دانلود کتاب Text, Speech and Dialogue: 13th International Conference, TSD 2010, Brno, Czech Republic, September 6-10, 2010. Proceedings

فهرست مطالب :

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 -