|
Invited Talks -- Language Modeling Experiments with Random Forests -- The Role of Speech in Multimodal Human-Computer Interaction -- Why Is the Recognition of Spontaneous Speech so Hard? -- On the Acoustic Components in Multimedia Presentations -- Fusing Data Streams in Continuous Audio-Visual Speech Recognition -- Speech Based User Interface for Users with Special Needs -- Text -- Automatic Construction of a Valency Lexicon of Czech Adjectives -- WebTranscribe – An Extensible Web-Based Speech Annotation Framework -- Learning Syntactic Patterns Using Boosting and Other Classifier Combination Schemas -- Text Classification with Tournament Methods -- New Meta-grammar Constructs in Czech Language Parser synt -- Anaphora in Czech: Large Data and Experiments with Automatic Anaphora Resolution -- Valency Lexicon of Czech Verbs VALLEX: Recent Experiments with Frame Disambiguation -- AARLISS – An Algorithm for Anaphora Resolution in Long-Distance Inter Sentential Scenarios -- Detection and Correction of Malapropisms in Spanish by Means of Internet Search -- The Szeged Treebank -- Automatic Lemmatizer Construction with Focus on OOV Words Lemmatization -- Modeling Syntax of Free Word-Order Languages: Dependency Analysis by Reduction -- Morphological Meanings in the Prague Dependency Treebank 2.0 -- Automatic Acquisition of a Slovak Lexicon from a Raw Corpus -- Equilibrium Points of Single-Layered Neural Networks with Feedback and Applications in the Analysis of Text Documents -- A Syntax and Semantics Linking Algorithm for the Chinese Language -- Fuzzy Information Retrieval Indexed by Concept Identification -- A Theme Allocation for a Sentence Based on Head Driven Patterns -- Speech -- A Hybrid Approach to Statistical Language Modeling with Multilayer Perceptrons and Unigrams -- Supervised and Unsupervised Speaker Adaptation in Large Vocabulary Continuous Speech Recognition of Czech -- Modelling Lexical Stress -- The Sound Database Formation for the Allophone-Based Model for English Concatenative Speech Synthesis -- Using Artificially Reverberated Training Data in Distant-Talking ASR -- French–German Bilingual Acoustic Modeling for Embedded Voice Driven Applications -- Sinusoidal Modeling Using Wavelet Packet Transform Applied to the Analysis and Synthesis of Speech Signals -- Speaker Identification Based on Subtractive Clustering Algorithm with Estimating Number of Clusters -- On Modelling Glottal Stop in Czech Text-to-Speech Synthesis -- Analysis of the Suitability of Common Corpora for Emotional Speech Modeling in Standard Basque -- Discrete and Fluent Voice Dictation in Czech Language -- Unit Selection for Speech Synthesis Based on Acoustic Criteria -- Generative Model for Decoding a Phoneme Recognizer Output -- Diction Based Prosody Modeling in Table-to-Speech Synthesis -- Phoneme Based Acoustics Keyword Spotting in Informal Continuous Speech -- Explicit Duration Modelling in HMM/ANN Hybrids -- Mapping the Speech Signal onto Electromagnetic Articulography Trajectories Using Support Vector Regression -- Automatic Transcription of Numerals in Inflectional Languages -- Experimental Evaluation of Tree-Based Algorithms for Intonational Breaks Representation -- Compact Representation of Speech Using 2-D Cepstrum – An Application to Slovak Digits Recognition -- An Alternative Way of Semantic Interpretation -- Robust Rule-Based Method for Automatic Break Assignment in Russian Texts -- of Improved UWB Speaker Verification System -- Formal Prosodic Structures and Their Application in NLP -- The VoiceTRAN Speech-to-Speech Communicator -- Dialogue -- Cluster Analysis of Railway Directory Inquire Dialogs -- A Framework for Rapid Multimodal Application Design -- Language-Independent Communication Using Icons on a PDA -- Software Tutors for Dialogue Systems -- Questions in Estonian Information Dialogues: Form and Functions -- Reducing Question Answering Input Data Using Named Entity Recognition -- Annotating Structural Constraints in Discourse Corpora -- A Passage Retrieval System for Multilingual Question Answering -- Error Analysis of Dialogue Act Classification. TheInternationalConferenceTSD 2005,the8theventin theseriesonText,Speech,and Dialogue, which originated in 1998, presented state-of-the-art technology and recent achievements in the ?eld of natural language processing. It declared its intent to be an interdisciplinary forum, intertwining research in speech and language processing with its applications in everyday practice. We feel that the mixture of different approaches and applications offered a great opportunity to get acquainted with the current act- ities in all aspects of language communication and to witness the amazing vitality of researchers from developing countries too. The ?nancial support of the ISCA (Inter- tional Speech Communication Association) enabled the wide attendance of researchers from all active regions of the world. Thisyear’sconferencewaspartiallyorientedtowardsmulti-modalhuman-computer interaction (HCI), which can be seen as the most attractive topic of HCI at the present time. In this way, we are involved in a rich complex of communicative activity, facial expressions, hand gestures, direction of gaze, to name but the most obvious ones. The interpretationof each user utterancedependson the context,prosody,facial expressions (e. g. brows raised, brows and gaze both raised) and gestures. Hearers have to adapt to the speaker (e. g. maintainingthe theme of the conversation,smiling etc. ). Research into the interaction of these channels is however limited, often focusing on the interaction between a pair of channels. Six signi?cant scienti?c results achieved in this area in the USA, Japan, Switzerland, Germany, The Netherlands, and the Czech Republic were presented by keynote speakers in special plenary sessions. Further, approx.
|
