Text, Speech and Dialogue: 11th International Conference, TSD 2008, Brno, Czech Republic, September 8-12, 2008, Proceedings

ISBN-13: 9783540873907 / Angielski / Miękka / 2008 / 667 str.

Petr Sojka;Aleš Horák;Ivan Kopecek

Opis

Constitutes the refereed proceedings of the 11th International Conference on Text, Speech and Dialogue, TSD 2008, held in Brno, Czech Republic, September 8-12, 2008. The topics of the conference include, but are not limited to, text corpora and tagging; transcription problems in spoken corpora; and links between text and speech oriented systems.

Spis treści

Invited Papers.- The Future of Text-Meaning in Computational Linguistics.- Deep Lexical Semantics.- Toward the Ultimate ASR Language Model.- Practical Prosody.- Text.- Sentiment Detection Using Lexically-Based Classifiers.- First Steps in Building a Verb Valency Lexicon for Romanian.- Hyponymy Patterns.- Temporal Issues and Recognition Errors on the Capitalization of Speech Transcriptions.- Web-Based Lemmatisation of Named Entities.- Combining Multiple Resources to Build Reliable Wordnets.- Active Tags for Semantic Analysis.- Spoken Requests for Tourist Information.- Affisix: Tool for Prefix Recognition.- Variants and Homographs.- An Empirical Bayesian Method for Detecting Out of Context Words.- Semantic Classes in Czech Valency Lexicon.- A Comparison of Language Models for Dialog Act Segmentation of Meeting Transcripts.- New Methods for Pruning and Ordering of Syntax Parsing Trees.- Web People Search with Domain Ranking.- Disyllabic Chinese Word Extraction Based on Character Thesaurus and Semantic Constraints in Word-Formation.- Statistical Word Sense Disambiguation in Contexts for Russian Nouns Denoting Physical Objects.- Where Do Parsing Errors Come From.- Dealing with Small, Noisy and Imbalanced Data.- Statistical Properties of Overlapping Ambiguities in Chinese Word Segmentation and a Strategy for Their Disambiguation.- The Verb Argument Browser.- Thinking in Objects.- Improving Unsupervised WSD with a Dynamic Thesaurus.- Normalization of Temporal Information in Estonian.- Word Sense Disambiguation with Semantic Networks.- A Pattern-Based Framework for Uncertainty Representation in Ontologies.- MSD Recombination for Statistical Machine Translation into Highly-Inflected Languages.- A Computational Framework to Integrate Different Semantic Resources.- Speech.- Age Determination of Children in Preschool and Primary School Age with GMM-Based Supervectors and Support Vector Machines/Regression.- Language Acquisition: The Emergence of Words from Multimodal Input.- A Tagged Corpus-Based Study for Repeats and Self-repairs Detection in French Transcribed Speech.- Study on Speaker Adaptation Methods in the Broadcast News Transcription Task.- Spoken Document Retrieval Based on Approximated Sequence Alignment.- Pitch Accents, Boundary Tones and Contours: Automatic Learning of Czech Intonation.- On the Use of MLP Features for Broadcast News Transcription.- Acoustic Modeling for Speech Recognition in Telephone Based Dialog System Using Limited Audio Resources.- Performance Evaluation for Voice Conversion Systems.- Influence of Reading Errors on the Text-Based Automatic Evaluation of Pathologic Voices.- Czech Pitch Contour Modeling Using Linear Prediction.- Energy Normalization in Automatic Speech Recognition.- HMM-Based Speech Synthesis for the Greek Language.- Advances in Acoustic Modeling for the Recognition of Czech.- Talking Head as Life Blog.- The Module of Morphological and Syntactic Analysis SMART.- An Extension to the Sammon Mapping for the Robust Visualization of Speaker Dependencies.- Analysis of Hypernasal Speech in Children with Cleft Lip and Palate.- Syllable Based Language Model for Large Vocabulary Continuous Speech Recognition of Polish.- Accent and Channel Adaptation for Use in a Telephone-Based Spoken Dialog System.- Efficient Unit-Selection in Text-to-Speech Synthesis.- Prosodic Events Recognition in Evaluation of Speech-Synthesis System Performance.- UU Database: A Spoken Dialogue Corpus for Studies on Paralinguistic Information in Expressive Conversation.- Perceptually Motivated Sub-band Decomposition for FDLP Audio Coding.- Forced-Alignment and Edit-Distance Scoring for Vocabulary Tutoring Applications.- Exploiting Contextual Information for Speech/Non-Speech Detection.- Identification of Speakers from Their Hum.- Reverse Correlation for Analyzing MLP Posterior Features in ASR.- Acquisition of Telephone Data from Radio Broadcasts with Applications to Language Recognition.- Multilingual Weighted Codebooks for Non-native Speech Recognition.- Prosodic Phrases and Semantic Accents in Speech Corpus for Czech TTS Synthesis.- Making Speech Technologies Available in (Serviko) Romani Language.- Emulating Temporal Receptive Fields of Higher Level Auditory Neurons for ASR.- A Framework for Language-Independent Analysis and Prosodic Feature Annotation of Text Corpora.- Quantification of Segmentation and F0 Errors and Their Effect on Emotion Recognition.- Deep Syntactic Analysis and Rule Based Accentuation in Text-to-Speech Synthesis.- Error Prediction-Based Semi-automatic Segmentation of Speech Databases.- Dialogue.- Cognitive and Emotional Interaction.- Architecture Model and Tools for Perceptual Dialog Systems.- The Generation of Emotional Expressions for a Text-Based Dialogue Agent.- Intelligent Voice Navigation of Spreadsheets.- A Semi-automatic Wizard of Oz Technique for Let’sFly Spoken Dialogue System.- Developing a Dialogue System.- Dialogue-Based Processing of Graphics and Graphical Ontologies.- An Issue-Based Approach to Information Search Modelling: Analysis of a Human Dialog Corpus.- Two-Level Fusion to Improve Emotion Classification in Spoken Dialogue Systems.- Automatic Semantic Annotation of Polish Dialogue Corpus.- Evaluation of the Slovak Spoken Dialogue System Based on ITU-T.- Shedding Light on a Troublesome Issue in NLIDBS.- Dialogue Based Text Editing.- SSML for Arabic Language.

Blurb

This book constitutes the refereed proceedings of the 11th International Conference on Text, Speech and Dialogue, TSD 2008, held in Brno, Czech Republic, September 8-12, 2008.

The 79 revised full papers presented together with 4 invited papers were carefully reviewed and selected from 173 submissions. The topics of the conference include, but are not limited to, text corpora and tagging; transcription problems in spoken corpora; sense disambiguation; links between text and speech oriented systems; parsing issues; parsing problems in spoken texts; multi-lingual issues; multi-lingual dialogue systems; information retrieval and information extraction; text/topic summarization; machine translation; semantic networks and ontologies; semantic web; speech modeling; speech segmentation; speech recognition; search in speech for IR and IE; text-to-speech synthesis; dialogue systems; development of dialogue strategies; prosody in dialogues; emotions and personality modeling; user modeling; knowledge representation in relation to dialogue systems; assistive technologies based on speech and dialogue; applied systems and software; facial animation; and  visual speech synthesis