INTERSPEECH 2004 - ICSLP, 8th International Conference on Spoken Language Processing, Jeju Island, Korea, October 4-8, 2004. ISCA 2004
: From decoding-driven to detection-based paradigms for automatic speech recognition.
: In search of a universal phonetic alphabet - theory and application of an organic visible speech-.
: From X-ray or MRU data to sounds through articulatory synthesis: towards an integrated view of the speech communication process.
Speech Recognition - Adaptation
, Rita Singh
: Maximum - likelihod adaptation of semi-continuous HMMs by latent variable decomposition of state distributions.
: Acoustic model adaptation based on coarse/fine training of transfer vectors and its application to a speaker adaptation task.
Hyung Soon Kim
, Hwa Jeon Song
: Simultaneous estimation of weights of eigenvoices and bias compensation vector for rapid speaker adaptation.
: Speaker dependent model order selection of spectral envelopes.
, Zhenyang Wu
: Mean and covariance adaptation based on minimum classification error linear regression for continuous density HMMs.
Spoken Language Identification, Translation and Retrieval I
: ACCDIST: a metric for comparing speakers' accents.
, Febe de Wet
: Histogram normalisation and the recognition of names and ontology words in the MUMIS project.
Linguistics, Phonology, and Phonetics
: Correlation between VOT and F0 in the perception of Korean stops and affricates.
: Data-driven approaches for automatic detection of syllable boundaries.
, Tae-Yeoub Jang
: A comparative study on the production of inter-stress intervals of English speech by English native speakers and Korean speakers.
: Effects of phonetic contexts on the duration of phonetic segments in fluent read speech.
: A study on nasal coda los in continuous speech.
: An improved pair-wise variability index for comparing the timing characteristics of speech.
: An acoustic study of speech rhythm in taiwan English.
: Language specific phonetic rules: evidence from domain-initial strengthening.
: Spectral characteristics of the release bursts in Korean alveolar stops.
: Phonology of exceptions for for Korean grapheme-to-phoneme conversion.
: A cross-linguistic acoustic comparison of unreleased word-final stops: Korean and Thai.
, James M. McQueen
: Phonotactics vs. phonetic cues in native and non-native listening: dutch and Korean listeners' perception of dutch and English.
, Kee-Ho Kim
: Phonetic realization of the suffix-suppressed accentual phrase in Korean.
: Pronunciation assessment based upon the compatibility between a learner's pronunciation structure and the target language's lexical structure.
Biomedical Applications of Speech Analysis
Robust Speech Recognition on AURORA
Hugo Van hamme
: PROSPECT features and their application to missing data techniques for robust speech recognition.
, Bo Xu
: Exploring high-performance speech recognition in noisy environments using high-order taylor series expansion.
, Lin-Shan Lee
: A new feature extraction front-end for robust speech recognition using progressive histogram equalization and multi-eigenvector temporal filtering.
Spoken / Multimodal Dialogue System
, Minkyu Lee
, Hui Jiang
: Constrained minimization technique for topic identification using discriminative training and support vector machines.
: Contextual revision in information seeking conversation systems.