Voice dictation of Mandarin Chinese

Abstract

The Chinese language is not alphabetic, and input of Chinese characters into computers remains a difficult problem even after decades of efforts made to overcome the problem. Voice dictation of Mandarin Chinese with a very large vocabulary is believed to be the perfect solution, but this is a highly challenging speech recognition problem with many technical issues yet unsolved. The characteristics of Mandarin Chinese, significantly different from those of most alphabetic western languages, lead to the fact that many special measures and unique approaches that consider the feature structure of the language are believed to be the key to providing better solutions to the problem. Such special measures and unique approaches are the primary focus of this article. We analyze the characteristic structure of Mandarin Chinese and discuss related issues. The primary focus is then on the key technology regarding the problem, including the basic architecture for Mandarin dictation, acoustic modeling/processing, and linguistic modeling/processing. Some typical prototype systems, other related applications, and initial industrial efforts and products are presented to indicate the feasibility of the key technology discussed.