Text, Speech, and Dialogue: 18th International Conference, TSD 2015 Pilsen, Czech Republic, September 14–17, 2015, Proceedings

Front Matter....Pages -
Front Matter....Pages 1-1
Speech Analysis in the Big Data Era....Pages 3-11
Front Matter....Pages 13-13
A Multi-criteria Text Selection Approach for Building a Speech Corpus....Pages 15-22
Experiment with GMM-Based Artefact Localization in Czech Synthetic Speech....Pages 23-31
Tuned and GPU-Accelerated Parallel Data Mining from Comparable Corpora....Pages 32-40
Investigating Genre and Method Variation in Translation Using Text Classification....Pages 41-50
Extracting Characteristics of Fashion Models from Magazines for Item Recommendation....Pages 51-60
Segment Representations in Named Entity Recognition....Pages 61-70
Analyzing Text Coherence via Multiple Annotation in the Prague Dependency Treebank....Pages 71-79
Automatic Detection of Parkinson’s Disease in Reverberant Environments....Pages 80-87
Automatic Detection of Parkinson’s Disease from Compressed Speech Recordings....Pages 88-95
Time Dependent ARMA for Automatic Recognition of Fear-Type Emotions in Speech....Pages 96-104
Using Lexical Stress in Authorship Attribution of Historical Texts....Pages 105-113
Eye Gaze Analyses in L1 and L2 Conversations: Difference in Interaction Structures....Pages 114-121
Word Categorization of Corporate Annual Reports for Bankruptcy Prediction by Machine Learning Methods....Pages 122-130
Novel Multi-word Lists for Investors’ Decision Making....Pages 131-139
Topic Classifier for Customer Service Dialog Systems....Pages 140-148
Defining a Global Adaptive Duration Target Cost for Unit Selection Speech Synthesis....Pages 149-157
Adaptive Speech Synthesis of Albanian Dialects....Pages 158-164
Language-Independent Age Estimation from Speech Using Phonological and Phonemic Features....Pages 165-173
LecTrack: Incremental Dialog State Tracking with Long Short-Term Memory Networks....Pages 174-182
Front Matter....Pages 13-13
Automatic Construction of Domain Specific Sentiment Lexicons for Hungarian....Pages 183-190
Investigation of Word Senses over Time Using Linguistic Corpora....Pages 191-198
Dependency-Based Problem Phrase Extraction from User Reviews of Products....Pages 199-206
Semantic Splitting of German Medical Compounds....Pages 207-215
A Comparison of MT Methods for Closely Related Languages: A Case Study on Czech - Slovak and Croatian - Slovenian Language Pairs....Pages 216-224
Ideas for Clustering of Similar Models of a Speaker in an Online Speaker Diarization System....Pages 225-233
Simultaneously Trained NN-Based Acoustic Model and NN-Based Feature Extractor....Pages 234-242
Named Entity Recognition for Mongolian Language....Pages 243-251
Comparing Semantic Models for Evaluating Automatic Document Summarization....Pages 252-260
Automatic Labeling of Semantic Roles with a Dependency Parser in Hungarian Economic Texts....Pages 261-272
Significance of Unvoiced Segments and Fundamental Frequency in Infant Cry Analysis....Pages 273-281
Speech Corpus Preparation for Voice Banking of Laryngectomised Patients....Pages 282-290
An Open Source Speech Synthesis Frontend for HTS....Pages 291-298
Tibetan Linguistic Terminology on the Base of the Tibetan Traditional Grammar Treatises Corpus....Pages 299-306
Improving Multi-label Document Classification of Czech News Articles....Pages 307-315
Score Normalization Methods for Relevant Documents Selection for Blind Relevance Feedback in Speech Information Retrieval....Pages 316-324
Imbalanced Text Categorization Based on Positive and Negative Term Weighting Approach....Pages 325-333
CloudASR: Platform and Service....Pages 334-341
Experimental Tagging of the ORAL Series Corpora: Insights on Using a Stochastic Tagger....Pages 342-350
Development and Evaluation of the Emotional Slovenian Speech Database - EmoLUKS....Pages 351-359
Front Matter....Pages 13-13
A Semi-automatic Adjective Mapping Between plWordNet and Princeton WordNet....Pages 360-368
Toward Exploring the Role of Disfluencies from an Acoustic Point of View: A New Aspect of (Dis)continuous Speech Prosody Modelling....Pages 369-377
Heuristic Algorithm for Zero Subject Detection in Polish....Pages 378-386
Vocal Tract Length Normalization Features for Audio Search....Pages 387-395
RENA: A Named Entity Recognition System for Arabic....Pages 396-404
Combining Evidences from Mel Cepstral and Cochlear Cepstral Features for Speaker Recognition Using Whispered Speech....Pages 405-413
Random Indexing Explained with High Probability....Pages 414-423
Hungarian Grammar Writing with LTAG and XMG....Pages 424-432
Phonetic Segmentation Using KALDI and Reduced Pronunciation Detection in Causal Czech Speech....Pages 433-441
Automatic Robust Rule-Based Phonetization of Standard Arabic....Pages 442-451
Knowledge-Based and Data-Driven Approaches for Georeferencing of Informal Documents....Pages 452-460
Automated Mining of Relevant N-grams in Relation to Predominant Topics of Text Documents....Pages 461-469
Incremental Dependency Parsing and Disfluency Detection in Spoken Learner English....Pages 470-479
Open Source German Distant Speech Recognition: Corpus and Acoustic Model....Pages 480-488
First Steps in Czech Entity Linking....Pages 489-496
Classification of Prosodic Phrases by Using HMMs....Pages 497-505
Adding Multilingual Terminological Resources to Parallel Corpora for Statistical Machine Translation Deteriorates System Performance: A Negative Result from Experiments in the Biomedical Domain....Pages 506-514
Derivancze — Derivational Analyzer of Czech....Pages 515-523
Detection of Large Segmentation Errors with Score Predictive Model....Pages 524-532
Identification of Noun-Noun Compounds in the Context of Speech-to-Speech Translation....Pages 533-541
Front Matter....Pages 13-13
From Spoken Language to Ontology-Driven Dialogue Management....Pages 542-550
Entity-Oriented Sentiment Analysis of Tweets: Results and Problems....Pages 551-559
Improved Estimation of Articulatory Features Based on Acoustic Features with Temporal Context....Pages 560-568
Do Important Words in Bag-of-Words Model of Text Relatedness Help?....Pages 569-577
Increased Recall in Annotation Variance Detection in Treebanks....Pages 578-586
Using Sociolinguistic Inspired Features for Gender Classification of Web Authors....Pages 587-594
Modified Group Delay Based Features for Asthma and HIE Infant Cries Classification....Pages 595-602
Self-Enrichment of Normalized LMF Dictionaries Through Syntactic-Behaviors-to-Meanings Links....Pages 603-610
Back Matter....Pages -