Text, Speech, and Dialogue

1. Front Matter

   Pages I-XXI

   PDF

2. Keynote Talk

   1. Front Matter

      Pages 1-1

      PDF

   2. A Glimpse Under the Surface: Language Understanding May Need Deep Syntactic Structure

      • Eva Hajičová

      Pages 3-7

3. Conference Papers

   1. Front Matter

      Pages 9-9

      PDF

   2. Robust Automatic Evaluation of Intelligibility in Voice Rehabilitation Using Prosodic Analysis

      • Tino Haderlein, Anne Schützenberger, Michael Döllinger, Elmar Nöth

      Pages 11-19

   3. Personality-Dependent Referring Expression Generation

      • Ivandré Paraboni, Danielle Sampaio Monteiro, Alex Gwo Jen Lan

      Pages 20-28

   4. Big Five Personality Recognition from Multiple Text Genres

      • Vitor Garcia dos Santos, Ivandré Paraboni, Barbara Barbosa Claudino Silva

      Pages 29-37

   5. Automatic Classification of Types of Artefacts Arising During the Unit Selection Speech Synthesis

      • Jiří Přibil, Anna Přibilová, Jindřich Matoušek

      Pages 38-46

   6. A Comparison of Lithuanian Morphological Analyzers

      • Jurgita Kapočiūtė-Dzikienė, Erika Rimkutė, Loic Boizou

      Pages 47-56

   7. Constrained Deep Answer Sentence Selection

      • Ahmad Aghaebrahimian

      Pages 57-65

   8. Quora Question Answer Dataset

      • Ahmad Aghaebrahimian

      Pages 66-73

   9. Sentiment Analysis with Tree-Structured Gated Recurrent Units

      • Marcin Kuta, Mikołaj Morawiec, Jacek Kitowski

      Pages 74-82

   10. Synthetic Speech in Therapy of Auditory Hallucinations

       • Kamil Sorokosz, Izabela Stefaniak, Artur Janicki

       Pages 83-91

   11. Statistical Pronunciation Adaptation for Spontaneous Speech Synthesis

       • Raheel Qader, Gwénolé Lecorvé, Damien Lolive, Marie Tahon, Pascale Sébillot

       Pages 92-101

   12. Machine Learning Approach to the Process of Question Generation

       • Miroslav Blšták, Viera Rozinajová

       Pages 102-110

   13. Automatic Extraction of Typological Linguistic Features from Descriptive Grammars

       • Shafqat Mumtaz Virk, Lars Borin, Anju Saxena, Harald Hammarström

       Pages 111-119

   14. Text Punctuation: An Inter-annotator Agreement Study

       • Marek Boháč, Michal Rott, Vojtěch Kovář

       Pages 120-128

   15. PDTSC 2.0 - Spoken Corpus with Rich Multi-layer Structural Annotation

       • Marie Mikulová, Jiří Mírovský, Anja Nedoluzhko, Petr Pajas, Jan Štěpánek, Jan Hajič

       Pages 129-137

   16. Automatic Phonetic Segmentation Using the Kaldi Toolkit

       • Jindřich Matoušek, Michal Klíma

       Pages 138-146

   17. Language Independent Assessment of Motor Impairments of Patients with Parkinson’s Disease Using i-Vectors

       • N. Garcia, J. C. Vásquez-Correa, J. R. Orozco-Arroyave, N. Dehak, E. Nöth

       Pages 147-155

This book constitutes the proceedings of the 20th International Conference on Text, Speech, and Dialogue, TSD 2017, held in Prague, CzechRepublic, in August 2017.

The 56 regular papers presented together with 3 abstracts of keynote talks were carefully reviewed and selected from 117 submissions. They focus on topics such as corpora and language resources; speech recognition; tagging, classification and parsing of text and speech; speech and spoken language generation; semantic processing of text and speech; integrating applications of text and speech processing; automatic dialogue systems; as well as multimodal techniques and modelling.

• Natural language processing
• Natural language generation
• Machine translation
• Discourse, dialogue and pragmatics
• Dialogue systems
• Speech recognition
• Speech synthesis
• Semantics and semantic analysis
• Computational linguistics
• Language resources and corpora
• signal processing
• speech analysis
• learning systems
• automatic speech recognition
• artificial intelligence

• University of West Bohemia, Pilsen, Czech Republic

  Kamil Ekštein, Václav Matoušek

Policies and ethics