Large Vocabulary Continuous Speech Recognition of Uyghur

摘要：

In this paper, we introduce statistical models of word sequences, a rudimentary language model, particularly with some probability theory for language modeling and design a trigram language modeling program based on. Then we use this program to calculate trigram, bigram and unigram probabilities based on the corpus of the entire text of the novel Qum basqan shelter.

关键词： Uyghur thrigram language model HMM speech recognition OOV

作者: Muhetaer Shadike LI Xiao Muhetaer Shadike Buheliqiguli Wasili

作者单位: The Xinjiang Technical Inistitute of Physics & Chemistry Urumchi, China Graduate School, Chinese Academy of Sciences Beijing, China Xinjiang Education Institute Urumchi, China

会议类型: 国际会议

会议名称: 2010 International Conference on Measurement and Control Engineering(2010年IEEE测量与控制工程国际会议 ICMCE2010)

会议地点: 成都

会议语种:英文

页码: 753-757

在线出版日期: 2010-11-16（万方平台首次上网日期，不代表论文的发表时间）