| 基于BP网络的汉语普通话声调识别 |
| |
| 引用本文： | 李仕强,王水平. 基于BP网络的汉语普通话声调识别[J]. 南京气象学院学报, 2012, 4(5): 456-460 |
| |
| 作者姓名： | 李仕强 王水平 |
| |
| 作者单位： | 南京信息工程大学 网络信息中心,南京,210044;南京信息工程大学 江苏省网络监控工程中心,南京,210044;南京信息工程大学 计算机与软件学院,南京,210044 |
| |
| 基金项目： | 2010年江苏省政府留学奖学金项目;江苏省教育科学"十二五"规划课题(C-C/2011/01/42);南京信息工程大学教学建设与改革工程项目(11JY056);南京信息工程大学高等教育调研及政策研究课题(2012GJ002);南京信息工程大学实验室开放项目(12KF034,12KF028) |
| |
| 摘 要： | 研究了一种常用的模式分类器——BP神经网络,分析了BP网络的训练及识别过程,提取了能体现声调特性的特征数据组成分类特征向量,设计了具有一个隐含层的3层前馈网络作为分类器,对普通话声调样本库做了分类识别实验,分析了不同隐含层节点数的识别实验结果.实验结果表明,提取的音频特征基本有效,分类效果良好,具有一定的应用价值.
|
| 关 键 词： | BP网络 音频特征分析 声调识别 |
| 收稿时间： | 2012-02-09 |
Mandarin Chinese tone recognition based on back-propagation neural network |
| |
| LI Shiqiang and WANG Shuiping. Mandarin Chinese tone recognition based on back-propagation neural network[J]. Journal of Nanjing Institute of Meteorology, 2012, 4(5): 456-460 |
| |
| Authors: | LI Shiqiang and WANG Shuiping |
| |
| Affiliation: | Network Information Center,Nanjing University of Information Science & Technology,Nanjing 210044;Jiangsu Engineering Center of Network Monitoring,Nanjing University of Information Science & Technology,Nanjing 210044;School of Computer & Software,Nanjing University of Information Science & Technology,Nanjing 210044 |
| |
| Abstract: | The BP neural network is studied and applied to tone recognition in this paper,which is a frequently used pattern classifier.Based on analysis of training and recognition processes of BP neural network,we extract feature data reflecting the tone characteristics to build the classification eigenvector.The classifier is designed as a 3-layer BP neural network with one hidden layer,and applied to recognize the four tones of Mandarin Chinese.The recognition results by BP neural network with different hidden layer nodes are compared.The experiment result indicates that the audio feature extracted by this classifier is valid for Mandarin Chinese,and verifies its good classification performance. |
| |
| Keywords: | back-propagation neural network audio feature extraction tone recognition |
|
| 点击此处可从《南京气象学院学报》浏览原始摘要信息 |
|
点击此处可从《南京气象学院学报》下载全文 |
|
