Text, Speech and Dialogue Book

	Language modeling experiments with random forests	1
	The role of speech in multimodal human-computer interaction	2
	Why is the recognition of spontaneous speech so hard?	9
	On the acoustic components in multimedia presentations	23
	Fusing data streams in continuous audio-visual speech recognition	33
	Speech based user interface for users with special needs	45
	Automatic construction of a valency lexicon of Czech adjectives	56
	WebTranscribe - an extensible Web-based speech annotation framework	61
	Learning syntactic patterns using boosting and other classifier combination schemas	69
	Text classification with tournament methods	77
	New mete-grammar constructs in Czech language parser synt	85
	Anaphora in Czech : large data and experiments with automatic anaphora resolution	93
	Valency lexicon of Czech verbs VALLEX : recent experiments with frame disambiguation	99
	AARLISS - an algorithm for anaphora resolution in long-distance inter sentential scenarios	107
	Detection and correction of malapropisms in Spanish by means of Internet search	115
	The Szeged treebank	123
	Automatic lemmatizer construction with focus on OOV words lemmatization	132
	Modeling syntax of free word-order languages : dependency analysis by reduction	140
	Morphological meanings in the Prague dependency treebank 2.0	148
	Automatic acquisition of a Slovak lexicon from a raw corpus	156
	Equilibrium points of single-layered neural networks with feedback and applications in the analysis of text documents	164
	A syntax and semantics linking algorithm for the Chinese language	171
	Fuzzy information retrieval indexed by concept identification	179
	A theme allocation for a sentence based on head driven patterns	187
	A hybrid approach to statistical language modeling with multilayer perceptrons and unigrams	195
	Supervised and unsupervised speaker adaptation in large vocabulary continuous speech recognition of Czech	203
	Modelling lexical stress	211
	The sound database formation for the allophone-based model for English concatenative speech synthesis	219
	Using artificially reverberated training data in distant-talking ASR	226
	French-German bilingual acoustic modeling for embedded voice driven applications	234
	Sinusoidal modeling using wavelet packet transform applied to the analysis and synthesis of speech signals	241
	Speaker identification based on subtractive clustering algorithm with estimating number of clusters	249
	On modelling glottal stop in Czech text-to-speech synthesis	257
	Analysis of the suitability of common corpora for emotional speech modeling in standard Basque	265
	Discrete and fluent voice dictation in Czech language	273
	Unit selection for speech synthesis based on acoustic criteria	281
	Generative model for decoding a phoneme recognizer output	288
	Diction based prosody modeling in table-to-speech synthesis	294
	Phoneme based acoustics keyword spotting in informal continuous speech	302
	Explicit duration modelling in HMM/ANN hybrids	310
	Mapping the speech signal onto electromagnetic articulography trajectories using support vector regression	318
	Automatic transcription of numerals in inflectional languages	326
	Experimental evaluation of tree-based algorithms for intonational breaks representation	334
	Compact representation of speech using 2-D cepstrum - an application to Slovak digits recognition	342
	An alternative way of semantic interpretation	348
	Robust rule-based method for automatic break assignment in Russian texts	356
	Introduction of improved UWB speaker verification system	364
	Formal prosodic structures and their application in NLP	371
	The VoiceTRAN speech-to-speech communicator	379
	Cluster analysis of railway directory inquire dialogs	385
	A framework for rapid multimodal application design	393
	Language-independent communication using icons on a PDA	404
	Software tutors for dialogue systems	412
	Questions in Estonian information dialogues : form and functions	420
	Reducing question answering input data using named entity recognition	428
	Annotating structural constraints in discourse corpora	435
	A passage retrieval system for multilingual question answering	443
	Error analysis of dialogue act classification	451