Text, Speech, and Dialogue: 22nd International Conference, TSD 2019, Ljubljana, Slovenia, September 11–13, 2019, Proceedings (Lecture Notes in Computer Science Book 11697)

This book constitutes the proceedings of the 22nd International Conference on Text, Speech, and Dialogue, TSD 2019, held in Ljubljana, Slovenia, in September 2019. The 33 full papers presented in this volume were carefully reviewed and selected from 73 submissions. They were organized in topical sections named text and speech. The book also contains one invited talk in full paper length. Front Matter ....Pages i-xix Front Matter ....Pages 1-1 Speech Processing and Prosody (Denis Jouvet)....Pages 3-15 Front Matter ....Pages 17-17 Using a Database of Multiword Expressions in Dependency Parsing (Tomáš Jelínek)....Pages 19-31 Explicit Discourse Argument Extraction for German (Peter Bourgonje, Manfred Stede)....Pages 32-44 Consonance as a Stylistic Feature for Authorship Attribution of Historical Texts (Lubomir Ivanov, Brandon Neilsen)....Pages 45-57 Bidirectional LSTM Tagger for Latvian Grammatical Error Detection (Daiga Deksne)....Pages 58-68 Methods for Assessing Theme Adherence in Student Thesis (Mikhail Tikhomirov, Natalia Loukachevitch, Boris Dobrov)....Pages 69-81 Natural Language Analysis to Detect Parkinson’s Disease (P. A. Pérez-Toro, J. C. Vásquez-Correa, M. Strauss, J. R. Orozco-Arroyave, E. Nöth)....Pages 82-90 Using Auto-Encoder BiLSTM Neural Network for Czech Grapheme-to-Phoneme Conversion (Markéta Jůzová, Jakub Vít)....Pages 91-102 The FRENK Datasets of Socially Unacceptable Discourse in Slovene and English (Nikola Ljubešić, Darja Fišer, Tomaž Erjavec)....Pages 103-114 KAS-term: Extracting Slovene Terms from Doctoral Theses via Supervised Machine Learning (Nikola Ljubešić, Darja Fišer, Tomaž Erjavec)....Pages 115-126 A Self-organizing Feature Map for Arabic Word Extraction (Hassina Bouressace, János Csirik)....Pages 127-136 Czech Text Processing with Contextual Embeddings: POS Tagging, Lemmatization, Parsing and NER (Milan Straka, Jana Straková, Jan Hajič)....Pages 137-150 On GDPR Compliance of Companies’ Privacy Policies (Nicolas M. Müller, Daniel Kowatsch, Pascal Debus, Donika Mirdita, Konstantin Böttinger)....Pages 151-159 A Semi-automatic Structure Learning Method for Language Modeling (Vitor Pera)....Pages 160-170 Coreference in English OntoNotes: Properties and Genre Differences (Berfin Aktaş, Tatjana Scheffler, Manfred Stede)....Pages 171-184 The TransBank Aligner: Cross-Sentence Alignment with Deep Neural Networks (Ahmad Aghaebrahimian, Michael Ustaszewski, Andy Stauder)....Pages 185-196 Exploiting Large Unlabeled Data in Automatic Evaluation of Coherence in Czech (Michal Novák, Jiří Mírovský, Kateřina Rysová, Magdaléna Rysová)....Pages 197-210 Examining Structure of Word Embeddings with PCA (Tomáš Musil)....Pages 211-223 Semantic Structure of Russian Prepositional Constructions (Victor Zakharov, Irina Azarova)....Pages 224-235 Explicit and Implicit Discourse Relations in the Prague Discourse Treebank (Šárka Zikánová, Jiří Mírovský, Pavlína Synková)....Pages 236-248 Front Matter ....Pages 249-249 On Practical Aspects of Multi-condition Training Based on Augmentation for Reverberation-/Noise-Robust Speech Recognition (Jiri Malek, Jindrich Zdansky)....Pages 251-263 Evaluation of Synthetic Speech by GMM-Based Continuous Detection of Emotional States (Jiří Přibil, Anna Přibilová, Jindřich Matoušek)....Pages 264-273 Deep Representation Learning for Orca Call Type Classification (Christian Bergler, Manuel Schmitt, Rachael Xi Cheng, Hendrik Schröter, Andreas Maier, Volker Barth et al.)....Pages 274-286 On Using Stateful LSTM Networks for Key-Phrase Detection (Martin Bulín, Luboš Šmídl, Jan Švec)....Pages 287-298 Consonant-to-Vowel/Vowel-to-Consonant Transitions to Analyze the Speech of Cochlear Implant Users (T. Arias-Vergara, J. R. Orozco-Arroyave, S. Gollwitzer, M. Schuster, E. Nöth)....Pages 299-306 Czech Speech Synthesis with Generative Neural Vocoder (Jakub Vít, Zdeněk Hanzlíček, Jindřich Matoušek)....Pages 307-315 Linguistic Resources Construction: Towards Disfluency Processing in Spontaneous Tunisian Dialect Speech (Emna Boughariou, Younès Bahou, Lamia Hadrich Bleguith)....Pages 316-328 Comparing Front-End Enhancement Techniques and Multiconditioned Training for Robust Automatic Speech Recognition (Meet H. Soni, Sonal Joshi, Ashish Panda)....Pages 329-340 Label-Driven Time-Frequency Masking for Robust Speech Command Recognition (Meet Soni, Imran Sheikh, Sunil Kumar Kopparapu)....Pages 341-351 A Comparison of Hybrid and End-to-End Models for Syllable Recognition (Sebastian P. Bayerl, Korbinian Riedhammer)....Pages 352-360 LSTM-Based Speech Segmentation for TTS Synthesis (Zdeněk Hanzlíček, Jakub Vít, Daniel Tihelka)....Pages 361-372 Spoken Language Identification Using Language Bottleneck Features (Malo Grisard, Petr Motlicek, Wissem Allouchi, Michael Baeriswyl, Alexandros Lazaridis, Qingran Zhan)....Pages 373-381 Front Matter ....Pages 383-383 Question-Answering Dialog System for Large Audiovisual Archives (Adam Chýlek, Luboš Šmídl, Jan Švec)....Pages 385-397 Crowd-Sourced Collection of Task-Oriented Human-Human Dialogues in a Multi-domain Scenario (Norbert Braunschweiler, Panagiotis Papadakos, Margarita Kotti, Yannis Marketakis, Yannis Tzitzikas)....Pages 398-411 Back Matter ....Pages 413-414