%0 Journal Article
%T Research and Implementation of the Techniques for Chinese Dictation Machines<br>汉语语音听写机技术的研究与实现
%A ZHENG Fang
%A MU Xiao-long
%A XU Ming-xing
%A WU Jian
%A SONG Zhan-jiang
%A <br>郑方
%A 牟晓隆
%A 徐明星
%A 武健
%A 宋战江
%J 软件学报
%D 1999
%I 
%X In this paper, the search strategies in the acoustic layer of the CSR (continuous speech recognition) and the CDM (Chinese dictation machine) are addressed in two aspects, the acoustic recognition unit and the syntax-constrained word search tree. The SKB-FSS (statistical knowledge based frame synchronous search) algorithm and the syntax-constrained WST (word search tree) structure are proposed, they form the TLSN (two-level search network) in the acoustic layer. The statistical knowledge used by the algorithm includes differential state dwell distribution, the feature difference sum and so on, which result in an improvement of 36.6% in CSR. The principles of a modified back-off estimation algorithm and the search algorithms for the N-gram based language models are also introduced. Finally, by integrating the authors' techniques, a Chinese dictation machine engine (CDME) is implemented. A speaker-independent CDM text editor named ST97 and a voice command system named CMD97 are established for personal computers (PCs) based on the CDME.
%K CSR (Continuous speech recognition)
%K CDM (Chinese dictation machine)
%K search strategy
%K SKB-FSS (statistical knowledge based frame synchronous search) algorithm
%K differential state dwell
%K feature difference sum
%K WST (word search tree)
%K TLSN (two-level sear<br>连续语音识别
%K 汉语语音听写机
%K 搜索策略
%K 基于统计知识的帧同步搜索算法
%K 差分状态驻留
%K 特征变化量
%K 词搜索树
%K 双层搜索网络
%K 汉语语音听写机引擎
%K 语音命令.
%U http://www.alljournals.cn/get_abstract_url.aspx?pcid=5B3AB970F71A803DEACDC0559115BFCF0A068CD97DD29835&cid=8240383F08CE46C8B05036380D75B607&jid=7735F413D429542E610B3D6AC0D5EC59&aid=CE5E4C17E93F65FA&yid=B914830F5B1D1078&vid=F3090AE9B60B7ED1&iid=E158A972A605785F&sid=08076B8B3CC96095&eid=68FDAD96FCC0AB1B&journal_id=1000-9825&journal_name=软件学报&referenced_num=3&reference_num=44