee Break (Lounge)
Parallel Sessions (2 x 3)
Section Speech (Hall II)
chair: Ivan Kopecek
Section Text (Hall III)
chair: Louise Guthrie
11:00Bálint Tóth and Tibor Fegyó and Géza Németh:
Some Aspects of ASR Transcription Based Unsupervised Speaker Adaptation for HMM Speech Synthesis
Anup Kumar Kolya and Asif Ekbal and Sivaji Bandyopadhyay:
Event-Time Relation Identification Using Machine Learning and Rules
11:30Milan Legát and Jindřich Matoušek:
Collection and Analysis of Data for Evaluation of Concatenation Cost Functions
Joe Vasak and Fei Song:
Coverage-Based Methods for Distributional Stopword Selection in Text Segmentation
12:00Jindřich Matoušek:
Automatic Segmentation of Parasitic Sounds in Speech Corpora for TTS Synthesis
Jakub Kanis and Lucie Skorkovská:
Comparison of Different Lemmatization Approaches through the Means of Information Retrieval Performance
12:30Lunch Break (Restaurant)
13:30Trip and Conference Dinner

Friday, September 10, 2010
9:30Miroslav Novak:
Evolution of the ASR Decoder Design - invited talk
(Hall II)
chair: Ivan Kopecek
10:30Coffee Break (Lounge)
Parallel Sessions (2 x 3)
Section Dialogue (Hall III)
chair: Miroslav Novak
Section Speech (Hall II)
chair: Leon Rothkrantz
11:00Jan Ptáček and Pavel Ircing and Miroslav Spousta and Jan Romportl and Zdeněk Loose and Silvie Cinková and José Relaño Gil and Raúl Santos:
Integration of Speech and Text Processing Modules into a Real-Time Dialogue System
Zdeněk Hanzlíček:
Czech HMM-Based Speech Synthesis
11:30David Griol and Michael F. McTear and Zoraida Callejas and Ramón López-Cózar and Nieves Ábalos and Gonzalo Espejo:
A Methodology for Learning Optimal Dialog Strategies
Csaba Zainkó and Tamás Gábor Csapó and Géza Németh:
Special Speech Synthesis for Social Network Websites
12:00Pablo Gervás and Gabriel Amores and Raquel Hervás and Guillermo Pérez and Susana Bautista and Virginia Francisco and Pilar Manchón:
Integrating Aggregation Strategies in an In-Home Domain Dialogue System
Martin Grůber and Jindřich Matoušek :
Listening-Test-Based Annotation of Communicative Functions for Expressive Speech Synthesis
12:30Closing Ceremony (Hall II)
12:45Lunch Break (Restaurant)

TSD 2009 | TSD 2008 | TSD 2007