Text, Speech, and Dialogue: 19th International Conference, TSD 2016, Brno , Czech Republic, September 12-16, 2016, Proceedings

Front Matter....Pages I-XXI
Front Matter....Pages 1-1
Grammatical Annotation of Historical Portuguese: Generating a Corpus-Based Diachronic Dictionary....Pages 3-11
Generating of Events Dictionaries from Polish WordNet for the Recognition of Events in Polish Documents....Pages 12-19
Building Corpora for Stylometric Research....Pages 20-27
Constraint-Based Open-Domain Question Answering Using Knowledge Graph Search....Pages 28-36
A Sentiment-Aware Topic Model for Extracting Failures from Product Reviews....Pages 37-45
Digging Language Model – Maximum Entropy Phrase Extraction....Pages 46-53
Vive la Petite Différence!....Pages 54-61
Towards It-CMC: A Fine-Grained POS Tagset for Italian Linguistic Analysis....Pages 62-73
FAQIR – A Frequently Asked Questions Retrieval Test Collection....Pages 74-81
Combining Dependency Parsers Using Error Rates....Pages 82-92
A Modular Chain of NLP Tools for Basque....Pages 93-100
Speech-to-Text Summarization Using Automatic Phrase Extraction from Recognized Text....Pages 101-108
Homonymy and Polysemy in the Czech Morphological Dictionary....Pages 109-116
Cross-Language Dependency Parsing Using Part-of-Speech Patterns....Pages 117-124
Assessing Context for Extraction of Near Synonyms from Product Reviews in Spanish....Pages 125-133
Gathering Information About Word Similarity from Neighbor Sentences....Pages 134-141
Short Messages Spam Filtering Using Sentiment Analysis....Pages 142-153
Preliminary Study on Automatic Recognition of Spatial Expressions in Polish Texts....Pages 154-162
Topic Modeling over Text Streams from Social Media....Pages 163-172
Neural Networks for Featureless Named Entity Recognition in Czech....Pages 173-181
Front Matter....Pages 1-1
SubGram: Extending Skip-Gram Word Representation with Substrings....Pages 182-189
WordSim353 for Czech....Pages 190-197
Automatic Restoration of Diacritics for Igbo Language....Pages 198-205
Predicting Morphologically-Complex Unknown Words in Igbo....Pages 206-214
Morphosyntactic Analyzer for the Tibetan Language: Aspects of Structural Ambiguity....Pages 215-222
Automatic Question Generation Based on Analysis of Sentence Structure....Pages 223-230
CzEng 1.6: Enlarged Czech-English Parallel Corpus with Processing Tools Dockered....Pages 231-238
Using Alliteration in Authorship Attribution of Historical Texts....Pages 239-248
Collecting Facebook Posts and WhatsApp Chats....Pages 249-258
A Dynamic Programming Approach to Improving Translation Memory Matching and Retrieval Using Paraphrases....Pages 259-269
AQA: Automatic Question Answering System for Czech....Pages 270-278
Annotation of Czech Texts with Language Mixing....Pages 279-286
Evaluation and Improvements in Punctuation Detection for Czech....Pages 287-294
Annotated Amharic Corpora....Pages 295-302
Front Matter....Pages 303-303
Evaluation of TTS Personification by GMM-Based Speaker Gender and Age Classifier....Pages 305-313
Grapheme to Phoneme Translation Using Conditional Random Fields with Re-Ranking....Pages 314-325
On the Influence of the Number of Anomalous and Normal Examples in Anomaly-Based Annotation Errors Detection....Pages 326-334
Unit-Selection Speech Synthesis Adjustments for Audiobook-Based Voices....Pages 335-342
The Custom Decay Language Model for Long Range Dependencies....Pages 343-351
Voice Activity Detector (VAD) Based on Long-Term Mel Frequency Band Features....Pages 352-358
Front Matter....Pages 303-303
Difficulties with Wh-Questions in Czech TTS System....Pages 359-366
Tools rPraat and mPraat....Pages 367-374
A Composition Algorithm of Compact Finite-State Super Transducers for Grapheme-to-Phoneme Conversion....Pages 375-382
Embedded Learning Segmentation Approach for Arabic Speech Recognition....Pages 383-390
KALDI Recipes for the Czech Speech Recognition Under Various Conditions....Pages 391-399
Glottal Flow Patterns Analyses for Parkinson’s Disease Detection: Acoustic and Nonlinear Approaches....Pages 400-407
Correction of Prosodic Phrases in Large Speech Corpora....Pages 408-417
Relevant Documents Selection for Blind Relevance Feedback in Speech Information Retrieval....Pages 418-425
Investigation of Bottle-Neck Features for Emotion Recognition....Pages 426-434
Classification of Speaker Intoxication Using a Bidirectional Recurrent Neural Network....Pages 435-442
Training Maxout Neural Networks for Speech Recognition Tasks....Pages 443-451
An Efficient Method for Vocabulary Addition to WFST Graphs....Pages 452-458
Front Matter....Pages 459-459
Influence of Reverberation on Automatic Evaluation of Intelligibility with Prosodic Features....Pages 461-469
Automatic Scoring of a Sentence Repetition Task from Voice Recordings....Pages 470-477
Platon: Dialog Management and Rapid Prototyping for Multilingual Multi-user Dialog Systems....Pages 478-485
How to Add Word Classes to the Kaldi Speech Recognition Toolkit....Pages 486-494
Starting a Conversation: Indexical Rhythmical Features Across Age and Gender (A Corpus Study)....Pages 495-505
Classification of Utterance Acceptability Based on BLEU Scores for Dialogue-Based CALL Systems....Pages 506-513
A Unified Parser for Developing Indian Language Text to Speech Synthesizers....Pages 514-521
Influence of Expressive Speech on ASR Performances: Application to Elderly Assistance in Smart Home....Pages 522-530
Front Matter....Pages 459-459
From Dialogue Corpora to Dialogue Systems: Generating a Chatbot with Teenager Personality for Preventing Cyber-Pedophilia....Pages 531-539
Automatic Syllabification and Syllable Timing of Automatically Recognized Speech – for Czech....Pages 540-547
Back Matter....Pages 549-550