[1]马小辉,富煜清,陆佶人.结合SOFM失真的HMM语音识别方法[J].东南大学学报(自然科学版),1997,27(1):49-52.[doi:10.3969/j.issn.1001-0505.1997.01.010]
 [J].Journal of Southeast University (Natural Science Edition),1997,27(1):49-52.[doi:10.3969/j.issn.1001-0505.1997.01.010]
点击复制

结合SOFM失真的HMM语音识别方法()
分享到:

《东南大学学报(自然科学版)》[ISSN:1001-0505/CN:32-1178/N]

卷:
27
期数:
1997年第1期
页码:
49-52
栏目:
信息与通信工程
出版日期:
1997-01-20

文章信息/Info

作者:
马小辉富煜清陆佶人
东南大学无线电工程系
关键词:
语言识别 神经网络 统计模型 自组织特征映射 隐马尔可夫模型
分类号:
TN912.34
DOI:
10.3969/j.issn.1001-0505.1997.01.010
摘要:
提出一种结合SOFM失真的HMM语音识别方法.它直接将SOFM失真测度与左右型离散HMM相结合,综合利用SOFM失真与HMM状态输出概率作为HMM的匹配失真测度.该方法既可以看作为基于VQ失真语音识别方法的推广,又可以看作为半连续HMM的一种特例.实验结果证明它具有良好的效果

相似文献/References:

[1]徐庆宏,戴先中.发电机励磁与汽门系统的改进神经网络逆控制方法[J].东南大学学报(自然科学版),2010,40(6):1196.[doi:10.3969/j.issn.1001-0505.2010.06.013]
 Xu Qinghong,Dai Xianzhong.Improved ANN-inversion control scheme of excitation and valve system for turbogenerator[J].Journal of Southeast University (Natural Science Edition),2010,40(1):1196.[doi:10.3969/j.issn.1001-0505.2010.06.013]
[2]滕军,卢伟.基于多类型传感器信息的结构损伤识别方法[J].东南大学学报(自然科学版),2010,40(3):538.[doi:10.3969/j.issn.1001-0505.2010.03.020]
 Teng Jun,Lu Wei.Structural damage identification method based on multi-type sensors[J].Journal of Southeast University (Natural Science Edition),2010,40(1):538.[doi:10.3969/j.issn.1001-0505.2010.03.020]
[3]张志伟,胡伍生,黄晓明.线性回归模型精化方法[J].东南大学学报(自然科学版),2009,39(6):1279.[doi:10.3969/j.issn.1001-0505.2009.06.037]
 Zhang Zhiwei,Hu Wusheng,Huang Xiaoming.Linear regressive model improved by neural network[J].Journal of Southeast University (Natural Science Edition),2009,39(1):1279.[doi:10.3969/j.issn.1001-0505.2009.06.037]
[4]朱清,费树岷,李涛.带有多个离散和分布时滞的不确定系统的鲁棒自适应控制[J].东南大学学报(自然科学版),2008,38(1):175.[doi:10.3969/j.issn.1001-0505.2008.01.034]
 Zhu Qing,Fei Shumin,Li Tao.Robust adaptive control for uncertain systems with multiple discrete and distributed delays[J].Journal of Southeast University (Natural Science Edition),2008,38(1):175.[doi:10.3969/j.issn.1001-0505.2008.01.034]
[5]庄哲民,黄惟一.机器人人工嗅觉系统设计[J].东南大学学报(自然科学版),2004,34(1):28.[doi:10.3969/j.issn.1001-0505.2004.01.007]
 Zhuang Zhemin,Huang Weiyi.Artificial olfactory system based on a telepresence robot[J].Journal of Southeast University (Natural Science Edition),2004,34(1):28.[doi:10.3969/j.issn.1001-0505.2004.01.007]
[6]王昌龙,高龙琴,黄惟一.基于电子鼻技术的化学热处理气氛测控[J].东南大学学报(自然科学版),2003,33(4):442.[doi:10.3969/j.issn.1001-0505.2003.04.015]
 Wang Changlong,Gao Longqin,Huang Weiyi.Electronic nose based atmosphere measuring and controlling system for thermal chemical treatment[J].Journal of Southeast University (Natural Science Edition),2003,33(1):442.[doi:10.3969/j.issn.1001-0505.2003.04.015]
[7]史笑兴,顾明亮,王太君,等.一种时间规整算法在神经网络语音识别中的应用[J].东南大学学报(自然科学版),1999,29(5):47.[doi:10.3969/j.issn.1001-0505.1999.05.009]
 Shi Xiaoxing,Gu Mingliang,Wang Taijun,et al.A New Time Wrapping Algorithm and Its Application on Neural Network Based Speech Recognition[J].Journal of Southeast University (Natural Science Edition),1999,29(1):47.[doi:10.3969/j.issn.1001-0505.1999.05.009]
[8]张胜,刘红星,高敦堂,等.ANN非线性时间序列预测模型输入延时τ的确定[J].东南大学学报(自然科学版),2002,32(6):905.[doi:10.3969/j.issn.1001-0505.2002.06.017]
 Zhang Sheng,Liu Hongxing,Gao Duntang,et al.Determining the input time delay τ of a neural network for nonlinear time series prediction[J].Journal of Southeast University (Natural Science Edition),2002,32(1):905.[doi:10.3969/j.issn.1001-0505.2002.06.017]
[9]林莉,万德钧,李滋刚.基于人工神经网络的船舶运动数学模型的辨识[J].东南大学学报(自然科学版),2000,30(2):71.[doi:10.3969/j.issn.1001-0505.2000.02.015]
 Lin Li,Wan Dejun,Li Zigang.Identifying Mathematical Model of Ship Movement Using Artificial Neural Network[J].Journal of Southeast University (Natural Science Edition),2000,30(1):71.[doi:10.3969/j.issn.1001-0505.2000.02.015]
[10]陈辉,宋爱国,黄惟一.人手抓取特性与机械手神经网络抓取策略[J].东南大学学报(自然科学版),1999,29(2):18.[doi:10.3969/j.issn.1001-0505.1999.02.004]
 Chen Hui,Song Aiguo,Huang Weiyi.Human Grasp Property and Robot Hand Grasp Tactics about Neural Networks[J].Journal of Southeast University (Natural Science Edition),1999,29(1):18.[doi:10.3969/j.issn.1001-0505.1999.02.004]

备注/Memo

备注/Memo:
国家自然科学基金
更新日期/Last Update: 2013-04-14