Text, Speech and Dialogue : Second International Workshop, TSD '99, Plzen, Czech Republic, September 13-17, 1999, Proceedings

by Tsd'9 1999 (Plzen, Czech Republic); Mautner, Pavel; Ocelikova, J.; Sojka, Petr; Carbonell, J. G.

• ISBN13: 9783540664949
• ISBN10: 3540664947
• Format: Paperback
• Copyright: 1999-06-01
• Publisher: Springer Verlag

Summary

This book constitutes the refereed proceedings of the Second International Workshop on Text, Speech and Dialogue, TSD'99, held in Plzen, Czech Republic in September 1999. The 57 revised full papers and 19 posters presented were carefully reviewed and selected for inclusion in the book. The book presents state-of-the-art research and technology in the field of natural language processing with emphasis on text, speech, and spoken dialogue.

Table of Contents

Invited Talks
Research Issues for the Next Generation Spoken Dialogue Systems	p. 1
Data-Driven Analysis of Speech	p. 10
Towards a Road Map for Machine Translation Research	p. 19
The Prague Dependency Treebank: Crossing the Sentence Boundary	p. 20
Text
Tiered Tagging and Combined Language Models Classifiers	p. 28
Syntactic Tagging	p. 34
Information, Language, Corpus and Linguistics	p. 39
Prague Dependency Treebank: Restoration of Deletions	p. 44
Some Types of Syntactic Ambiguity	p. 50
Semantic Annotation of (Czech) Corpus Texts	p. 56
The General Principles of the Diachronic Part of the Czech National Corpus	p. 62
Performing Adaptive Morphological Analysis Using Internet Resources	p. 66
Automatic Text-to-Speech Alignment: Aspects of Robustification	p. 72
Czech Translation of G. Orwell's `1984': Morphology and Syntactic Patterns in the Corpus	p. 77
Handling Word Order in a Multilingual System for Generation of Instructions	p. 83
Text Structuring in a Multilingual System for Generation of Instructions	p. 89
Leveraging Syntactic Information for Text Normalization	p. 95
Automatic Structuring of Written Texts	p. 101
Implementation of Efficient and Portable Parser for Czech	p. 105
Word Sense Disambiguation of Czech Texts	p. 109
The Acquisition of Some Lexical Constraints from Corpora	p. 115
Run-Time Extensible (Semi-)Top-Down Parser	p. 121
Enhancing Readability of Automatic Summaries by Using Schemas	p. 127
Use of a Weighted Topic Hierarchy for Document Classification	p. 133
Speech
Remarks on Sentence Prosody and Topic-Focus Articulation	p. 139
Speech Recognition Using Elman Neural Networks	p. 146
Use of Hidden Markov Models for Evaluation of Russian Digits Pronunciation by the Foreigners	p. 152
Allophone-Based Concatenative Speech Synthesis System for Russian	p. 156
Intonation Questions in English and Armenian: Results of the Perceptual Study	p. 160
Methods of Sentences Selection for Read-Speech Corpus Design	p. 165
Speaker Identification Using Discriminative Centroids Weighting - A Growing Cell Structure Approach	p. 171
Speech Analysis and Recognition Synchronised by One-Quasiperiodical Segmentation	p. 175
Spanish Phoneme Classification by Means of a Hierarchy of Kohonen Self-Organizing Maps	p. 181
Information Theoretic Based Segments for Language Identification	p. 187
Fast and Robust Features for Prosodic Classification	p. 193
A Segment Based Approach for Prosodic Boundary Detection	p. 199
Speech Recognition and Syllable Segments	p. 203
Text Preprocessing for Czech Speech Synthesis	p. 209
MLPs and Mixture Models for the Estimation of the Posterior Probabilities of Class Membership	p. 215
A Simple Spanish Part of Speech Tagger for Detection and Correction of Accentuation Error	p. 219
Slovene Interactive Text-to-Speech Evaluation Site - SITES	p. 223
Developing HMM-Based Recognizers with ESMERALDA	p. 229
Large Vocabulary Speech Recognition for Read and Broadcast Czech	p. 235
Rules for Automatic Grapheme-to-Allophone Transcription in Slovene	p. 241
Speech Segmentation Aspects of Phone Transition Acoustical Modelling	p. 248
Context Dependent Phoneme Recognition	p. 252
State-Space Model Based Labeling of Speech Signals	p. 258
Very Low Bit Rate Speech Coding: Comparison of Data-Driven Units with Syllable Segments	p. 262
Storing Prosody Attributes of Spontaneous Speech	p. 268
Dialogue
An Overview of the State of the Art of Coding Schemes for Dialogue Act Annotation	p. 274
Structural and Semantic Dialogue Filters	p. 280
A Retrieval System of Broadcast News Speech Documents through Keyboard and Voice	p. 286
Situations in Dialogs	p. 290
Components for Building an Automatic Voice-Dialogue Telephone System	p. 296
Modeling of the Information Retrieval Dialogue Systems	p. 302
Improvement of the Recognition Rate of Spoken Queries to the Dialogue System	p. 308
Analysis of Different Dialog Strategies in the Slovenian Spoken Dialog System	p. 315
Posters
Dispersion of Words in a Language Corpus	p. 321
Corpus-Based Rules for Czech Verb Discontinuous Constituents	p. 325
Automatic Modelling of Regional Pronunciation Variation for Russian	p. 329
Experiments Regarding the Superposition of Emotional Features on Neutral Korean Speech	p. 333
Modeling Cue Phrases in Turkish: A Case Study	p. 337
Speaker Identification Based on Vector Quantization	p. 341
Robustness in Tabular Deduction for Multimodal Logical Grammar - Part 1	p. 345
Classifying Visemes for Automatic Lipreading	p. 349
Semantic Inference in the Human-Machine Communication	p. 353
Playing with RST: Two Algorithms for the Automated Manipulation of Discourse Trees	p. 357
Another Step in the Modeling of Basque Intonation: Bermeo	p. 361
Electronic Dictionaries: For Both Humans and Computers	p. 365
Statistical Evaluation of Similarity Measures on Multi-lingual Text Corpora	p. 369
Document Title Patterns in Information Retrieval	p. 372
Statistical Approach to the Automatic Synthesis of Czech Speech	p. 376
Language Model Representations for the GOPOLIS Database	p. 380
Recognition of Alkohol Influence on Speech	p. 384
Recording of Czech and Slovak Telephone Databases within SpeechDat-E	p. 388
Pragmatic Features of the Electronic Discourse in the Internet	p. 392
Author Index	p. 395
Table of Contents provided by Publisher. All Rights Reserved.