中国語文章の連続音声認識をめざして

概要

論文の詳細を見る
A fundamental speech recognition procedure for continuously spoken simple Chinese sentences is described and the method of specific regions is proposed. Phonemes are identified every 10 ms by extracting numbers of zero-crossings, PARCOR coefficients, F_1 and F_2 etc. from speech waves. In Chinese language, each Chinese character is pronounced as a monosyllable and has definite meaning. Using these characteristics, continuously spoken speech waves are divided into monosyllables, and each vowel segment of monosyllables is partitioned into 8 minor segments. The average first 2 formant frequencies of each first minor vowel segment point out a specific region on the F_1-F_2 plane. Since this region decides a group of monosyllables or Chinese characters which have similar vowels, a monosyllable can be identified from them. Moreover, use of a syntactic state transition network improves recognition scores of sentences. Average recognition scores of 130 characters and 33 sentences uttered by 3 male adults are 90. 7% and 75. 7%, respectively.
社団法人日本音響学会の論文