Full Description
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.
Contents
Speech Processing and Prosody.- Using a Database of Multiword Expressions in Dependency Parsing
Explicit Discourse Argument Extraction for German.- Consonance as a Stylistic Feature for Authorship Attribution of Historical Texts.- Bidirectional LSTM Tagger for Latvian Grammatical Error Detection.- Testing Features for Assessing Theme Adherence in Student Thesis.- Natural language analysis to detect Parkinson's disease.- Using Auto-Encoder BiLSTM Neural Network for Czech Grapheme-to-Phoneme Conversion.- The FRENK datasets of socially unacceptable discourse in Slovene and English.- KAS-term: Extracting Slovene terms via supervised machine learning.- Self-Organizing Feature Map for Arabic Word Extraction. -Czech Text Processing with Contextual Embeddings: POS Tagging, Lemmatization, Parsing and NER.- A Privacy Policy Dataset for GDPR compliance.- A semi-automatic structure learning method for language modeling.- Coreference in English OntoNotes: Properties and Genre Differences.- Cross-Sentence Alignment with Deep Neural Networks.- Exploiting Large Unlabeled Data in Automatic Evaluation of Coherence in Czech.- Structure of Representation in Word Embeddings.- Semantic Structure of Russian Prepositional Constructions.- Explicit and implicit discourse relations.- On Practical Aspects of Multi-Condition Training based on Augmentation for Reverberation-/Noise-Robust Speech Recognition.- Evaluation of Synthetic Speech by GMM-Based Continuous Detection of Emotional States.- Deep Representation Learning for Orca Call Type Classification.- On Using Stateful LSTM Networks for Key-phrase Detection.- Consonant-to-Vowel/Vowel-to-Consonant Transitions to Analyze the Speech of Cochlear Implant Users.- Czech Speech Synthesis with Generative Neural Vocoder.- Linguistic Resources Construction: Towards Disfluency Processing in Spontaneous Tunisian Dialect Speech.- Comparing Front-end Enhancement Techniques and Multiconditioned Training for Robust Automatic Speech Recognition.-Label-Driven T-F Masking For Robust Speech Command Recognition.- A Comparison of Hybrid and End-to-End Models for Syllable Recognition.- LSTM-based Speech Segmentation for TTS Synthesis.- Spoken language identification using Language Bottleneck Features.- Question-Answering Dialog System for Large Audiovisual Archives.- Crowd-sourced Collection of Task-Oriented Human-Human Dialogues in a Multi-Domain Scenario.
