CCLMDS'96: towards a speaker-independent large-vocabulary Mandarin dictation system
T.H. Chiang, Chung-Mou Pengwu, Shih-Chieh Chien, Chao-Huang Chang · 2002
This paper presents the first known results for the speaker-independent large-vocabulary Mandarin dictation system, namely CCLMDS'96, developed by the Computer and Communication Research Laboratories (CCL) at the Industrial Technology Research Institute (ITRI). First, a fast searching algorithm is proposed to improve the searching efficiency such that the CCLMDS'96 can operate in real time running on a personal computer. In addition, a discriminative scoring function is proposed to integrate the speech recognizer and the word-class-based bigram language model. With this discriminative scoring function, the system attains a word accuracy rate of 91.3%, which significantly outperforms the conventional integration approach.