Banff, Alberta, Canada
The Second International Conference on Spoken Language Processing, ICSLP 1992, Banff, Alberta, Canada, October 13-16, 1992. ISCA 1992
Patricia K. Kuhl
: Infants' perception and representation of speech: development of a new theory.
: The behavior of the larynx in spoken language production.
: Low-rate speech coding based on time-frequency interpolation.
Unto K. Laine
: Speech analysis using complex orthogonal auditory transform (coat).
, Nathan Intrator
: Phonetic classification of timit segments preprocessed with lyon's cochlear model using a supervised/unsupervised hybrid neural network.
Recognition of Telephone Speech
Text-to-Speech Synthesis 1, 1
Voice Source Characteristics
Higher-Order Processes 1, 1
: Antecedent activation by empty pronominals in Spanish.
: Multiple feature matching in pronoun resolution: a new look at parallel function.
Speaker-Independent Word Recognition
S. M. (Raj) Ulagaraj
: Characterization of directory assistance operator-customer dialogues in AGT limited.
Continuous Speech Recognition 1, 2
, Kenji Kita
, Toshiyuki Hanazawa
, Tadashi Suzuki
, Tomohiro Iwasaki
, Tsuyoshi Kawabata
, Kunio Nakajima
, Kiyohiro Shikano
, Tsuyoshi Morimoto
, Shigeki Sagayama
, Akira Kurematsu
: Hardware implementation of realtime 1000-word HMM-LR continuous speech recognition.
, Shozo Makino
: Word pre-selection using a redundant hash addressing method for continuous speech recognition.
Natural Language Processing and Speech Understanding 1-3
, Seiichi Nakagawa
: A frame-synchronous continuous speech recognition algorithm using a top-down parsing of context-free grammar.
: Using probabilistic shift-reduce parsing in speech recognition systems.
: Integrating two complementary approaches to spoken language understanding.
: Continuous speech recognition using a combination of syntactic constraints and dependency relationship.
Language Learning and Acquisition 1, 2
: Phonology as a byproduct of learning to recognize and produce words: a connectionist model.
Units of Processing
The Phrase and Beyond 1, 2
: Modeling sentential stress in the context of a large vocabulary continuous speech recognizer.
Self-Organizing Systems in ASR 1, 2
: Self-organizing map with supervision for speech recognition.
Helge B. D. Sørensen
: Context-dependent and -independent self-structuring hidden control models for speech recognition.
, Kari Torkkola
: Application of self-organizing maps and LVQ in training continuous density hidden Markov models for phonemes.
, Ove Andersen
: Identification of mono- and poly-phonemes using acoustic-phonetic features derived by a self-organising neural network.