Text, Speech, and Dialogue

Invited Talks.- Corpora of the Russian Language.- Long, Deep and Wide Artificial Neural Nets for Dealing with Unexpected Noise in Machine Recognition of Speech.- Multilingual Media Monitoring and Text Analysis – Challenges for Highly Inflected Languages.- Spoken Dialogs with Children for Science Learning and Literacy.- Statecharts and SCXML for Dialogue Management.- Conference Papers.- A Comparison of Deep Neural Network Training Methods for Large Vocabulary Speech Recognition.- A Comparison of Two Approaches to Bilingual HMM-based Speech Synthesis.- A Direct Criterion Minimization Based fMLLR via Gradient Descend.- A Machine Learning Based Approach for Vocabulary Selection for Speech Transcription.- A New State-Of-The-Art Czech Named Entity Recognizer.- Algorithms for Dysfluency Detection in Symbolic Sequences Using Suffix Arrays.- Analysis and Combination of Forward and Backward Based Decoders for Improved Speech Transcription.- Annotating Signs of Syntactic Complexity to Support Sentence Simplification.- Application of LSTM Neural Networks in Language Modelling.- Automatic Laughter Detection in Spontaneous Speech Using GMM–SVM Method.- Automatic Machine Translation Evaluation with Part-of-Speech Information.- Automatic Extraction of Polish Language Errors from Text Edition History.- Bilingual Voice Conversion by Weighted Frequency Warping Based on Formant Space.- Building a Hybrid: Chatterbot – Dialog System.- CRF-based Czech Named Entity Recognizer and Consolidation of Czech NER Research.- Comparison and Analysis of Several Phonetic Decoding Approaches.- Concatenation Artifact Detection Trained from Listeners Evaluations.- Configuring TTS Evaluation Method Based on Unit Cost Outlier Detection.- Development and Evaluation of Spoken Dialog Systems with One or Two Agents Through Two Domains.- Distant Supervision Learning of DBPedia Relations.- Downdating Lexicon and Language Model for Automatic Transcription of Czech Historical Spoken Documents.- Dynamic Threshold Selection Method for Multi-label Newspaper Topic Identification.- Efficiency of Multi-tap Text Entry Method on Interactive Television.- English Nominal Compound Detection with Wikipedia-Based Methods.- Evaluating Voice Quality and Speech Synthesis Using Crowdsourcing.- Experiment with Evaluation of Quality of the Synthetic Speech by the GMM Classifier.- Experiments on Reducing Footprint of Unit Selection TTS System.- Expressive Speech Synthesis for Urgent Warning Messages Generation in Romani and Slovak.- Extracting Relations Between Arabic Named Entities.- Foot Detection in Czech Using Pitch Information and HMM.- Improved Hungarian Morphological Disambiguation with Tagger Combination.- Improving Dependency Parsing by Filtering Linguistic Noise.- Improving Speech Recognition by Detecting Foreign Inclusions and Generating Pronunciations.- Intensifying verb prefix patterns in Czech and Russian.- K-component Adaptive Recurrent Neural Network Language Models.- LIUM ASR System for ETAPE French Evaluation Campaign: Experiments on System Combination Using Open-source Recognizers.- Lexical Stress-based Morphological Decomposition and Its Application for Ukrainian Speech Recognition.- Motion Event in Croatian, English, German and Italian Concerning Path Prefixes and Prepositions.- Multi-label Document Classification in Czech.- On Behaviour of PLDA Models in the Task of Speaker Recognition.- On the Quantitative and Qualitative Speech Changes of the Czech Radio Broadcasts News within Years 1969-2005.- On the Use of Phoneme Lattices in Spoken Language Understanding.- Online Speaker Adaptation of an Acoustic Model Using Face Recognition.- Ontology of Rhetorical Figures for Serbian.- Phoneme Set and Pronouncing Dictionary Creation for Large Vocabulary Continuous Speech Recognition of Vietnamese.- Phonetic Spoken Term Detection in Large Audio Archive Using the WFST Framework.- Ranking Machine Translation Systems via Post-Editing.- Recursive Part-of-Speech Tagging Using Word Structures.- Resolving Ambiguities in Sentence Boundary Detection in Russian Spontaneous Speech.- Revealing Prevailing Semantic Contents of Clusters Generated from Untagged Freely Written Text Documents in Natural Languages.- Robust Methodology for TTS Enhancement Evaluation.- Romanian Syllabication Using Machine Learning.- SVM-Based Detection of Misannotated Words in Read Speech Corpora.- Scratching the Surface of Possible Translations.- Selecting and Weighting N-Grams to Identify 1100 Languages.- Semantic Spaces for Sentiment Analysis.- Semi-automatic Verb Valence Frame Assignment Through VerbNet Classification.- Speaker-specific Pronunciation for Speech Synthesis.- Structuring a Multimedia Tri-dialectal Dictionary.- Stylistic Changes for Temporal Text Classification.- SummEC: A Summarization Engine for Czech.- Text-to-Speech Alignment for Imperfect Transcriptions.- The CNG Corpus of European Portuguese Children’s Speech.- The Joint Optimization of Spectro-Temporal Features and Neural Net Classifiers.- Three Syntactic Formalisms for Data-Driven Dependency Parsing of Croatian.- Topic Models for Comparative Summarization.- Using Low-Cost Annotation to Train a Reliable Czech Shallow Parser.- Verb Subcategorisation Acquisition for Estonian Based on Morphological Information.- Whispered Speech Database: Design, Processing and Application.