首页 | 本学科首页   官方微博 | 高级检索  
     

支持向量机的汉语连续语音声调识别方法
引用本文:傅德胜,李仕强,王水平. 支持向量机的汉语连续语音声调识别方法[J]. 计算机科学, 2010, 37(5): 228-230
作者姓名:傅德胜  李仕强  王水平
作者单位:1. 南京信息工程大学计算机与软件学院,南京,210044
2. 南京信息工程大学信息与控制学院,南京,210044
摘    要:声调信息在汉语语音识别中具有非常重要的意义。采用支持向量机对连续汉语连续语音进行声调识别实验,首先采用基于Teager能量算子和过零率的两级判别策略对连续语音进行浊音段提取,然后建立了适合于支持向量机分类模型的等维声调特征向量。使用6个二类SVM模型对非特定人汉语普通话的4种声调进行分类识别,与BP神经网络相比,支持向量机具有更高的识别率。

关 键 词:声调识别  基音频率  支持向量机  
收稿时间:2009-07-03
修稿时间:2009-09-25

Tone Recognition Based on Support Vector Machine in Continuous Mandarin Chinese
FU De-sheng,LI Shi-qiang,WANG Shui-ping. Tone Recognition Based on Support Vector Machine in Continuous Mandarin Chinese[J]. Computer Science, 2010, 37(5): 228-230
Authors:FU De-sheng  LI Shi-qiang  WANG Shui-ping
Affiliation:Computer and Software Institute/a>;Nanjing University of Information Science and Technology/a>;Nanjing 210044/a>;China;School of Information and Control/a>;China
Abstract:Tone is an essential component for word formation in Chinese languages.It plays a very important role in the transmission of information in speech communication.We looked at using support vector machines(SVMs) for automatic tone recognition in continuously spoken Mandarin.The voiced segments were detected based on Teager Energy Operation and ZCR.Compared with BP neural network,considerable improvement was achieved by adopting 6 binary-SVMs scheme in a speaker-independent Mandarin tone recognition system.
Keywords:Tone recognition  Fundamental frequency  Support vector machine  
本文献已被 CNKI 万方数据 等数据库收录!
点击此处可从《计算机科学》下载全文
设为首页 | 免责声明 | 关于勤云 | 加入收藏

Copyright©北京勤云科技发展有限公司  京ICP备09084417号