期刊文献+
任意字段
题名或关键词
题名
关键词
文摘
作者
第一作者
机构
刊名
分类号
参考文献
作者简介
基金资助
栏目信息

ANN/HMM混合模型中状态数的自适应确定方法研究 被引量：1

Self-Adjusting the State Number of the ANN / HMM Hybrid Model
下载PDF
导出
摘要 本文在分析了固定状态数目来确定模型状态数的方法的缺陷之后,提出了一种根据训练样本具体形态来自动增加或减少模型状态数目的方法。其中的增加状态实质是将原状态拆分成两个新状态,而被分割的是建摸精度不够的状态。而删除状态就是将状态从原模型中删除,并重新连接被删除状态两端的状态。被删除的状态是帧数相对较少的,这样的状态可以被合并到与其相临的状态当中。 This paper presents a method of increasing or decreasing the state number of the ANN/HMM hybrid model based on the specific forms of training samples. Increasing the state number is to split a state with lower modeling accuracy into two new separated states. Deleting a state is to remove it from the original model.
作者 刘明宇 高晓晶
机构地区 哈尔滨师范大学计算机科学与信息工程学院 黑龙江省兵器职工大学
出处 《自动化技术与应用》 2009年第7期29-32,共4页 Techniques of Automation and Applications
关键词 ANN/HMM混合模型 固定状态数目 自动增减状态数 ANN/HMM hybrid model fixed states number automatically increase or decrease the state number
分类号 TP273.2 [自动化与计算机技术—检测技术与自动化装置]
  • 相关文献

参考文献7

  • 1刘明宇.ANN/HMM混合模型在语音识别中的应用[J].自动化技术与应用,2009,28(6):122-124. 被引量：4
  • 2LIXIAO-GE,SHAO LI-HONG,LI NA.The Realization of Artificial Neural Network BP Algorithm[J]. Computer Knowledge and Technology. 2008, (5). 921-923.
  • 3MA LIN,LI HAIFENG,HAN IIQING,AND PATRICKGALLINARI.Hidden control neural network and HMM hybrid approach for on-line cursive handwriting recognition. Nanjing, China,2003[C].Neural Networks and Signal Processing, 2003(1): 236-239.
  • 4HAIFENG LI,THIERRY ARTIERES,PATRICK GALLINARI.Data driven design of an ANN/HMM system for on-line unconstrained handwritten character recognition [C].Proceedings.Fou_rth IEEE International Conference,2002. Multimodal Interfaces,2002,149-154.
  • 5HAIFENG LI,THIERRY ARTIRES,PATRICKGALLINARI,BERNADETTE DORIZZI.Topology inference for an ANN/HMM hybrid on-line handwriting recognition system[C].Proceedings of the 9th International Conference, 2002 . Neural Information Processing, 2002, (5):2479-2483.
  • 6HAIFENG LI,THIERIY ARTIIRES,PATRICKGALLINARI,BERNADETFE DORIZZI.VQ-based on-line hand- written character recognition through learning and adaptive edit distances[C].Proceedings of the 9th International Conference, 2002. Neural Information Processing, 2002, (4). 2008-2012.
  • 7舒倩,李银国.基于CHMM语音识别特征参数的选择方法[J].计算技术与自动化,2007,26(4):92-94. 被引量：5

二级参考文献9

  • 1HAIFENG LI,THIERRY ARTIRES, PATRICK GALLINARI,BERNADETTE DORIZZI.Topology inference for an ANN/HMM hybrid on-line handwriting recognition system. Lipo Wang, Jagath C.Rajapakse, Kuniluko Fukushuna,SooYoung Lee, Xin Yao.Proceedings of the 9th International Conference, 2002 . Neural Information Processing,2002,5.-2479-2483.
  • 2HAIFENG LI, THIERIY ARTIIRES,PATRICK GALLINARI,BERNADETTE DORIZZI.VQ-based on-line handwritten character recognition through learning and adaptive edit distances.Proceedings of the 9th International Conference,2002. Neural Information Processing, 2002,4: 2008-2012.
  • 3HAIFENG LI,THIERRY ARTIERES, PATRICK GALLINARI.Data driven design of an ANN/HMM system for on-line unconstrained handwritten character recognition. Proceedings. Fourth IEEE International Conference, 2002. Multimodal Interfaces, 2002:149-154.
  • 4LIXIAO-GE,SHAO LI-HONG,LI NA.The Realization of Artificial Neural Network BP Algorithm.Computer Knowledge and Technology. 2008, (5): 921-923.
  • 5MA LIN,LI HAIFENG,HAN JIQING,AND PATRICK GALLINARI. Hidden control neural network and HMM hybrid approach for on-line cursive handwriting recognition.Nanjing, China, 2003. Neural Networks and Signal Processing,2003,1,236- 239.
  • 6L. R. Rabiner. A Tutorial on Hidden Markov Models and Selected Applications in Speech Recognition [ J ]. Proc . of IEEE, 1989,77(2).
  • 7Rabiner L, Juang B H. Fundamentals of Speech Recognition [ M]. BeiJing: Tsinghua University Press , 1999.
  • 8甄斌,吴玺宏,刘志敏,迟惠生.语音识别和说话人识别中各倒谱分量的相对重要性[J].北京大学学报（自然科学版）,2001,37(3):371-378. 被引量：74
  • 9王让定,柴佩琪.语音倒谱特征的研究[J].计算机工程,2003,29(13):31-33. 被引量：50

共引文献7

同被引文献1

引证文献1

自动化技术与应用
2009年 第7期

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