Table of Contents

• Language Modeling with Linguistic Cluster ConstraintsFrederick Jelinek, Jia Cui. 1 [doi]
• Some of Our Best Friends Are StatisticiansJan Hajic, Eva Hajicová. 2-10 [doi]
• Some Special Problems of Speech CommunicationHeinrich Niemann. 11-13 [doi]
• Recent Advances in Spoken Language UnderstandingRenato de Mori. 14 [doi]
• Transformation-Based Tectogrammatical Dependency Analysis of EnglishVáclav Klimes. 15-22 [doi]
• Multilingual Name Disambiguation with Semantic InformationZornitsa Kozareva, Sonia Vázquez, Andrés Montoyo. 23-30 [doi]
• Inducing Classes of Terms from TextPablo Gamallo, Gabriel P. Lopes, Alexandre Agustini. 31-38 [doi]
• Accurate Unlexicalized Parsing for Modern HebrewReut Tsarfaty, Khalil Sima an. 39-47 [doi]
• Disambiguation of the Neuter Pronoun and Its Effect on Pronominal Coreference ResolutionVéronique Hoste, Iris Hendrickx, Walter Daelemans. 48-55 [doi]
• Constructing a Large Scale Text Corpus Based on the Grid and TrustworthinessPeifeng Li, Qiaoming Zhu, Peide Qian, Geoffrey Fox. 56-65 [doi]
• Disambiguating Hypernym Relations for ::::Roget s:::: ThesaurusAlistair Kennedy, Stan Szpakowicz. 66-75 [doi]
• Dependency and Phrasal Parsers of the Czech Language: A ComparisonAles Horák, Tomás Holan, Vladimír Kadlec, Vojtech Kovár. 76-84 [doi]
• Automatic Word Clustering in Russian TextsOlga Mitrofanova, Anton Mukhin, Polina Panicheva, Vyacheslav Savitsky. 85-91 [doi]
• Feature Engineering in Maximum Spanning Tree Dependency ParserVáclav Novák, Zdenek Zabokrtský. 92-98 [doi]
• Automatic Selection of Heterogeneous Syntactic Features in Semantic Similarity of Polish NounsMaciej Piasecki, Stan Szpakowicz, Bartosz Broda. 99-106 [doi]
• Bilingual News Clustering Using Named Entities and Fuzzy SimilaritySoto Montalvo, Raquel Martínez, Arantza Casillas, Víctor Fresno. 107-114 [doi]
• Extractive Summarization of Broadcast News: Comparing Strategies for European PortugueseRicardo Ribeiro, David Martins de Matos. 115-122 [doi]
• On the Evaluation of Korean WordNetAltangerel Chagnaa, Hoseop Choe, Cheolyoung Ock, Hwamook Yoon. 123-130 [doi]
• An Adaptive Keyboard with Personalized Language-Based FeaturesSiska Fitrianie, Léon J. M. Rothkrantz. 131-138 [doi]
• An All-Path Parsing Algorithm for Constraint-Based Dependency Grammars of CF-PowerTomasz Obrêbski. 139-146 [doi]
• Word Distribution Based Methods for Minimizing Segment OverlapsJoe Vasak, Fei Song. 147-154 [doi]
• On the Relative Hardness of Clustering CorporaDavid Pinto, Paolo Rosso. 155-161 [doi]
• Indexing and Retrieval Scheme for Content-Based Multimedia ApplicationsDmitry O. Martynov, Eugenij Bovbel. 162-169 [doi]
• Automatic Diacritic Restoration for Resource-Scarce LanguagesGuy De Pauw, Peter W. Wagacha, Gilles-Maurice de Schryver. 170-179 [doi]
• Lexical and Perceptual Grounding of a Sound OntologyAnna Lobanova, Jennifer Spenader, Bea Valkenier. 180-187 [doi]
• Named Entities in Czech: Annotating Data and Developing NE TaggerMagda Sevcíková, Zdenek Zabokrtský, Oldrich Kruza. 188-195 [doi]
• Identifying Expressions of Emotion in TextSaima Aman, Stan Szpakowicz. 196-205 [doi]
• ECAF: Authoring Language for Embodied Conversational AgentsLadislav Kunc, Jan Kleindienst. 206-213 [doi]
• Dynamic Adaptation of Language Models in Speech Driven Information RetrievalCésar González Ferreras, Valentín Cardeñoso-Payo. 214-221 [doi]
• Whitening-Based Feature Space Transformations in a Speech Impediment Therapy SystemAndrás Kocsor, Róbert Busa-Fekete, András Bánhalmi. 222-229 [doi]
• Spanish-Basque Parallel Corpus Structure: Linguistic Annotations and Translation UnitsArantza Casillas, A. Díaz de Illarraza, J. Igartua, Raquel Martínez, K. Sarasola, A. Sologaistoa. 230-237 [doi]
• An Automatic Version of the Post-Laryngectomy Telephone TestTino Haderlein, Korbinian Riedhammer, Andreas Maier, Elmar Nöth, Hikmet Toy, Frank Rosanowski. 238-245 [doi]
• Speaker Normalization Via Springy Discriminant Analysis and Pitch EstimationDénes Paczolay, András Bánhalmi, András Kocsor. 246-253 [doi]
• A Study on Speech with Manifest EmotionsHoria-Nicolai L. Teodorescu, Silvia Monica Feraru. 254-261 [doi]
• Speech Recognition Supported by Prosodic Information for Fixed Stress LanguagesGyörgy Szaszák, Klára Vicsi. 262-269 [doi]
• TRAP-Based Techniques for Recognition of Noisy SpeechFrantisek Grézl, Jan Cernocký. 270-277 [doi]
• Intelligibility Is More Than a Single Word: Quantification of Speech Intelligibility by ASR and ProsodyAndreas Maier, Tino Haderlein, Maria Schuster, Emeka Nkenke, Elmar Nöth. 278-285 [doi]
• Appositions Versus Double Subject Sentences - What Information the Speech Analysis Brings to a Grammar DebateHoria-Nicolai L. Teodorescu, Diana Trandabat. 286-293 [doi]
• Automatic Evaluation of Pathologic Speech - from Research to Routine Clinical UseElmar Nöth, Andreas Maier, Tino Haderlein, Korbinian Riedhammer, Frank Rosanowski, Maria Schuster. 294-301 [doi]
• The LIA Speech Recognition System: From 10xRT to 1xRTGeorges Linares, Pascal Nocera, Dominique Massonié, D. Matrouf. 302-308 [doi]
• Logic-Based Rhetorical Structuring for Natural Language Generation in Human-Computer DialogueVladimir Popescu, Jean Caelen, Corneliu Burileanu. 309-317 [doi]
• Text-Independent Speaker Identification Using Temporal PatternsTobias Bocklet, Andreas Maier, Elmar Nöth. 318-325 [doi]
• Recording and Annotation of Speech Corpus for Czech Unit Selection Speech SynthesisJindrich Matousek, Jan Romportl. 326-333 [doi]
• Sk-ToBI Scheme for Phonological Prosody Annotation in SlovakMilan Rusko, Róbert Sabo, Martin Dzúr. 334-341 [doi]
• Towards Automatic Transcription of Large Spoken Archives in Agglutinating Languages - Hungarian ASR for the MALACH ProjectPéter Mihajlik, Tibor Fegyó, Bottyán Németh, Zoltán Tüske, Viktor Trón. 342-349 [doi]
• Non-uniform Speech/Audio Coding Exploiting Predictability of Temporal Evolution of Spectral EnvelopesPetr Motlícek, Hynek Hermansky, Sriram Ganapathy, Harinath Garudadri. 350-357 [doi]
• Filled Pauses in Speech Synthesis: Towards Conversational SpeechJordi Adell, Antonio Bonafonte, David Escudero Mancebo. 358-365 [doi]
• Exploratory Analysis of Word Use and Sentence Length in the Spoken Dutch CorpusPascal Wiggers, Léon J. M. Rothkrantz. 366-373 [doi]
• Design of Tandem Architecture Using Segmental Trend FeaturesYoung-Sun Yun, Yunkeun Lee. 374-381 [doi]
• An Automatic Retraining Method for Speaker Independent Hidden Markov ModelsAndrás Bánhalmi, Róbert Busa-Fekete, András Kocsor. 382-389 [doi]
• User Modeling to Support the Development of an Auditory Help SystemFlaithrí Neff, Aidan Kehoe, Ian J. Pitt. 390-397 [doi]
• Fast Discriminant Training of Semi-continuous HMMG. Linarès, C. Lévy. 398-405 [doi]
• Speech/Music Discrimination Using Mel-Cepstrum Modulation EnergyBong-Wan Kim, Dae-Lim Choi, Yong-Ju Lee. 406-414 [doi]
• Parameterization of the Input in Training the HVS Semantic ParserJan Svec, Filip Jurcícek, Ludek Müller. 415-422 [doi]
• A Comparison Using Different Speech Parameters in the Automatic Emotion Recognition Using Feature Subset Selection Based on Evolutionary AlgorithmsAitor Álvarez, Idoia Cearreta, Juan Miguel López, Andoni Arruti, Elena Lazkano, Basilio Sierra, Nestor Garay. 423-430 [doi]
• Benefit of Maximum Likelihood Linear Transform (MLLT) Used at Different Levels of Covariance Matrices Clustering in ASR SystemsJosef V. Psutka. 431-438 [doi]
• Information Retrieval Test Collection for Searching Spontaneous Czech SpeechPavel Ircing, Pavel Pecina, Douglas W. Oard, Jianqiang Wang, Ryen W. White, Jan Hoidekr. 439-446 [doi]
• Inter-speaker Synchronization in Audiovisual Database for Lip-Readable Speech to Animation ConversionGergely Feldhoffer, Balázs Oroszi, György Takács, Attila Tihanyi, Tamás Bárdi. 447-454 [doi]
• Constructing Empirical Models for Automatic Dialog ParameterizationMikhail Alexandrov, Xavier Blanco, Natalia Ponomareva, Paolo Rosso. 455-463 [doi]
• The Effect of Lexicon Composition in Pronunciation by AnalogyTasanawan Soonklang, Robert I. Damper, Yannick Marchand. 464-471 [doi]
• Festival-si: A Sinhala Text-to-Speech SystemRuvan Weerasinghe, Asanka Wasala, Viraj Welgama, Kumudu Gamage. 472-479 [doi]
• Voice Conversion Based on Probabilistic Parameter Transformation and Extended Inter-speaker Residual PredictionZdenek Hanzlícek, Jindrich Matousek. 480-487 [doi]
• Automatic Czech - Sign Speech TranslationJakub Kanis, Ludek Müller. 488-495 [doi]
• Maximum Likelihood and Maximum Mutual Information Training in Gender and Age Recognition SystemValiantsina Hubeika, Igor Szöke, Lukas Burget, Jan Cernocký. 496-501 [doi]
• Pitch Marks at Peaks or Valleys?Milan Legát, Daniel Tihelka, Jindrich Matousek. 502-507 [doi]
• Quality Deterioration Factors in Unit Selection Speech SynthesisDaniel Tihelka, Jindrich Matousek, Jirí Kala. 508-515 [doi]
• Topic-Focus Articulation Algorithm on the Syntax-Prosody Interface of RomanianNeculai Curteanu, Diana Trandabat, Mihai Alex Moruz. 516-523 [doi]
• Translation and Conversion for Czech Sign Speech SynthesisZdenek Krnoul, Milos Zelezný. 524-531 [doi]
• A Wizard-of-Oz System Evaluation StudyMelita Hajdinjak, France Mihelic. 532-539 [doi]
• New Measures for Open-Domain Question Answering Evaluation Within a Time ConstraintElisa Noguera, Fernando Llopis, Antonio Ferrández, Alberto Escapa. 540-547 [doi]
• A Methodology for Domain Dialogue Engineering with the Midiki Dialogue ManagerLúcio M. M. Quintal, Paulo Nazareno Maia Sampaio. 548-555 [doi]
• The Intonational Realization of Requests in Polish Task-Oriented DialoguesMaciej Karpinski. 556-563 [doi]
• Analysis of Changes in Dialogue Rhythm Due to Dialogue Acts in Task-Oriented DialoguesNoriki Fujiwara, Toshihiko Itoh, Kenji Araki. 564-573 [doi]
• Recognition and Understanding Simulation for a Spoken Dialog Corpus AcquisitionFernando García, Lluìs F. Hurtado, David Griol, María José Castro, Encarna Segarra, Emilio Sanchis. 574-581 [doi]
• First Approach in the Development of Multimedia Information Retrieval Resources for the Basque ContextN. Barroso, Aitzol Ezeiza, N. Gilisagasti, K. López de Ipiña, A. López, Juan Miguel López. 582-590 [doi]
• The Weakest LinkHarry Bunt, Roser Morante. 591-598 [doi]
• A Spoken Dialog System for Chat-Like Conversations Considering Response TimingRyota Nishimura, Norihide Kitaoka, Seiichi Nakagawa. 599-606 [doi]
• Digitisation and Automatic Alignment of the DIALOG Corpus: A Prosodically Annotated Corpus of Czech Television DebatesNino Peterek, Petr Kaderka, Zdenka Svobodová, Eva Havlová, Martin Havlík, Jana Klímová, Patricie Kubácková. 607-612 [doi]
• Setting Layout in Dialogue Generating Web PagesLudek Bártek, Ivan Kopecek, Radek Oslejsek. 613-620 [doi]
• Graph-Based Answer Fusion in Multilingual Question AnsweringRita M. Aceves-Pérez, Manuel Montes-y-Gómez, Luis Villaseñor Pineda. 621-629 [doi]
• Using Query-Relevant Documents Pairs for Cross-Lingual Information RetrievalDavid Pinto, Alfons Juan, Paolo Rosso. 630-637 [doi]
• Detection of Dialogue Acts Using Perplexity-Based Word ClusteringIosif Mporas, Dimitrios P. Lyras, Kyriakos N. Sgarbas, Nikos Fakotakis. 638-643 [doi]
• Dialogue Management for Intelligent TV Based on Statistical Learning MethodHyo-Jung Oh, Chung-Hee Lee, Yi-Gyu Hwang, Myung-Gil Jang. 644-652 [doi]
• Multiple-Taxonomy Question Classification for Category Search on Faceted InformationDavid Tomás, José Luis Vicedo González. 653-660 [doi]