Sixth European Conference on Speech Communication and Technology, EUROSPEECH 1999, Budapest, Hungary, September 5-9, 1999.
: The controversial connection between speech production and perception: theories vs. facts.
Speech Recognition, Adaptation 1
: Maximum a posterior linear regression with elliptically symmetric matrix variate priors.
: Maximum likelihood sequential adaptation.
Prosody - Prosodic Features in Dialogues
, S. Kobayashi
: Paralinguistic features as suprasegmental acoustics observed in natural Japanese dialogue.
Speech Recognition - Confidence Measures
Speech Recognition - Acoustic Processing
: Robust energy normalization using speech/nonspeech discriminator for German connected digit recognition.
Kuldip K. Paliwal
: Decorrelated and liftered filter-bank energies for robust speech recognition.
, Feili Chen
: The analysis and application of a new endpoint detection method based on distance of autocorrelated similarity#.
Articulatory Measurements and Modelling
: Modeling of the vocal tract in three dimensions.
Slim Ouni And Yves Laprie
: Design of hypercube codebooks for the acoustic-to-articulatory inversion respecting the non-linearities of the articulatory-to-acoustic mapping.
: Estimating velum height from acoustics during continuous speech.
First and Second Language Learning
: Computer-aided spoken-language training with enhanced visual and auditory feedback.
: Pronouncing unknown words using multi-dimensional analogies.
: Characteristics features of planning of speech and production of secondary schoolchildren's spontaneous speech.
Speech Recognition - Adaptation 2
Prosody - Prosodic Phrasing and Interruptions
: Prosodic word boundary detection using mora transition modeling of fundamental frequency contours -speaker independent experiments-.
: Prosodic correlates of interruptions in spoken dialogue.
Speech Recognition - Confidence Measures 2
Eric I. Chang
: Improving rejection with semantic slot-based confidence scores.
, Jean Monné
: Recognition of spelled names over the telephone and rejection of data out of the spelling lexicon.
, Sun-Jeong Lee
: An utterance verification system based on subword modeling for a vocabulary independent speech recognition system.
, Denis Jouvet
: Use of a confidence measure based on frame level likelihood ratios for the rejection of incorrect data.
Speech Analysis and Tools
Michael F. McTear
: Software to support research and development of spoken dialogue systems.
Márcio N. de Souza
, E. J. Caprini
, Glaucio J. Couri Machado
, M. V. Ludolf
, Luiz Pereira Calôba
, José Manoel de Seixas
, Fernando Gil Resende
, Sergio L. Netto
, Diamantino Rui da Silva Freitas
, João Paulo Teixeira
, Carlos Espain
, Vitor Pera
, F. Moreira
: Developing a voiced information retrieval system for the portuguese language capable to handle both brazilian and portuguese spoken versions.
Speech Recognition - Speaking Rate
: Acoustic characteristics of plosives in consonant-consonant sequences at word boundaries.
Speech Recognition - Search and Pronunciation Modelling
: Automatic modeling of pronunciation variations.
: Evaluation of a segmentation system based on multi-level lattices.
Xavier L. Aubert
: One pass cross word decoding for large vocabularies based on a lexical tree search organization.
Prosody - Stress, Accent and Prominence Phrasing
Speech Disorders & Speech for Disabled
Speech Recognition - Multi-stream ASR
Speech Generation and Synthesis - Concatenation
Speech Communication Education
Michael F. McTear
: Curricula and courseware in spoken language engineering in europe: a critical appraisal.
Speech Recognition - Broadcast News
Prosody - Temporal and/or Intonational Features
: Effects of articulation rate on duration in read French speech.
: Developing the database of the spontaneous speech prosody characteristics.
: Whole tunes, nuclear and pre-nuclear patterns and prosodic features in the perception of interrogativity and non-finality in dutch.
Speaker Recognition - Acoustic Features and Robustness
: Speaker recognition by means of a combination of linear and nonlinear predictive models.
Ran D. Zilca
, Yuval Bistritz
: Text independent speaker identification using LSP codebook speaker models and linear discriminant functions.
Speech Recognition - Large Vocabulary Continuous Speech Recognition (LVCSR)
Speech Generation and Synthesis - Systems and Evaluation
Speech Technology for Language Learning
Speech Recognition - Multilinguality
S. M. Ahadi
: Recognition of continuous persian speech using a medium-sized vocabulary speech corpus.
, Pascale Fung
: Decision tree-based triphones are robust and practical for mandarian speech recognition.
Systems, Architectures, Interfaces
Speaker Recognition - Scoring and Decision
Speech Recognition - Broadcast News
Speech Generation and Synthesis - Acoustic Synthesis
: Formant analysis and synthesis using hidden Markov models.
: Accurate estimation of sinusoidal parameters in an harmonic+noise model for speech synthesis.
Disorders in Speech Production and/or Speech Perception
Ramón García Gómez
, Ricardo López Barquilla
, José Ignacio Puertas Tera
, José Parera Bermudez
, Marie-Christine Haton
, Jean Paul Haton
, Pierre Alinat
, Sofia Moreno
, Wolfgang Hess
, Ma Araceli Sanchez Raya
, Eduardo Alberto Martínez Gual
, Juan Luis Navas-Chaveli Daza
, Christophe Antoine
, Marie-Madeleine Durel
, Genevieve Maugin
, Silke Hohmann
: Speech training for deaf and hearing-impaired people.
Speech Recognition - Acoustic Modelling 1
, T. Ross
: Reduced gaussian mixture models in a large vocabulary continuous speech recognizer.
: Mixture trees - hierarchically tied mixture densities for modeling HMM emission probabilities.
Michael L. Shire
: Data-driven modulation filter design under adverse acoustic conditions and using phonetic and syllabic units.
Speaker Recognition and Topic Detection
: Dynamic test durations for text-independent speaker verification systems.
Speech Recognition - Search
: Theory of structured cogitation in speech recognition.
Speech Recognition - Acoustic Modelling 2
Jeff Z. Ma
, Li Deng
: Optimization of dynamic regimes in a statistical hidden dynamic model for conversational speech recognition.
: Task hierarchies representing sub-dialogs in speech dialog systems.