期刊文献+

基于DDBHMM的维吾尔语音声学识别

Uyghur Speech Acoustics Recognition Based on DDBHMM
下载PDF
导出
摘要 在维吾尔语连续语音识别试验的声学层建模基础上,引用DDBHMM模型将上下文相关的三音子作为基本识别单元,并提出一种状态绑定的思想,对状态进行优化。为得到更充分的训练模型,提高识别效率,对语料库进行扩充,在多组对比试验的基础上,分析扩充前后对声学层识别速度、准确率等各个方面的影响。 DDBHMM(Duration Distribution Based HMM) is adopted as the acoustic model for Uyghur continuous speech recognition, and the context-dependent triphone model is selected as the best recognition unit, the Uyghur speech recognition system is optimised by using the state-binding method. In order to make the models be trained more sufficiently to improve the recognition performance, the corpus is enlarged, the emphasis is on analysis of the effect that the speech database's enlargement brings to the recognition rate and accuracy and so on based on several groups of contrasted experiments.
出处 《计算机工程》 CAS CSCD 北大核心 2011年第2期197-199,共3页 Computer Engineering
基金 国家自然科学基金资助项目(60762006 60863008) 国家语委基金资助重点项目(MZ115-75)
关键词 语料库 维吾尔语 DDBHMM模型理论 三音子 corpus Uyghur DDBHMM model theory triphone
  • 相关文献

参考文献6

二级参考文献12

  • 1齐士钤 张家禄.汉语普通话辅音音长分析[J].声学学报,1982,(1):8-13.
  • 2王作英.基于段长分布的HMM语音识别模型 [A]..第二届全国汉字汉语识别会议 [C].庐山,1989.9.
  • 3赵庆卫. 非特定人大词汇量汉语连续语音识别系统的研究 [D]. 北京: 清华大学,1998.ZHAO Qingwei. The research on speaker-independent large-vocabulary Mandarin continuous speech recognition system [D]. Beijing: Tsinghua University,1998. (in Chinese)
  • 4WANG Zuoying,SUN Jiasong,XIAO Xi,et al. A minimum corpus designed for training the acoustic model [A]. Academia Sinica,Oriental COCOSDA Proceedings [C]. Taipei,Taiwan: Academia Sinica,1999. 77-80.
  • 5HUANG Xuedong,Acero A,HON Hsiaowen. Spoken Language Processing [M]. New Jersey: Prentice Hall,2001. 427-434.
  • 6MEI Yuhwang. Subphonetic acoustic modeling for speaker-independent continuous speech recognition [D]. Pittsburgh: Carnegie Mellon Univ,1994.
  • 7Huang Xuedong, Acero A. Spoken Language Processing: A Guide to Theory, Algorithm and System Development[M]. New Jersey: Prentice-Hall, 2001.
  • 8Nordholm S, Slow Yong Low. Speech Signal Extraction Utilizing PCA-ICA Algorithm with a Non-uniform Spacing Microphone Array[C]//Proc. of IEEE International Conference on Acoustics, Speech, and Signal Processing. Toulouse, France: [s. n.], 2006: 965.
  • 9Tsuneo N. Feature Extraction for Speech Recognition Based on Ohogonal Acoustic-feature Panes and LDA[C]//Proc. of IEEE International Conference on Acoustics, Speech and Signal Processing. Phoenix, AZ, USA: [s. n.], 1999: 421-424.
  • 10Aubert X L. An Overview of Decoding Techniques for Large Vocabulary Continuous Speech Recognition[J]. Computer Speech and Language, 2002, 16(1): 89-114.

共引文献52

相关作者

内容加载中请稍等...

相关机构

内容加载中请稍等...

相关主题

内容加载中请稍等...

浏览历史

内容加载中请稍等...
;
使用帮助 返回顶部