我们的网站为什么显示成这样？

可能因为您的浏览器不支持样式，您可以更新您的浏览器到最新版本，以获取对此功能的支持，访问下面的网站，获取关于浏览器的信息：

|本期目录/Table of Contents|

隐马尔可夫模型和支持向量机混合模型声识别(PDF)

《探测与控制学报》[ISSN:1008-1194/CN:61-1316/TJ]

期数:
2009年06期
页码:
33
栏目:
出版日期:
2009-12-26

文章信息/Info

Title:
Acoustic Targets Recognition Based on HMM and SVM
文章编号:
1008-1194(2009)06-0033-05
作者:
刘辉1; 2;  杨俊安1; 2; 许学忠3
1.解放军电子工程学院，安徽 合肥230037；2.安徽省电子制约技术重点实验室，安徽 合肥230037；3.西北核技术研究所，陕西 西安710613
Author(s):
LIU Hui1; 2; YANG Jun-an1; 2; XU Xue-zhong3
1.Electronic Engineering Institute,Hefei 230037,China;2.Key Laboratory of Electronic Restriction,
Hefei 230037,China;3.Northwest Institute of Nuclear Technology,Xi’an 710613,China
关键词:
低空飞行目标识别; 隐马尔科夫模型(HMM); 支持向量机(SVM)
Keywords:
acoustic recognition of flying target; Hidden Markov Model (HMM); Support Vector Machines (SVM)
分类号:
TB132
DOI:
.
文献标识码:
A
摘要:
为弥补单一模型在识别低空飞行目标时的不足，进一步提高低空飞行目标的识别率，提出一种基于HMM和SVM混合结构的低空飞行目标声识别算法。针对战场环境下声信号的特点，算法综合考虑HMM适合处理连续动态信号及SVM小样本情况下的强分类能力，利用HMM处理待辨识的连续动态信号，将HMM易混淆的信号作为与待辨识信号较为相似的模式类，形成候选模式集，再由SVM在候选模式中对待辨识信号作最后决策。实际数据的识别结果表明相对于单一的HMM和SVM，混合模型的识别率有一定的提高。
Abstract:
In order to overcome the deficiency of the single model for the recognition of low-altitude flying target and improve the recognition rate,a new algorithm is proposed,which takes the advantages of Hidden Markov Model (HMM) and Support Vector Machines (SVM).HMM is good at dealing with sequential inputs,while SVM shows superior performance in classification especially for limited samples.Therefore,they can be combined to get a better and effective multilayer architecture classifier.SVM is used to resolve the uncertainty of the remaining signal which is confusable after the HMM-based recognition.Experimental results prove that the hybrid model has a better performance than the simple one.

参考文献/References

［1］吕国云,许学忠, 赵锐.战场目标被动噪声识别技术［J］.探测与控制学报,2001,23(4):22-25.
LV Guo-yun,XU Xue-zhong,ZHAO Rui.Passive sound recognition technology for the targets in battlefield［J］.Journal of Detection&Control,2001,23(4):22-25.
［2］刘辉,杨俊安,许学忠. 基于MFCC参数和HMM的低空飞行目标声识别方法研究［J］.弹箭与制导学报,2007,27(5):217-222.
LIU Hui,YANG Jun-an,XU Xue-zhong.Anovel low altitude passive acoustic target identify approach research based on MFCC and HMM［J］.Journal of Projectiles, Rockets, Missiles and Guidance,2007,27(5):217-222.
［3］LIU Hui,YANG Jun-an.A novel approach research on low altitude passive acoustic target recognition based on ICA and HMM［C］//The Fourth International Conference on Natural Computation.US:IEEE,2008:371-375.
［4］陈虎虎,钟方平,许学忠,等.基于支持向量机的低空飞行目标声识别［J］.系统工程与电子技术,2005,27(1):46-48.
CHEN Hu-hu,ZHONG Fang-ping,XU Xue-zhong.Acoustic recognition of low-altitude flight targets by SVM［J］.System Engineering and electronics,2005,27(1):46-48.
［5］陈功.战场被动声目标识别关键技术的研究［D］.南京:解放军理工大学,2007:12-15.
［6］Michael T Johnson.Capacity and Complexity of HMM Duration Modeling Techniques［C］//IEEE signal processing letters,US:IEEE,2005:407-410.
［7］ZHANG Le,Steve Renals.Acoustic-Articulatory Modeling With the Trajectory HMM［C］//IEEE signal processing letters.US:IEEE,2008:245-248.
［8］QU Zhi-jian,LUO Jun.Latent correlation analysis of HMM parameters for speech recognition［C］//ICASSP.US:IEEE,2007(IV) 753-756.
［9］Doumpiotis V,Tsakalidis S,Byrne W.Discriminative training for segmental minimum Bayes risk decoding［C］//ICASSP.US:IEEE,2003:512-516.
［10］Yuh-Jye Lee,Su-Yun Huang.Reduced Support Vector Machines:A Statistical Theory［C］//IEEE transactions neural networks,US:IEEE,2007:1-13.
［11］LIU Ming-hui,XIE Yan-lu.A New Hybrid GMM/SVM for Speaker Verification［C］//The 18th International Conference on pattern Recognition.US:IEEE,2006:314-317.

备注/Memo

备注/Memo:
*收稿日期：2009-07-19    修回日期：2009-08-31
基金项目：2008年度国家自然科学基金项目资助（60872113）
作者简介：刘辉(1983-)，男，安徽亳州人，博士研究生，研究方向：信号分析与识别。E-mail：christ592604@qq.com。
更新日期/Last Update: 2010-01-07