National Taiwan University DEPT ELECT ENGNLee, Lin-ShanLin-ShanLeeTseng, Chiu-YuChiu-YuTsengChen, K.J.K.J.ChenHuang, JamesJamesHuangHwang, Chia-HwaChia-HwaHwangTing, Pei-YihPei-YihTingLin, Long-JiLong-JiLinChen, C.C.C.C.Chen2006-11-142018-07-062006-11-142018-07-061990-07http://ntur.lib.ntu.edu.tw//handle/246246/200611150121461This correspondence describes the first experimental Mandarin dictation machine developed in the world for the input of Mandarin speech (spoken Chinese language) into computers. Considering the special characteristics of the Chinese language, syllables are chosen as the basic units for dictation. The machine is designed based on a hierarchical language recognition approach, in which acoustic signals are first recognized as a sequence of syllables, possible word hypotheses are then formed from the syllables, and the complete sentences are finally obtained. This approach is implemented by two subsystems. The first recognizes the syllables using speech signal processing techniques, including the recognition of the finals, initials, and tones of the syllables, respectively. Because every syllable can represent many different characters with completely different meaning, and can possibly form different multisyllabic words with syllables on its right or left, the second subsystem then identifies the exact characters from the syllables and corrects the errors in syllable recognition by first forming all possible word hypotheses from the syllables then finding out one combination of the word hypotheses which is grammatically valid in a sentence. The detailed syllable recognition algorithms, word formation rules, parser, grammar, and the syntactic checking algorithms are described in the correspondence. Using everyday newspaper text in the form of isolated syllables as input, the preliminary test results indicate that such a dictation machine is not only practically attractive, but technically achievable.application/pdf1254528 bytesapplication/pdfzh-TWChart parserhierarchical approachMandarin Chinesenatural languagespeech recognitionsyllablessyntactic checkingword hypothesesjournal articlehttp://ntur.lib.ntu.edu.tw/bitstream/246246/200611150121461/1/10598.pdf