Text, Speech and Dialogue: 7th International Conference, TSD 2004, Brno, Czech Republic, September 8-11, 2004, Proceedings (Lecture Notes in Computer Science, 3206)

This Volume Contains The Proceedings Of The 7th International Conference On Text, Speech And Dialogue, Held In Brno, Czech Republic, In September 2004, Under The Auspices Of The Masaryk University. This Series Of International Conferences On Text, Speech And Dialogue Has Come To C- Stitute A Major Forum For Presentation And Discussion, Not Only Of The Latest Developments In Academic Research In These ?elds, But Also Of Practical And Industrial Applications. Uniquely, These Conferences Bring Together Researchers From A Very Wide Area, Both Intellectually And Geographically, Including Scientists Working In Speech Technology, Dialogue Systems, Text Processing, Lexicography, And Other Related ?elds. In Recent Years The Conference Has Dev- Oped Into Aprimary Meetingplacefor Speech And Languagetechnologistsfrom Manydifferent Parts Of The World And In Particular It Has Enabled Important And Fruitful Exchanges Of Ideas Between Western And Eastern Europe. Tsd 2004 Offered A Rich Program Of Invited Talks, Tutorials, Technical Papers And Poster Sessions, Aswellasworkshops Andsystemdemonstrations. Atotalof78paperswereaccepted Out Of 127 Submitted, Contributed Altogether By 190 Authors From 26 Countries. Our Thanks As Usual Go To The Program Committee Members And To The External Reviewers For Their Conscientious And Diligent Assessment Of Submissions, And To The Authors Themselves For Their High-quality Contributions. We Would Also Like To Take This Opportunity To Express Our Appreciation To All The Members Of The Organizing Committee For Their Tireless Efforts In Organizing The Conference And Ensuring Its Smooth Running. Invited Papers -- Speech And Language Processing: Can we use the past to predict the future? -- Common Sense About Word Meaning: Sense In Context -- Scansoft’s Technologies -- Text -- A Positional Linguistics-based System For Word Alignment -- Handling Multi-word Expressions Without explicit linguistic rules in an mt system -- The Szeged Corpus: A Pos Tagged And Syntactically Annotated Hungarian Natural Language Corpus -- Item Summarization In personalisation Of news delivery systems -- Ir-n System, A Passage Retrieval Architecture -- Event Clustering In The News Domain -- Handy: Sign Language Synthesis From Sublexical Elements Based On An Xml Data Representation -- Using Linguistic Resources To construct conceptual graph representation of texts -- Slovak National Corpus -- Grammatical Heads Optimized For Parsing And Their Comparison With Linguistic Intuition -- How Dominant Is The Commonest Sense Of A Word? --^ Pos Tagging Of Hungarian With Combined Statistical And Rule-based Methods -- Grammatical Relations Identification Of Korean Parsed Texts Using Support Vector Machines -- Clustering Abstracts Instead Of Full Texts -- Bayesian Reinforcement For A Probabilistic Neural Net Part-of-speech Tagger -- Automatic Language Identification Using Phoneme And Automatically Derived Unit Strings -- Slovak Text-to-speech Synthesis In Artic System -- Identifying Semantic Roles Using maximum entropy models -- A Lexical Grammatical Implementation Of Affect -- Towards Full Lexical Recognition -- Discriminative Models Of Scfg And Stsg -- Coupling Grammar And Knowledge Base: Range Concatenation Grammars And Description Logics -- Balancing Manual And Automatic Indexing For retrieval of paper abstracts -- Unsupervised Learning Of Rules For morphological disambiguation -- Ambiguous Supertagging Using A Feature Structure --^ A Practical Word Sense Disambiguation System With high performance for korean -- Morphological Tagging Of Russian Texts Of The Xixth Century -- Speech -- Large Vocabulary Continuous Speech Recognition For estonian using morphemes and classes -- A New Classifier For Speaker Verification Based On The Fractional Brownian Motion Process -- A Universal Human Machine Speech Interaction Language For Robust Speech Recognition Applications -- Embedded Viavoice -- New Speech Enhancement Approach For formant evolution detection -- Measurement Of Complementarity Of Recognition Systems -- Text-to-speech For Slovak Language -- Speaker Verification Based On Wavelet Packets -- A Decoding Algorithm For speech input statistical translation -- Aggregation Operators And Hypothesis Space Reductions In speech recognition -- Combinations Of Trap Based Systems -- Automatic Recognition And Evaluation Of tracheoesophageal speech --^ Using Neural Networks To Model Prosody In czech tts system epos -- Auditory Scene Analysis Via Application Of Ica In a time-frequency domain -- Using The Lemmatization Technique For Phonetic Transcription In Text-to-speech System -- Automatic Categorization Of Voicemail Transcripts Using Stochastic Language Models -- Low Latency Real-time Vocal Tract Length Normalization -- Multimodal Phoneme Recognition Of Meeting Data -- A New Multi-modal Database For developing speech recognition systems For an assistive technology application -- Obtaining And Evaluating An Emotional Database For prosody modelling in standard basque -- Fully Automated Approach To Broadcast News Transcription In Czech Language -- A Computational Model Of Intonation For Yorùbá Text-to-speech Synthesis: Design And Analysis -- Dynamic Unit Selection For Very Low Bit Rate Coding At 500 bits/sec -- On The Background Model Construction For speaker verification using gmm --^ A Speaker Clustering Algorithm For Fast Speaker Adaptation In Continuous Speech Recognition -- Advanced Prosody Modelling -- Voice Stress Analysis -- Slovak Speech Database For Experiments And Application Building In Unit-selection Speech Synthesis -- Towards Lower Error Rates In Phoneme Recognition -- Examination Of Pronunciation Variation From Hand-labelled Corpora -- New Refinement Schemes For Voice Conversion -- Acoustic And Linguistic Information Based Chinese Prosodic Boundary Labelling -- F0 Prediction Model Of Speech Synthesis Based on template and statistical method -- An Architecture For Spoken Document Retrieval -- Evaluation Of The Slovenian Hmm-based Speech synthesis system -- Modeling Prosodic Structures In linguistically enriched environments -- Parallel Root-finding Method For Lpc Analysis Of Speech -- Automatic General Letter-to-sound Rules Generation For german text-to-speech system --^ Pitch Accent Prediction From Tobi Annotated Corpora Based on bayesian learning -- Processing Of Logical Expressions For visually impaired users -- Dialogue -- Durational Aspects Of Turn-taking In Spontaneous Face-to-face And Telephone Dialogues -- A Speech Platform For A Bilingual City Information System -- Rapid Dialogue Prototyping Methodology -- Building Voice Applications From Web Content -- Information-providing Dialogue Management -- Realistic Face Animation For A Czech Talking Head -- Evaluation Of A Web Based Information System For Blind And Visually Impaired Students: A Descriptive Study -- Multimodal Dialogue Management -- Looking At The Last Two Turns, I’d Say This Dialogue Is Doomed – Measuring Dialogue Success -- Logical Approach To Natural Language Understanding In a spoken dialogue system -- Building A Dependency-based Grammar For Parsing Informal Mathematical Discourse. Petr Sojka, Ivan Kopeček, Karel Pala (eds.). Includes Bibliographical References And Index. Also Issued Online. Front Matter....Pages - Front Matter....Pages 1-1 Speech and Language Processing: Can We Use the Past to Predict the Future?....Pages 3-13 Common Sense About Word Meaning: Sense in Context....Pages 15-17 ScanSoft’s Technologies....Pages 19-19 Front Matter....Pages 21-21 A Positional Linguistics-Based System for Word Alignment....Pages 23-30 Handling Multi-word Expressions Without Explicit Linguistic Rules in an MT System....Pages 31-40 The Szeged Corpus: A POS Tagged and Syntactically Annotated Hungarian Natural Language Corpus....Pages 41-47 Item Summarization in Personalisation of News Delivery Systems....Pages 49-56 IR-n System, a Passage Retrieval Architecture....Pages 57-64 Event Clustering in the News Domain....Pages 65-72 HANDY: Sign Language Synthesis from Sublexical Elements Based on an XML Data Representation....Pages 73-80 Using Linguistic Resources to Construct Conceptual Graph Representation of Texts....Pages 81-88 Slovak National Corpus....Pages 89-93 Grammatical Heads Optimized for Parsing and Their Comparison with Linguistic Intuition....Pages 95-101 How Dominant Is the Commonest Sense of a Word?....Pages 103-111 POS Tagging of Hungarian with Combined Statistical and Rule-Based Methods....Pages 113-120 Grammatical Relations Identification of Korean Parsed Texts Using Support Vector Machines....Pages 121-128 Clustering Abstracts Instead of Full Texts....Pages 129-135 Bayesian Reinforcement for a Probabilistic Neural Net Part-of-Speech Tagger....Pages 137-145 Automatic Language Identification Using Phoneme and Automatically Derived Unit Strings....Pages 147-153 Slovak Text-to-Speech Synthesis in ARTIC System....Pages 155-162 Front Matter....Pages 21-21 Identifying Semantic Roles Using Maximum Entropy Models....Pages 163-170 A Lexical Grammatical Implementation of Affect....Pages 171-177 Towards Full Lexical Recognition....Pages 179-186 Discriminative Models of SCFG and STSG....Pages 187-194 Coupling Grammar and Knowledge Base: Range Concatenation Grammars and Description Logics....Pages 195-202 Balancing Manual and Automatic Indexing for Retrieval of Paper Abstracts....Pages 203-210 Unsupervised Learning of Rules for Morphological Disambiguation....Pages 211-216 Ambiguous Supertagging Using a Feature Structure....Pages 217-224 A Practical Word Sense Disambiguation System with High Performance for Korean....Pages 225-234 Morphological Tagging of Russian Texts of the XIX th Century....Pages 235-242 Front Matter....Pages 243-243 Large Vocabulary Continuous Speech Recognition for Estonian Using Morphemes and Classes....Pages 245-252 A New Classifier for Speaker Verification Based on the Fractional Brownian Motion Process....Pages 253-259 A Universal Human Machine Speech Interaction Language for Robust Speech Recognition Applications....Pages 261-267 Embedded ViaVoice....Pages 269-274 New Speech Enhancement Approach for Formant Evolution Detection....Pages 275-282 Measurement of Complementarity of Recognition Systems....Pages 283-290 Text-to-Speech for Slovak Language....Pages 291-298 Speaker Verification Based on Wavelet Packets....Pages 299-306 A Decoding Algorithm for Speech Input Statistical Translation....Pages 307-314 Aggregation Operators and Hypothesis Space Reductions in Speech Recognition....Pages 315-322 Front Matter....Pages 243-243 Combinations of TRAP Based Systems....Pages 323-330 Automatic Recognition and Evaluation of Tracheoesophageal Speech....Pages 331-338 Using Neural Networks to Model Prosody in Czech TTS System Epos....Pages 339-345 Auditory Scene Analysis via Application of ICA in a Time-Frequency Domain....Pages 347-353 Using the Lemmatization Technique for Phonetic Transcription in Text-to-Speech System....Pages 355-361 Automatic Categorization of Voicemail Transcripts Using Stochastic Language Models....Pages 363-370 Low Latency Real-Time Vocal Tract Length Normalization....Pages 371-378 Multimodal Phoneme Recognition of Meeting Data....Pages 379-384 A New Multi-modal Database for Developing Speech Recognition Systems for an Assistive Technology Application....Pages 385-392 Obtaining and Evaluating an Emotional Database for Prosody Modelling in Standard Basque....Pages 393-400 Fully Automated Approach to Broadcast News Transcription in Czech Language....Pages 401-408 A Computational Model of Intonation for Yorùbá Text-to-Speech Synthesis: Design and Analysis....Pages 409-416 Dynamic Unit Selection for Very Low Bit Rate Coding at 500 bits/sec....Pages 417-423 On the Background Model Construction for Speaker Verification Using GMM....Pages 425-432 A Speaker Clustering Algorithm for Fast Speaker Adaptation in Continuous Speech Recognition....Pages 433-440 Advanced Prosody Modelling....Pages 441-447 Voice Stress Analysis....Pages 449-456 Slovak Speech Database for Experiments and Application Building in Unit-Selection Speech Synthesis....Pages 457-464 Towards Lower Error Rates in Phoneme Recognition....Pages 465-472 Examination of Pronunciation Variation from Hand-Labelled Corpora....Pages 473-480 Front Matter....Pages 243-243 New Refinement Schemes for Voice Conversion....Pages 481-488 Acoustic and Linguistic Information Based Chinese Prosodic Boundary Labelling....Pages 489-496 F0 Prediction Model of Speech Synthesis Based on Template and Statistical Method....Pages 497-504 An Architecture for Spoken Document Retrieval....Pages 505-511 Evaluation of the Slovenian HMM-Based Speech Synthesis System....Pages 513-520 Modeling Prosodic Structures in Linguistically Enriched Environments....Pages 521-528 Parallel Root-Finding Method for LPC Analysis of Speech....Pages 529-536 Automatic General Letter-to-Sound Rules Generation for German Text-to-Speech System....Pages 537-543 Pitch Accent Prediction from ToBI Annotated Corpora Based on Bayesian Learning....Pages 545-552 Processing of Logical Expressions for Visually Impaired Users....Pages 553-560 Front Matter....Pages 561-561 Durational Aspects of Turn-Taking in Spontaneous Face-to-Face and Telephone Dialogues....Pages 563-570 A Speech Platform for a Bilingual City Information System....Pages 571-578 Rapid Dialogue Prototyping Methodology....Pages 579-586 Building Voice Applications from Web Content....Pages 587-594 Information-Providing Dialogue Management....Pages 595-602 Realistic Face Animation for a Czech Talking Head....Pages 603-610 Evaluation of a Web Based Information System for Blind and Visually Impaired Students: A Descriptive Study....Pages 611-619 Multimodal Dialogue Management....Pages 621-628 Looking at the Last Two Turns, I’d Say This Dialogue Is Doomed – Measuring Dialogue Success....Pages 629-636 Logical Approach to Natural Language Understanding in a Spoken Dialogue System....Pages 637-644 Front Matter....Pages 561-561 Building a Dependency-Based Grammar for Parsing Informal Mathematical Discourse....Pages 645-652 Back Matter....Pages - This volume contains the Proceedings of the 7th International Conference on Text, Speech and Dialogue, held in Brno, Czech Republic, in September 2004, under the auspices of the Masaryk University. This series of international conferences on text, speech and dialogue has come to constitute a major forum for presentation and discussion, not only of the latest developments in academic research in these fields, but also of practical and industrial applications. Uniquely, these conferences bring together researchers from a very wide area, both intellectually and geographically, including scientists working in speech technology, dialogue systems, text processing, lexicography, and other related fields. In recent years the conference has developed into a primary meeting place for speech and language technologists from many different parts of the world and in particular it has enabled important and fruitful exchanges of ideas between Western and Eastern Europe. TSD 2004 offered a rich program of invited talks, tutorials, technical papers and poster sessions, as well as workshops and system demonstrations. A total of 78 papers were accepted out of 127 submitted, contributed altogether by 190 authors from 26 countries. Our thanks as usual go to the Program Committee members and to the external reviewers for their conscientious and diligent assessment of submissions, and to the authors themselves for their high-quality contributions. We would also like to take this opportunity to express our appreciation to all the members of the Organizing Committee for their tireless efforts in organizing the conference and ensuring its smooth running This book constitutes the refereed proceedings of the 7th International Conference on Text, Speech and Dialogue, TSD 2004, held in Brno, Czech Republic, in September 2004. The 78 revised full papers presented together with 3 invited papers were carefully reviewed and selected from 128 submissions. The papers present a wealth of state-of-the-art research results in the field of natural language processing with an emphasis on text, speech, and spoken dialogue ranging from theoretical and methodological issues to applications in various fields, such as information retrieval, the semantic Web, algorithmic learning, classification and clustering, speaker recognition and verification, and dialogue management