[1]于云,周伟栋. 基于稀疏表示的鲁棒性说话人识别系统[J].计算机技术与发展,2015,25(12):41-46.
　YU Yun,ZHOU Wei-dong. Robust Speaker Recognition System Based on Sparse Representation[J].,2015,25(12):41-46.
点击复制

 基于稀疏表示的鲁棒性说话人识别系统()
分享到：

《计算机技术与发展》[ISSN:1006-6977/CN:61-1281/TN]

卷:
25
期数:
2015年12期
页码:
41-46
栏目:
智能、算法、系统工程
出版日期:
2015-12-10

文章信息/Info

Title:
 Robust Speaker Recognition System Based on Sparse Representation
文章编号:
1673-629X（2015)12-0041-06
作者:
 于云; 周伟栋
 南京邮电大学 通信与信息工程学院
Author(s):
YU Yun; ZHOU Wei-dong
关键词:
说话人识别; 稀疏表示; 多状态训练; 谱减法
Keywords:
 ; speaker recognition; sparse representation; multi-condition training; spectrum subtraction
分类号:
TN912.3
文献标志码:
A
摘要:
 基于稀疏表示的说话人识别方法在无噪的环境下已经达到了理想的效果,然而在背景噪声下,此方法的识别性能大幅度下降. 为了提高系统的鲁棒性,提出了一种新型的基于稀疏表示的鲁棒性说话人识别系统模型. 此系统结合多状态训练和语音增强谱减法,在训练阶段和测试阶段同时利用语音增强技术,然后对增强后的语音进行多状态训练,以便提高训练特征数据集和测试特征数据集之间的匹配度. 实验分析和结果表明,所提出的新型模型在所研究的白噪声和有色噪声下达到了很好的抗噪性能,具有很强的鲁棒性.
Abstract:
 Robust speaker recognition method based on sparse representation in the absence of noise has reached ideal performance. How-ever,speaker recognition based on sparse representation doesn’t perform well where background noise exists. To improve the robustness of this system,describe a new robust speaker recognition system based on sparse representation. The system combines multi-condition training and spectrum subtraction,which is thought to be a preprocessing block not only for the testing stage,but also for the training stage. Then propose to make multi-condition training where various sets of features are extracted,so as to improve the matched degree be-tween training data and testing data. Experimental analysis and results show that the proposed new model under white and colored noises can get the great anti-noise performance,and obviously improve the robustness of the speaker recognition under background noisy envi-ronments.

相似文献/References:

[1]吴庆棋 林江云.基于聚类优化GMM提高说话人识别性能的研究[J].计算机技术与发展,2009,(04):35.
　WU Qing-qi,LIN Jiang-yun.A Study on GMM Optimization with Clustering for Improving Speaker Recognition[J].,2009,(12):35.
[2]但志平 郑胜.最小二乘向量机在说话人识别中的应用[J].计算机技术与发展,2007,(05):30.
　DAN Zhi-ping,ZHENG Sheng.Application of LS - SVM in Speaker Recognition[J].,2007,(12):30.
[3]张华 裘雪红.说话人识别中LPCCEP倒谱分量的相对重要性[J].计算机技术与发展,2006,(04):67.
　ZHANG Hua,QIU Xue-hong.On the Importance of Components of LPCCEP in Speaker Recognition[J].,2006,(12):67.
[4]朱伟冬 胡剑凌.基于马氏距离的稀疏表示分类算法[J].计算机技术与发展,2011,(11):27.
　ZHU Wei-dong,HU Jian-ling.Sparse Representation Classification Algorithm Based on Mahalanobis Distance[J].,2011,(12):27.
[5]王韦刚 庄伟胤.基于NIOS Ⅱ的图像压缩感知[J].计算机技术与发展,2012,(04):12.
　WANG Wei-gang,ZHUANG Wei-yin.Compressed Sensing of Image Based on NIOS Ⅱ[J].,2012,(12):12.
[6]葛广重,杨敏.基于稀疏表示的单幅图像超分辨率重建[J].计算机技术与发展,2013,(09):113.
　GE Guang-zhong,YANG Min.Single Image Super-resolution Reconstruction Based on Sparse Representation[J].,2013,(12):113.
[7]赵海峰,于雪敏,邹际祥,等.基于L1范数主成分分析的颅脑图像恢复[J].计算机技术与发展,2014,24(01):231.
　ZHAO Hai-feng[],YU Xue-min[],ZOU Ji-xiang[],et al.Cerebral Image Recovery Based on L1-norm Principal Component Analysis[J].,2014,24(12):231.
[8]陈静,邱晓晖,孙娜. 基于二维Gabor小波与SPP算法的人脸识别研究[J].计算机技术与发展,2014,24(11):110.
　CHEN Jing,QIU Xiao-hui,SUN Na. Research on Face Recognition Based on 2 D Gabor Wavelet and SPP Algorithm[J].,2014,24(12):110.
[9]姚刚,杨敏. 稀疏子空间聚类的惩罚参数自调整交替方向法[J].计算机技术与发展,2014,24(11):131.
　YAO Gang,YANG Min. Alternating Direction Method of Self-adjusting Penalty Parameters of Sparse Subspace Clustering[J].,2014,24(12):131.
[10]刘俊坤,李燕萍,凌云志.基于AutoEncoder DBN－VQ 的说话人识别系统[J].计算机技术与发展,2018,28(02):45.[doi:10.3969/j.issn.1673－629X.2018.02.]
　LIU Junkun,LI Yanping,LING Yunzhi.Speaker Ｒecognition System Based on AutoEncoder Deep Belief Network and Vector Quantization[J].,2018,28(12):45.[doi:10.3969/j.issn.1673－629X.2018.02.]

更新日期/Last Update: 2016-01-28