Bulletin of the Electrotechnical Laboratory, Vol. 54, No. 7, 1990. Special Issue on Speech Research

摘要

The special issue on speech research contains: Word Recognition System Using Network Representation of Acoustic Phonetic Segments; Observation of Formant Transition in the Vicinity of Consonants in Continuous Speech; Hierarchical Representation of Speech in Symbolic Domain and Fine Phonetic Labeling; Relative Formant Changes of Dentals and Alveolars in Japanese CV and VCV Syllables; Re-Categorization of Pseudo-Phoneme as a Synthesis-Unit; Consonant Discrimination Using the Formant Coarticulation Model; Phonetic Network Representation of Phoneme Sequences Based on CVC-Unit Concatenation; New Vowel Spectrum Interpolation Method by Articulatory Parameters, Considering Vowel Durations; Consonant Classification in Continuous Speech Using Neural Networks; CVC-Based Network Representation of Phoneme Sequences with Applications to Spoken Word Recognition; Voiced-Unvoiced Classification Using Weighted Distance Measures; New Vowel Spectrum Interpolation Method Using Articulatory Parameters; Neural Network Application for Time Sequence Data; and Estimation Accuracy of the Symmetrical Axis of Antimetrical Vocal Tract Shapes and Discrimination Rates among Japanese Vowels.