@Proceedings{nlp:tsd2003proceedings, title = {{Proceedings of the 6th International Conference on Text, Speech and Dialogue---TSD 2003}}, series= "Lecture Notes in Artificial Intelligence LNCS/LNAI 2807", year = 2003, editor = {V{\'a}clav Matou{\v s}ek and Pavel Mautner}, address = {{\v C}esk{\'e} Bud\v{e}jovice, Czech Republic}, month = Sep, pages = {xiii + 426}, publisher = {Springer-Verlag}, isbnnote = {ISBN 3-540-20024-X}, annote = {This book constitutes the refereed proceedings of the 4th International Conference on Text, Speech and Dialogue, held in {\v C}esk{\'e} Bud{\v e}jovice, Czech Republic, in September 2003. The 60 contributed papers are organized in the three areas of Natural Language Processing: Text, Speech and Dialogue. Written for researchers and advanced students.}, keywords = {Natural Language Processing, NLP, Speech Processing, Information Retrieval, Information Extraction, Speech Recognition, Spoken Dialogue, User Interfaces, Speech Perception, Text Processing, Statistical Methods, Algorithmic Learning, Semantic Web} } @InProceedings{nlp:tsd2003proc1, title = "{Combating the Sparse Data Problem of Language Modelling}", pages = {1--1}, author = {Frederick Jelinek}, crossref = {nlp:tsd2003proceedings}, } @InProceedings{nlp:tsd2003proc2, title = "{Toward Robust Speech Recognition and Understanding}", pages = {2--11}, author = {Sadaoki Furui}, crossref = {nlp:tsd2003proceedings}, } @InProceedings{nlp:tsd2003proc12, title = "{A Pilot Study of English Selectional Preferences and their Cross-Lingual Compatibility with Basque}", pages = {12--19}, author = {Eneko Agirre and Izaskun Aldezabal and Eli Pociello}, crossref = {nlp:tsd2003proceedings}, } @InProceedings{nlp:tsd2003proc20, title = "{Auto-Tagging of Text Documents into XML}", pages = {20--26}, author = {Shazia Akhtar and Ronan G. Reilly and John Dunnion}, crossref = {nlp:tsd2003proceedings}, } @InProceedings{nlp:tsd2003proc27, title = "{Stable Coordinated Pairs in Text Processing}", pages = {27--34}, author = {Igor A. Bolshakov and Alexander Gelbukh and Sof{\'\i }a N. Galicia-Haro}, crossref = {nlp:tsd2003proceedings}, } @InProceedings{nlp:tsd2003proc35, title = "{Backoff DOP: Parameter Estimation by Backoff}", pages = {35--42}, author = {Luciano Buratto and Khalil Sima'an}, crossref = {nlp:tsd2003proceedings}, } @InProceedings{nlp:tsd2003proc43, title = "{Document Clustering into an Unknown Number of Clusters Using a Genetic Algorithm}", pages = {43--49}, author = {A. Casillas and M. T. Gonz{\'a}lez de Lena and R. Mart{\'i}nez}, crossref = {nlp:tsd2003proceedings}, } @InProceedings{nlp:tsd2003proc50, title = "{Experiments in German Treebank Parsing}", pages = {50--57}, author = {Sisay Fissaha and Daniel Olejnik and Ralf Kornberger and Karin M{\"u}ller and Detlef Prescher}, crossref = {nlp:tsd2003proceedings}, } @InProceedings{nlp:tsd2003proc58, title = "{A Theoretical Basis of an Architecture of a Shell of a Reasonably Robust Syntactic Analyser}", pages = {58--65}, author = {Tom{\'a}{\v s} Holan and Vladislav Kubo{\v n} and Martin Pl{\'a}tek and Karel Oliva}, crossref = {nlp:tsd2003proceedings}, } @InProceedings{nlp:tsd2003proc66, title = "{Si3Trenn and Si3Silb: Using the SiSiSi Word Analysis System for Pre-Hyphenation and Syllable Counting in German Documents}", pages = {66--73}, author = {Gabriele Kodydek and Martin Sch{\"o}nhacker}, crossref = {nlp:tsd2003proceedings}, } @InProceedings{nlp:tsd2003proc74, title = "{Detecting Annotation Errors in a Corpus by Induction of Syntactic Patterns}", pages = {74--81}, author = {Miloslav Nepil}, crossref = {nlp:tsd2003proceedings}, } @InProceedings{nlp:tsd2003proc82, title = "{The Computational Complexity of Rule-Based Part-of-Speech Tagging}", pages = {82--89}, author = {Karel Oliva and Pavel Kv{\v e}to{\v n} and Roman Ondru{\v s}ka}, crossref = {nlp:tsd2003proceedings}, } @InProceedings{nlp:tsd2003proc90, title = "{Text Corpus with Errors}", pages = {90--97}, author = {Karel Pala and Pavel Rychl{\'y} and Pavel Smr{\v z}}, crossref = {nlp:tsd2003proceedings}, } @InProceedings{nlp:tsd2003proc98, title = "{Identification of Multiwords as Preprocessing for Automatic Extraction of Lexical Similarities}", pages = {98--105}, author = {Aristomenis Thanopoulos and Nikos Fakotakis and George Kokkinakis}, crossref = {nlp:tsd2003proceedings}, } @InProceedings{nlp:tsd2003proc106, title = "{Build a Large-Scale Syntactically Annotated Chinese Corpus}", pages = {106--113}, author = {Qiang Zhou}, crossref = {nlp:tsd2003proceedings}, } @InProceedings{nlp:tsd2003proc114, title = "{Computational Benefits of a Totally Lexicalist Grammar}", pages = {114--119}, author = {Kata Balogh and Judit Kleiber}, crossref = {nlp:tsd2003proceedings}, } @InProceedings{nlp:tsd2003proc120, title = "{Using a Czech Valency Lexicon for Annotation Support}", pages = {120--125}, author = {V{\'a}clav Honetschl{\"a}ger}, crossref = {nlp:tsd2003proceedings}, } @InProceedings{nlp:tsd2003proc126, title = "{On Concept Based Approach for Determining Semantic Index Terms}", pages = {126--131}, author = {Bo-Yeong Kang and Sang-Jo Lee}, crossref = {nlp:tsd2003proceedings}, } @InProceedings{nlp:tsd2003proc132, title = "{Corpora Issues in Validation of Serbian Wordnet}", pages = {132--137}, author = {Cvetana Krstev and Gordana Pavlovi{\'c}-La{\v z}eti{\'c} and Ivan Obradovi{\'c} and Du{\v s}ko Vitas}, crossref = {nlp:tsd2003proceedings}, } @InProceedings{nlp:tsd2003proc138, title = "{Optimising Attribute Selection in Conversational Search}", pages = {138--145}, author = {Dario Teixeira and Wim Verhaegh}, crossref = {nlp:tsd2003proceedings}, } @InProceedings{nlp:tsd2003proc146, title = "{Russian Corpus of the 19th Century}", pages = {146--151}, author = {Victor Zakharov}, crossref = {nlp:tsd2003proceedings}, } @InProceedings{nlp:tsd2003proc152, title = "{On Homogeneous Segments}", pages = {152--157}, author = {Robert Bat{\r u}{\v s}ek and Ivan Kope{\v c}ek and Anton{\'i}n Ku{\v c}era}, crossref = {nlp:tsd2003proceedings}, } @InProceedings{nlp:tsd2003proc158, title = "{Advances in Automatic Speech Recognitionby Imitating Spreading Activation}", pages = {158--164}, author = {Stefan Bordag and Denisa Bordag}, crossref = {nlp:tsd2003proceedings}, } @InProceedings{nlp:tsd2003proc165, title = "{The Incorporation of Confidence Measures to Language Understanding}", pages = {165--172}, author = {Fernando Garc{\'i}a and Llu{\'i}s Hurtado and Emilio Sanchis and Encarna Segarra}, crossref = {nlp:tsd2003proceedings}, } @InProceedings{nlp:tsd2003proc173, title = "{Speech Recognition with $\mu$-Law Companded Features on Reverberated Signals}", pages = {173--180}, author = {Tino Haderlein and Georg Stemmer and Elmar N{\"o}th}, crossref = {nlp:tsd2003proceedings}, } @InProceedings{nlp:tsd2003proc181, title = "{Understanding Speech Based on a Bayesian Concept Extraction Method}", pages = {181--188}, author = {Salma Jamoussi and Kamel Sma{\"\i}li and Jean-Paul}, crossref = {nlp:tsd2003proceedings}, } @InProceedings{nlp:tsd2003proc189, title = "{A Data-Driven Framework for Intonational Phrase Break Prediction}", pages = {189--197}, author = {M. Maragoudakis and P. Zervas and N. Fakotakis and G. Kokkinakis}, crossref = {nlp:tsd2003proceedings}, } @InProceedings{nlp:tsd2003proc198, title = "{Phoneme Recognition Using Temporal Patterns}", pages = {198--205}, author = {Pavel Mat{\v e}jka and Petr Schwarz and Hynek Hermansky and Jan {\v C}ernock{\'y}}, crossref = {nlp:tsd2003proceedings}, } @InProceedings{nlp:tsd2003proc206, title = "{Multi-array Multi-speaker Tracking}", pages = {206--213}, author = {Ilyas Potamitis and George Tremoulis and Nikos Fakotakis}, crossref = {nlp:tsd2003proceedings}, } @InProceedings{nlp:tsd2003proc214, title = "{Towards Automatic Transcription of Spontaneous Czech Speech in the MALACH Project}", pages = {214--219}, author = {Josef Psutka and Pavel Ircing and Josef V. Psutka and Vlasta Radov{\'a} and William Byrne and Veera Venkataramani and Jan Haji{\v c} and Samuel Gustman}, crossref = {nlp:tsd2003proceedings}, } @InProceedings{nlp:tsd2003proc220, title = "{TERSEO: Temporal Expression Resolution System Applied to Event Ordering}", pages = {220--228}, author = {E. Saquete and R. Mu{\~n}oz and P. Mart{\'\i}nez-Barco}, crossref = {nlp:tsd2003proceedings}, } @InProceedings{nlp:tsd2003proc229, title = "{Non-Native Pronunciation Variants of City Names as a Problem for Speech Technology Applications}", pages = {229--236}, author = {Stefan Schaden}, crossref = {nlp:tsd2003proceedings}, } @InProceedings{nlp:tsd2003proc237, title = "{Improving Speech Recognition by Utilizing Domain Knowledge and Confidence Measures}", pages = {237--244}, author = {Pascal Wiggers and Leon J. M. Rothkrantz}, crossref = {nlp:tsd2003proceedings}, } @InProceedings{nlp:tsd2003proc245, title = "{Comparison of Acoustic Adaptation Methods in Multilingual Speech Recognition Environment}", pages = {245--250}, author = {Andrej {\v Z}gank and Zdravko Ka{\v c}i{\v c} and Bogomir Horvat}, crossref = {nlp:tsd2003proceedings}, } @InProceedings{nlp:tsd2003proc251, title = "{A Comparison of Unit Selection Techniques in Limited Domain Speech Synthesis}", pages = {251--256}, author = {Robert Bat{\r u}{\v s}ek and Pavel Gaura}, crossref = {nlp:tsd2003proceedings}, } @InProceedings{nlp:tsd2003proc257, title = "{Recognition of Speech with Non-Random Attributes}", pages = {257--262}, author = {Luk{\'a}{\v s} Burget and Jan {\v C}ernock{\'y}}, crossref = {nlp:tsd2003proceedings}, } @InProceedings{nlp:tsd2003proc263, title = "{Text-Independent Speaker Verification: the WCL-1 System}", pages = {263--268}, author = {Todor Ganchev and Nikos Fakotakis and George Kokkinakis}, crossref = {nlp:tsd2003proceedings}, } @InProceedings{nlp:tsd2003proc269, title = "{Local Time-frequency Operators in TRAPs for Speech Recognition}", pages = {269--274}, author = {Franti{\v s}ek Gr{\'e}zl}, crossref = {nlp:tsd2003proceedings}, } @InProceedings{nlp:tsd2003proc275, title = "{Entropy and Dynamism Criteria for Speech and Audio Classification Applications}", pages = {275--280}, author = {Igor E. Kheidorov and Hanna M. Lukashevich and Denis L. Mitrofanov}, crossref = {nlp:tsd2003proceedings}, } @InProceedings{nlp:tsd2003proc281, title = "{Speech Production: Phonetic Encodingof Real and Non-words}", pages = {281--286}, author = {Jana Kle{\v c}kov{\'a}}, crossref = {nlp:tsd2003proceedings}, } @InProceedings{nlp:tsd2003proc287, title = "{Experiments with Automatic Segmentation for Czech Speech Synthesis}", pages = {287--294}, author = {Jind{\v r}ich Matou{\v s}ek and Daniel Tihelka and Josef Psutka}, crossref = {nlp:tsd2003proceedings}, } @InProceedings{nlp:tsd2003proc295, title = "{All-Pole Modeling for Definition of Speech Features in Aurora3 DSR Task}", pages = {295--300}, author = {Petr Motl{\'\i}{\v c}ek and Jan {\v C}ernock{\'y}}, crossref = {nlp:tsd2003proceedings}, } @InProceedings{nlp:tsd2003proc301, title = "{Building of a Vocabulary for the Automatic Voice-Dictation System}", pages = {301--308}, author = {Dana Nejedlov{\'a} and Jan Nouza}, crossref = {nlp:tsd2003proceedings}, } @InProceedings{nlp:tsd2003proc309, title = "{Real-Time Vocal Tract Length Normalizationin a Phonological Awareness Teaching System}", pages = {309--314}, author = {D{\'e}nes Paczolay and Andr{\'a}s Kocsor and L{\'a}szl{\'o} T{\'o}th}, crossref = {nlp:tsd2003proceedings}, } @InProceedings{nlp:tsd2003proc315, title = "{Hard-Testing the Multi-Stream Approach to Automatic Speech Recognition}", pages = {315--320}, author = {Vitor Pera and Jean-Pierre Martens}, crossref = {nlp:tsd2003proceedings}, } @InProceedings{nlp:tsd2003proc321, title = "{Pitch-synchronous Speech Signal Segmentationand its Applications}", pages = {321--326}, author = {Valery A. Petrushin}, crossref = {nlp:tsd2003proceedings}, } @InProceedings{nlp:tsd2003proc327, title = "{Building LVCSR System for Transcriptionof Spontaneously Pronounced Russian Testimoniesin the MALACH Project: Initial Steps and First Results}", pages = {327--332}, author = {Josef Psutka and Ilja Iljuchin and Pavel Ircing and Josef V. Psutka and V{\'a}clav Trejbal and William Byrne and Jan Haji{\v c} and Samuel Gustman}, crossref = {nlp:tsd2003proceedings}, } @InProceedings{nlp:tsd2003proc333, title = "{The Phase Substitutions in Czech Harmonic Concatenative Speech Synthesis}", pages = {333--340}, author = {Zbyn{\v e}k Tychtl and Karel Matou{\v s}}, crossref = {nlp:tsd2003proceedings}, } @InProceedings{nlp:tsd2003proc341, title = "{Combining Task Descriptions and Ontological Knowledge for Adaptive Dialogue}", pages = {341--348}, author = {Martin Beveridge and David Milward}, crossref = {nlp:tsd2003proceedings}, } @InProceedings{nlp:tsd2003proc349, title = "{Large Text and Audio Data Alignment for Multimedia Applications}", pages = {349--356}, author = {Konstantin Biatov}, crossref = {nlp:tsd2003proceedings}, } @InProceedings{nlp:tsd2003proc357, title = "{Building Multilingual Speech Corpora from Interpreted Spontaneous Dialogues on the Net}", pages = {357--364}, author = {Georges Fafiotte}, crossref = {nlp:tsd2003proceedings}, } @InProceedings{nlp:tsd2003proc365, title = "{Multi-Modal Voice Application Designin a Multi-Client Environment}", pages = {365--371}, author = {Jozef Ivaneck{\'y} and Markus Klehr and Volker Fischer and Siegfried Kunzmann}, crossref = {nlp:tsd2003proceedings}, } @InProceedings{nlp:tsd2003proc372, title = "{User Modeling and Plan Recognition under Conditions of Uncertainty}", pages = {372--379}, author = {Manolis Maragoudakis and Aristomenis Thanopoulos and Nikos Fakotakis}, crossref = {nlp:tsd2003proceedings}, } @InProceedings{nlp:tsd2003proc380, title = "{Bilingual Speech Recognition for a Weather Information Retrieval Dialogue System}", pages = {380--387}, author = {Sanda Martin{\v c}i{\'c}-Ip{\v s}i{\'c} and Janez {\v Z}ibert and Ivo Ip{\v s}i{\'c} and France Miheli{\v c} and Nikola Pave{\v s}i{\'c}}, crossref = {nlp:tsd2003proceedings}, } @InProceedings{nlp:tsd2003proc388, title = "{On the Use of Prosodic Labelling in Corpus-Based Linguistic Studies of Spontaneous Speech}", pages = {388--393}, author = {Daniela Braga and Diamantino Freitas and Joao Paulo Teixeira and Aldina Marques}, crossref = {nlp:tsd2003proceedings}, } @InProceedings{nlp:tsd2003proc394, title = "{A Multi-modal Eliza Using Natural Language Processing and Emotion Recognition}", pages = {394--399}, author = {Siska Fitrianie and Pascal Wiggers and Leon J. M. Rothkrantz}, crossref = {nlp:tsd2003proceedings}, } @InProceedings{nlp:tsd2003proc400, title = "{The Wizard of Oz System for Weather Information Retrieval}", pages = {400--405}, author = {Melita Hajdinjak and France Miheli{\v c}}, crossref = {nlp:tsd2003proceedings}, } @InProceedings{nlp:tsd2003proc406, title = "{Directives in Estonian Information Dialogues}", pages = {406--411}, author = {Tiit Hennoste and Mare Koit and Andriela R{\"a}{\"a}bis and Krista Strandson and Maret Valdisoo and Evely Vutt}, crossref = {nlp:tsd2003proceedings}, } @InProceedings{nlp:tsd2003proc412, title = "{SpeechDat-like Estonian Database}", pages = {412--417}, author = {Einar Meister and J\"urgen Lasn and Lya Meister}, crossref = {nlp:tsd2003proceedings}, } @InProceedings{nlp:tsd2003proc418, title = "{Dialogue Experiment for Elderly Peoplein Home Health Care System}", pages = {418--423}, author = {{Shin-ya} Takahashi and Tsuyoshi Morimoto and Sakashi Maeda and Naoyuki Tsuruta}, crossref = {nlp:tsd2003proceedings}, }