2025年4月4日 21:07 星期五
首页 > 过刊浏览>2012年第4卷第5期 >456-460
PDF HTML阅读 XML下载 导出引用 引用提醒
基于BP网络的汉语普通话声调识别
作者:
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)


Mandarin Chinese tone recognition based on back-propagation neural network
Author:
  • 摘要
    • | |
  • 访问统计
    • |
  • 参考文献
    • |
  • 相似文献
    • | | |
  • 文章评论
    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.

    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.

    参考文献
    [1] 韩纪庆,冯涛,郑贵滨,等.音频信息处理技术[M].北京:清华大学出版社,2007 HAN Jiqing,FENG Tao,ZHENG Guibing,et al.Speech signal processing technology[M].Beijing:Tsinghua University Press,2007
    [2] 汤霖,尹俊勋,粟志昂,等.基于两级BP模型的普通话声调识别系统[J].计算机工程与应用,2004(25):96-99 TANG Lin,YIN Junxun,SU Zhiang,et al.Mandarin tone recognition system based on two-level BP model[J].Computer Engineering and Applications,2004(25):96-99
    [3] 张德丰.Matlab神经网络应用设计[M].北京:机械工业出版社,2009 ZHANG Defeng.Matlab neutral network application design[M].Beijing:China Machine Press,2009
    [4] Hagan M T,Demuth H B,Beale M.神经网络设计[M].北京:机械工业出版社,2002 Hagan M T,Demuth H B,Beale M.Neural network design[M].Beijing:China Machine Press,2002
    [5] 冯康,时慧琨.语音信号基音检测的现状及展望[J].微机发展,2004,14(3):95-101 FENG Kang,SHI Huikun.The current situation and prospects of pitch detection[J].Microcomputer Development,2004,14(3):95-101
    [6] Emonts M,Lonsdale D.A memory-based approach to cantonese tone recognition//Proceedings of the 8th European Conference on Speech Communication and Technology,2003:2305-2308
    [7] Surendran D,Levow G A,Xu Y.Tone recognition in Mandarin using Focus[J].Baseline,2005,17(4):3301-3304
    [8] Peng G,Wang W S Y.Tone recognition of continuous Cantonese speech based on support vector machines[J].Speech Communication 2005,45(1):49-62
    [9] 肖汉光,蔡从中.基于SVM的非特定人声调识别的研究[J].计算机工程与应用,2009,45(9):174-176 XIAO Hanguang,CAI Congzhong.Study of speaker-independent tone recognition based on support vector machine[J].Computer Engineering and Applications,2009,45(9):174-176
    [10] 王改良,武妍.基于仿生模式识别理论的声调识别[J].计算机应用,2010,30(10):2709-2711 WANG Gailiang,WU Yan.Tone recognition based on biomimetic pattern recognition theory[J].Computer Applications,2010,30(10):2709-2711
    引证文献
    网友评论
    网友评论
    分享到微博
    发 布
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].南京信息工程大学学报(自然科学版),2012,4(5):456-460
LI Shiqiang, WANG Shuiping. Mandarin Chinese tone recognition based on back-propagation neural network[J]. Journal of Nanjing University of Information Science & Technology, 2012,4(5):456-460

复制
分享
文章指标
  • 点击次数:1378
  • 下载次数: 2724
  • HTML阅读次数: 0
  • 引用次数: 0
历史
  • 收稿日期:2012-02-09

地址：江苏省南京市宁六路219号    邮编：210044

联系电话：025-58731025    E-mail：nxdxb@nuist.edu.cn

南京信息工程大学学报 ® 2025 版权所有  技术支持：北京勤云科技发展有限公司