Text, Speech and Dialogue: 7th International Conference, TSD 2004, Brno, Czech Republic, September 8-11, 2004, Proceedings Book

	Speech and language processing : can we use the past to predict the future?	3
	Common sense about word meaning : sense in context	15
	ScanSoft's technologies	19
	A positional linguistics-based system for word alignment	23
	Handling multi-word expressions without explicit linguistic rules in an MT system	31
	The Szeged corpus : a POS tagged and syntactically annotated Hungarian natural language corpus	41
	Item summarization in personalisation of news delivery systems	49
	IR-n system, a passage retrieval architecture	57
	Event clustering in the news domain	65
	HANDY : sign language synthesis from sublexical elements based on an XML data representation	73
	Using linguistic resources to construct conceptual graph representation of texts	81
	Slovak national corpus	89
	Grammatical heads optimized for parsing and their comparison with linguistic intuition	95
	How dominant is the commonest sense of a word?	103
	POS tagging of Hungarian with combined statistical and rule-based methods	113
	Grammatical relations identification of Korean parsed texts using support vector machines	121
	Clustering abstracts instead of full texts	129
	Bayesian reinforcement for a probabilistic neural net part-of-speech tagger	137
	Automatic language identification using phoneme and automatically derived unit strings	147
	Slovak text-to-speech synthesis in ARTIC system	155
	Identifying semantic roles using maximum entropy models	163
	A lexical grammatical implementation of affect	171
	Towards full lexical recognition	179
	Discriminative models of SCFG and STSG	187
	Coupling grammar and knowledge base : range concatenation grammars and description logics	195
	Balancing manual and automatic indexing for retrieval of paper abstracts	203
	Unsupervised learning of rules for morphological disambiguation	211
	Ambiguous supertagging using a feature structure	217
	A practical word sense disambiguation system with high performance for Korean	225
	Morphological tagging of Russian texts of the XIX[superscript th] century	235
	Large vocabulary continuous speech recognition for Estonian using morphemes and classes	245
	A new classifier for speaker verification based on the fractional Brownian motion process	253
	A universal human machine speech interaction language for robust speech recognition applications	261
	Embedded via voice	269
	New speech enhancement approach for formant evolution detection	275
	Measurement of complementarity of recognition systems	283
	Text-to-speech for Slovak language	291
	Speaker verification based on wavelet packets	299
	A decoding algorithm for speech input statistical translation	307
	Aggregation operators and hypothesis space reductions in speech recognition	315
	Combinations of TRAP based systems	323
	Automatic recognition and evaluation of tracheoesophageal speech	331
	Using neural networks to model prosody in Czech TTS system epos	339
	Auditory scene analysis via application of ICA in a time-frequency domain	347
	Using the Lemmatization technique for phonetic transcription in text-to-speech system	355
	Automatic categorization of voicemail transcripts using stochastic language models	363
	Low latency real-time vocal tract length normalization	371
	Multimodal phoneme recognition of meeting data	379
	A new multi-modal database for developing speech recognition systems for an assistive technology application	385
	Obtaining and evaluating an emotional database for prosody modelling in standard Basque	393
	Fully automated approach to broadcast news transcription in Czech language	401
	A computational model of intonation for Yoruba text-to-speech synthesis : design and analysis	409
	Dynamic unit selection for very low bit rate coding at 500 bits/sec	417
	On the background model construction for speaker verification using GMM	425
	A speaker clustering algorithm for fast speaker adaptation in continuous speech recognition	433
	Advanced prosody modelling	441
	Voice stress analysis	449
	Slovak speech database for experiments and application building in unit-selection speech synthesis	457
	Towards lower error rates in phoneme recognition	465
	Examination of pronunciation variation from hand-labelled corpora	473
	New refinement schemes for voice conversion	481
	Acoustic and linguistic information based Chinese prosodic boundary labelling	489
	F0 prediction model of speech synthesis based on template and statistical method	497
	An architecture for spoken document retrieval	505
	Evaluation of the Slovenian HMM-based speech synthesis system	513
	Modeling prosodic structures in linguistically enriched environments	521
	Parallel root-finding method for LPC analysis of speech	529
	Automatic general letter-to-sound rules generation for German text-to-speech system	537
	Pitch accent prediction from ToBI annotated corpora based on Bayesian learning	545
	Processing of logical expressions for visually impaired users	553
	Durational aspects of turn-taking in spontaneous face-to-face and telephone dialogues	563
	A speech platform for a bilingual city information system	571
	Rapid dialogue prototyping methodology	579
	Building voice applications from Web content	587
	Information-providing dialogue management	595
	Realistic face animation for a Czech talking head	603
	Evaluation of a Web based information system for blind and visually impaired students : a descriptive study	611
	Multimodal dialogue management	621
	Looking at the last two turns, I'd say this dialogue is doomed - measuring dialogue success	629
	Logical approach to natural language understanding in a spoken dialogue system	637
	Building a dependency-based grammar for parsing informal mathematical discourse	645