Text, Speech and Dialogue: 10th International Conference, TSD 2007, Pilsen, Czech Republic, September 3-7, 2007, ProceedingsVáclav Matoušek, Pavel Mautner This book constitutes the refereed proceedings of the 10th International Conference on Text, Speech and Dialogue, TSD 2007, held in Pilsen, Czech Republic, in September 2007. The 80 revised full papers presented in this volume cover 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. |
Contents
Language Modeling with Linguistic Cluster Constraints | 1 |
Some of Our Best Friends Are Statisticians | 2 |
Some Special Problems of Speech Communication | 11 |
Recent Advances in Spoken Language Understanding | 14 |
TransformationBased Tectogrammatical Dependency Analysis of English | 15 |
Multilingual Name Disambiguation with Semantic Information | 23 |
Inducing Classes of Terms from Text | 31 |
Accurate Unlexicalized Parsing for Modern Hebrew | 39 |
Organization | vii |
Table of Contents | xi |
Language Modeling with Linguistic Cluster Constraints | 1 |
Some of Our Best Friends Are Statisticians | 2 |
Some Special Problems of Speech Communication | 11 |
Recent Advances in Spoken Language Understanding | 14 |
TransformationBased Tectogrammatical Dependency Analysis of English | 15 |
Multilingual Name Disambiguation with Semantic Information | 23 |
Disambiguation of the Neuter Pronoun and Its Effect on Pronominal Coreference Resolution | 48 |
Constructing a Large Scale Text Corpus Based on the Grid and Trustworthiness | 56 |
Disambiguating Hypernym Relations for Rogets Thesaurus | 66 |
A Comparison | 76 |
Automatic Word Clustering in Russian Texts | 85 |
Feature Engineering in Maximum Spanning Tree Dependency Parser | 92 |
Automatic Selection of Heterogeneous Syntactic Features in Semantic Similarity of Polish Nouns | 99 |
Bilingual News Clustering Using Named Entities and Fuzzy Similarity | 107 |
Comparing Strategies for European Portuguese | 115 |
On the Evaluation of Korean WordNet | 123 |
An Adaptive Keyboard with Personalized LanguageBased Features | 131 |
An AllPath Parsing Algorithm for ConstraintBased Dependency Grammars of CFPower | 139 |
Word Distribution Based Methods for Minimizing Segment Overlaps | 147 |
On the Relative Hardness of Clustering Corpora | 155 |
Indexing and Retrieval Scheme for ContentBased Multimedia Applications | 162 |
Automatic Diacritic Restoration for ResourceScarce Languages | 170 |
Lexical and Perceptual Grounding of a Sound Ontology | 180 |
Annotating Data and Developing NE Tagger | 188 |
Identifying Expressions of Emotion in Text | 196 |
Authoring Language for Embodied Conversational Agents | 206 |
Dynamic Adaptation of Language Models in Speech Driven Information Retrieval | 214 |
WhiteningBased Feature Space Transformations in a Speech Impediment Therapy System | 222 |
Linguistic Annotations and Translation Units | 230 |
An Automatic Version of the PostLaryngectomy Telephone Test | 238 |
Speaker Normalization Via Springy Discriminant Analysis and Pitch Estimation | 246 |
A Study on Speech with Manifest Emotions | 254 |
Speech Recognition Supported by Prosodic Information for Fixed Stress Languages | 262 |
TRAPBased Techniques for Recognition of Noisy Speech | 270 |
Quantification of Speech Intelligibility by ASR and Prosody | 278 |
Appositions Versus Double Subject Sentences What Information the Speech Analysis Brings to a Grammar Debate | 286 |
Automatic Evaluation of Pathologic Speech from Research to Routine Clinical Use | 294 |
From 10xRT to 1xRT | 302 |
LogicBased Rhetorical Structuring for Natural Language Generation in HumanComputer Dialogue | 309 |
TextIndependent Speaker Identification Using Temporal Patterns | 318 |
Recording and Annotation of Speech Corpus for Czech Unit Selection Speech Synthesis | 326 |
SkToBI Scheme for Phonological Prosody Annotation in Slovak | 334 |
Towards Automatic Transcription of Large Spoken Archives in Agglutinating Languages Hungarian ASR for the MALACH Project | 342 |
Nonuniform SpeechAudio Coding Exploiting Predictability of Temporal Evolution of Spectral Envelopes | 350 |
Towards Conversational Speech | 358 |
Exploratory Analysis ofWord Use and Sentence Length in the Spoken Dutch Corpus | 366 |
Design of Tandem Architecture Using Segmental Trend Features | 374 |
An Automatic Retraining Method for Speaker Independent Hidden Markov Models | 382 |
User Modeling to Support the Development of an Auditory Help System | 390 |
Fast Discriminant Training of Semicontinuous HMM | 398 |
SpeechMusic Discrimination Using MelCepstrum Modulation Energy | 406 |
Parameterization of the Input in Training the HVS Semantic Parser | 415 |
A Comparison Using Different Speech Parameters in the Automatic Emotion Recognition Using Feature Subset Selection Based on Evolutionary Alg... | 423 |
Benefit of Maximum Likelihood Linear Transform MLLT Used at Different Levels of Covariance Matrices Clustering in ASR Systems | 431 |
Information Retrieval Test Collection for Searching Spontaneous Czech Speech | 439 |
Interspeaker Synchronization in Audiovisual Database for LipReadable Speech to Animation Conversion | 447 |
Constructing Empirical Models for Automatic Dialog Parameterization | 455 |
The Effect of Lexicon Composition in Pronunciation by Analogy | 464 |
A Sinhala TexttoSpeech System | 472 |
Voice Conversion Based on Probabilistic Parameter Transformation and Extended Interspeaker Residual Prediction | 480 |
Automatic Czech Sign Speech Translation | 488 |
Maximum Likelihood and Maximum Mutual Information Training in Gender and Age Recognition System | 496 |
Pitch Marks at Peaks or Valleys? | 502 |
Quality Deterioration Factors in Unit Selection Speech Synthesis | 508 |
TopicFocus Articulation Algorithm on the SyntaxProsody Interface of Romanian | 516 |
Translation and Conversion for Czech Sign Speech Synthesis | 524 |
AWizardofOz System Evaluation Study | 532 |
New Measures for OpenDomain Question Answering Evaluation Within a Time Constraint | 540 |
A Methodology for Domain Dialogue Engineering with the Midiki Dialogue Manager | 548 |
The Intonational Realization of Requests in Polish TaskOriented Dialogues | 556 |
Analysis of Changes in Dialogue Rhythm Due to Dialogue Acts in TaskOriented Dialogues | 564 |
Recognition and Understanding Simulation for a Spoken Dialog Corpus Acquisition | 574 |
First Approach in the Development of Multimedia Information Retrieval Resources for the Basque Context | 582 |
The Weakest Link | 591 |
A Spoken Dialog System for ChatLike Conversations Considering Response Timing | 599 |
A Prosodically Annotated Corpus of Czech Television Debates | 607 |
Setting Layout in Dialogue Generating Web Pages | 613 |
GraphBased Answer Fusion in Multilingual Question Answering | 621 |
Using QueryRelevant Documents Pairs for CrossLingual Information Retrieval | 630 |
Detection of Dialogue Acts Using PerplexityBased Word Clustering | 638 |
Dialogue Management for Intelligent TV Based on Statistical Learning Method | 644 |
MultipleTaxonomy Question Classification for Category Search on Faceted Information | 653 |
Author Index | 661 |
Title Page | iii |
Preface | vi |
Inducing Classes of Terms from Text | 31 |
Accurate Unlexicalized Parsing for Modern Hebrew | 39 |
Disambiguation of the Neuter Pronoun and Its Effect on Pronominal Coreference Resolution | 48 |
Constructing a Large Scale Text Corpus Based on the Grid and Trustworthiness | 56 |
Disambiguating Hypernym Relations for Rogets Thesaurus | 66 |
A Comparison | 76 |
Automatic Word Clustering in Russian Texts | 85 |
Feature Engineering in Maximum Spanning Tree Dependency Parser | 92 |
Automatic Selection of Heterogeneous Syntactic Features in Semantic Similarity of Polish Nouns | 99 |
Bilingual News Clustering Using Named Entities and Fuzzy Similarity | 107 |
Comparing Strategies for European Portuguese | 115 |
On the Evaluation of Korean WordNet | 123 |
An Adaptive Keyboard with Personalized LanguageBased Features | 131 |
An AllPath Parsing Algorithm for ConstraintBased Dependency Grammars of CFPower | 139 |
Word Distribution Based Methods for Minimizing Segment Overlaps | 147 |
On the Relative Hardness of Clustering Corpora | 155 |
Indexing and Retrieval Scheme for ContentBased Multimedia Applications | 162 |
Automatic Diacritic Restoration for ResourceScarce Languages | 170 |
Lexical and Perceptual Grounding of a Sound Ontology | 180 |
Annotating Data and Developing NE Tagger | 188 |
Identifying Expressions of Emotion in Text | 196 |
Authoring Language for Embodied Conversational Agents | 206 |
Dynamic Adaptation of Language Models in Speech Driven Information Retrieval | 214 |
WhiteningBased Feature Space Transformations in a Speech Impediment Therapy System | 222 |
Linguistic Annotations and Translation Units | 230 |
An Automatic Version of the PostLaryngectomy Telephone Test | 238 |
Speaker Normalization Via Springy Discriminant Analysis and Pitch Estimation | 246 |
A Study on Speech with Manifest Emotions | 254 |
Speech Recognition Supported by Prosodic Information for Fixed Stress Languages | 262 |
TRAPBased Techniques for Recognition of Noisy Speech | 270 |
Quantification of Speech Intelligibility by ASR and Prosody | 278 |
Appositions Versus Double Subject Sentences What Information the Speech Analysis Brings to a Grammar Debate | 286 |
Automatic Evaluation of Pathologic Speech from Research to Routine Clinical Use | 294 |
From 10xRT to 1xRT | 302 |
LogicBased Rhetorical Structuring for Natural Language Generation in HumanComputer Dialogue | 309 |
TextIndependent Speaker Identification Using Temporal Patterns | 318 |
Recording and Annotation of Speech Corpus for Czech Unit Selection Speech Synthesis | 326 |
SkToBI Scheme for Phonological Prosody Annotation in Slovak | 334 |
Towards Automatic Transcription of Large Spoken Archives in Agglutinating Languages Hungarian ASR for the MALACH Project | 342 |
Nonuniform SpeechAudio Coding Exploiting Predictability of Temporal Evolution of Spectral Envelopes | 350 |
Towards Conversational Speech | 358 |
Exploratory Analysis ofWord Use and Sentence Length in the Spoken Dutch Corpus | 366 |
Design of Tandem Architecture Using Segmental Trend Features | 374 |
An Automatic Retraining Method for Speaker Independent Hidden Markov Models | 382 |
User Modeling to Support the Development of an Auditory Help System | 390 |
Fast Discriminant Training of Semicontinuous HMM | 398 |
SpeechMusic Discrimination Using MelCepstrum Modulation Energy | 406 |
Parameterization of the Input in Training the HVS Semantic Parser | 415 |
A Comparison Using Different Speech Parameters in the Automatic Emotion Recognition Using Feature Subset Selection Based on Evolutionary Alg... | 423 |
Benefit of Maximum Likelihood Linear Transform MLLT Used at Different Levels of Covariance Matrices Clustering in ASR Systems | 431 |
Information Retrieval Test Collection for Searching Spontaneous Czech Speech | 439 |
Interspeaker Synchronization in Audiovisual Database for LipReadable Speech to Animation Conversion | 447 |
Constructing Empirical Models for Automatic Dialog Parameterization | 455 |
The Effect of Lexicon Composition in Pronunciation by Analogy | 464 |
A Sinhala TexttoSpeech System | 472 |
Voice Conversion Based on Probabilistic Parameter Transformation and Extended Interspeaker Residual Prediction | 480 |
Automatic Czech Sign Speech Translation | 488 |
Maximum Likelihood and Maximum Mutual Information Training in Gender and Age Recognition System | 496 |
Pitch Marks at Peaks or Valleys? | 502 |
Quality Deterioration Factors in Unit Selection Speech Synthesis | 508 |
TopicFocus Articulation Algorithm on the SyntaxProsody Interface of Romanian | 516 |
Translation and Conversion for Czech Sign Speech Synthesis | 524 |
AWizardofOz System Evaluation Study | 532 |
New Measures for OpenDomain Question Answering Evaluation Within a Time Constraint | 540 |
A Methodology for Domain Dialogue Engineering with the Midiki Dialogue Manager | 548 |
The Intonational Realization of Requests in Polish TaskOriented Dialogues | 556 |
Analysis of Changes in Dialogue Rhythm Due to Dialogue Acts in TaskOriented Dialogues | 564 |
Recognition and Understanding Simulation for a Spoken Dialog Corpus Acquisition | 574 |
First Approach in the Development of Multimedia Information Retrieval Resources for the Basque Context | 582 |
The Weakest Link | 591 |
A Spoken Dialog System for ChatLike Conversations Considering Response Timing | 599 |
A Prosodically Annotated Corpus of Czech Television Debates | 607 |
Setting Layout in Dialogue Generating Web Pages | 613 |
GraphBased Answer Fusion in Multilingual Question Answering | 621 |
Using QueryRelevant Documents Pairs for CrossLingual Information Retrieval | 630 |
Detection of Dialogue Acts Using PerplexityBased Word Clustering | 638 |
Dialogue Management for Intelligent TV Based on Statistical Learning Method | 644 |
MultipleTaxonomy Question Classification for Category Search on Faceted Information | 653 |
Other editions - View all
Common terms and phrases
accuracy acoustic aizuchi algorithm analysis annotation applied approach automatic average baseline Berlin Heidelberg 2007 bigram Brno classes classification clustering components Computational Linguistics context corpora corpus Czech Republic data set database diacritic dialogue acts disambiguation documents emotion evaluation experiments extracted F-measure feature vectors filled pauses frame frequency function Gaussian Heidelberg hypernym input language model Language Processing lexical lexicon LMTs LNAI LNCS machine learning Matoušek matrix Mautner Eds means method module morphological n-gram Natural Language Natural Language Processing node nouns obtained output paper parallel corpus parameters parser parsing performance phoneme phrase pitch Prague prediction Proc proposed query rater relations retrieval Romanian score Section segmentation selection semantic sentences similar sounds speaker speech recognition speech synthesis Springer Springer-Verlag Berlin Heidelberg structure syntactic Table tags task techniques training data transformation translation tree Treebank utterance values voice WordNet words