This book constitutes the refereed proceedings of the 13th International Conference on Text, Speech and Dialogue, TSD 2010, held in Brno, Czech Republic, September 2010. The 71 revised full papers presented together with 3 invited papers were carefully reviewed and selected from 144 submissions. The topics of the conference include, but are not limited to text corpora and tagging, transcription problems in spoken corpora, sense disambiguation, links between text and speech oriented systems, parsing issues, multi-lingual issues, information retrieval and information extraction, text/topic summarization, machine translation, semantic web, speech modeling, speech recognition, search in speech for IR and IE, text-to-speech synthesis, emotions and personality modeling, user modeling, knowledge representation in relation to dialogue systems, assistive technologies based on speech and dialogue, applied systems and software, facial animation, as well as visual speech synthesis.
Author(s): John Carroll (auth.), Petr Sojka, Aleš Horák, Ivan Kopeček, Karel Pala (eds.)
Series: Lecture Notes in Computer Science 6231 : Lecture Notes in Artificial Intelligence
Edition: 1
Publisher: Springer-Verlag Berlin Heidelberg
Year: 2010
Language: English
Pages: 593
Tags: Artificial Intelligence (incl. Robotics); Information Systems Applications (incl.Internet); Information Storage and Retrieval; User Interfaces and Human Computer Interaction; Database Management; Data Mining and Knowledge Discovery
Front Matter....Pages -
Front Matter....Pages 1-1
Parsing and Real-World Applications....Pages 3-5
Knowledge for Everyman....Pages 6-9
Evolution of the ASR Decoder Design....Pages 10-17
Front Matter....Pages 19-19
Encoding Event and Argument Structures in Wordnets....Pages 21-28
Lexical-Conceptual Relations as Qualia Role Encoders....Pages 29-36
Towards Disambiguation of Word Sketches....Pages 37-42
Towards an N-Version Dependency Parser....Pages 43-50
Advanced Searching in the Valency Lexicons Using PML-TQ Search Engine....Pages 51-58
These Nouns That Hide Events: An Initial Detection....Pages 59-66
Can Corpus Pattern Analysis Be Used in NLP?....Pages 67-74
Extracting Human Spanish Nouns....Pages 75-83
Semantic Duplicate Identification with Parsing and Machine Learning....Pages 84-92
Comparison of Different Lemmatization Approaches through the Means of Information Retrieval Performance....Pages 93-100
Evaluation of a Sentence Ranker for Text Summarization Based on Roget’s Thesaurus....Pages 101-108
Real Anaphora Resolution Is Hard....Pages 109-116
Event-Time Relation Identification Using Machine Learning and Rules....Pages 117-124
Question Answering for Not Yet Semantic Web....Pages 125-132
Automatic Acquisition of Wordnet Relations by Distributionally Supported Morphological Patterns Extracted from Polish Corpora....Pages 133-141
Study on Named Entity Recognition for Polish Based on Hidden Markov Models....Pages 142-149
Semantic Role Patterns and Verb Classes in Verb Valency Lexicon....Pages 150-156
Front Matter....Pages 19-19
Opinion Mining by Transformation-Based Domain Adaptation....Pages 157-164
Improving Automatic Image Captioning Using Text Summarization Techniques....Pages 165-172
Perplexity of n-Gram and Dependency Language Models....Pages 173-180
Analysis of Czech Web 1T 5-Gram Corpus and Its Comparison with Czech National Corpus Data....Pages 181-188
Borda-Based Voting Schemes for Semantic Role Labeling....Pages 189-196
Towards a Bank of Constituent Parse Trees for Polish....Pages 197-204
Coverage-Based Methods for Distributional Stopword Selection in Text Segmentation....Pages 205-215
Using TectoMT as a Preprocessing Tool for Phrase-Based Statistical Machine Translation....Pages 216-223
Automatic Sentiment Analysis Using the Textual Pattern Content Similarity in Natural Language....Pages 224-231
Front Matter....Pages 233-233
Correlation Features and a Linear Transform Specific Reproducing Kernel....Pages 235-242
Automatic Detection and Evaluation of Edentulous Speakers with Insufficient Dentures....Pages 243-250
Diagnostics for Debugging Speech Recognition Systems....Pages 251-258
Automatic Lip Reading in the Dutch Language Using Active Appearance Models on High Speed Recordings....Pages 259-266
Towards the Optimal Minimization of a Pronunciation Dictionary Model....Pages 267-274
Multimodal Emotion Recognition Based on the Decoupling of Emotion and Speaker Information....Pages 275-282
Listening-Test-Based Annotation of Communicative Functions for Expressive Speech Synthesis....Pages 283-290
Czech HMM-Based Speech Synthesis....Pages 291-298
Using Syllables as Acoustic Units for Spontaneous Speech Recognition....Pages 299-305
Embedded Speech Recognition in UPnP (DLNA) Environment....Pages 306-313
Estonian: Some Findings for Modelling Speech Rhythmicity and Perception of Speech Rate....Pages 314-321
Front Matter....Pages 233-233
Using Gradient Descent Optimization for Acoustics Training from Heterogeneous Data....Pages 322-329
Recovery of Rare Words in Lecture Speech....Pages 330-337
Enhancing Emotion Recognition from Speech through Feature Selection....Pages 338-344
Collection and Analysis of Data for Evaluation of Concatenation Cost Functions....Pages 345-352
Emotion Recognition from Speech by Combining Databases and Fusion of Classifiers....Pages 353-360
Emologus—A Compositional Model of Emotion Detection Based on the Propositional Content of Spoken Utterances....Pages 361-368
Automatic Segmentation of Parasitic Sounds in Speech Corpora for TTS Synthesis....Pages 369-376
Adapting Lexical and Language Models for Transcription of Highly Spontaneous Spoken Czech....Pages 377-384
Fast Phonetic/Lexical Searching in the Archives of the Czech Holocaust Testimonies: Advancing Towards the MALACH Project Visions....Pages 385-391
CORPRES....Pages 392-399
Hybrid HMM/BLSTM-RNN for Robust Speech Recognition....Pages 400-407
Some Aspects of ASR Transcription Based Unsupervised Speaker Adaptation for HMM Speech Synthesis....Pages 408-415
Online TV Captioning of Czech Parliamentary Sessions....Pages 416-422
Adaptation of a Feedforward Artificial Neural Network Using a Linear Transform....Pages 423-430
Gender-Dependent Acoustic Models Fusion Developed for Automatic Subtitling of Parliament Meetings Broadcasted by the Czech TV....Pages 431-438
Parallel Training of Neural Networks for Speech Recognition....Pages 439-446
Design and Implementation of a Bayesian Network Speech Recognizer....Pages 447-454
Special Speech Synthesis for Social Network Websites....Pages 455-463
Robust Statistic Estimates for Adaptation in the Task of Speech Recognition....Pages 464-471
A Priori and A Posteriori Machine Learning and Nonlinear Artificial Neural Networks....Pages 472-479
Front Matter....Pages 233-233
Posterior Estimates and Transforms for Speech Recognition....Pages 480-487
Front Matter....Pages 489-489
A Multimodal Dialogue System for an Ambient Intelligent Application in Home Environments....Pages 491-498
Integrating Aggregation Strategies in an In-Home Domain Dialogue System....Pages 499-506
A Methodology for Learning Optimal Dialog Strategies....Pages 507-514
The Structure of a Discontinuous Dialogue Formed by Internet Comments....Pages 515-522
Using Knowledge about Misunderstandings to Increase the Robustness of Spoken Dialogue Systems....Pages 523-530
Linguistic Adaptation in Semi-natural Dialogues: Age Comparison....Pages 531-538
Automatic Speech Recognition Based on Multiple Level Units in Spoken Dialogue System for In-Vehicle Appliances....Pages 539-546
Dialogue System Based on EDECÁN Architecture....Pages 547-551
Integration of Speech and Text Processing Modules into a Real-Time Dialogue System....Pages 552-559
Client and Speech Detection System for Intelligent Infokiosk....Pages 560-567
Prototype of Czech Spoken Dialog System with Mixed Initiative for Railway Information Service....Pages 568-575
An NLP-Oriented Analysis of the Instant Messaging Discourse....Pages 576-583
Expressive Gibberish Speech Synthesis for Affective Human-Computer Interaction....Pages 584-590
Back Matter....Pages -
