期刊文献+

嵌入自联想神经网络的高斯混合模型说话人辨认 被引量:4

Speaker Identification Based on GMM with Embedded AANN
下载PDF
导出
摘要 该文提出了一种嵌入自联想神经网络的高斯混合模型,它充分利用了神经网络和高斯混合模型各自的优点,以最大似然概率(ML)为准则,把它们作为一个整体来进行训练。训练过程中,高斯混合模型和神经网络的参数交替更新。由于神经网络起到了"数据整形"的作用,因而提高了类内数据的相似性。实验结果表明,采用该文提出的模型在各种信噪比情况下的识别率都比基线系统有所提高,最高能达到19%。 In this paper,a modified Gaussian Mixed Model (GMM) with an embedded Auto-Associate Neural Network (AANN) is proposed.It integrates the merits of GMM and AANN.GMM and AANN as a whole are trained by means of Maximum Likelihood (ML).In the process of training,the parameters of GMM and AANN are updated alternately.AANN reshapes the distribution of the data and improves the similarity of the data in one class.Experiments show that the proposed system improves accuracy rate against baseline GMM at all SNR,maximum to 19%.
作者 陈存宝 赵力
出处 《电子与信息学报》 EI CSCD 北大核心 2010年第3期528-532,共5页 Journal of Electronics & Information Technology
基金 国家自然科学基金(60872073 60975017) 江苏省自然科学基金(BK2008291)资助课题
关键词 说话人识别 高斯混合模型(GMM) 自联想神经网络(AANN) 嵌入 Speaker identification Gaussian Mixed Model (GMM) Auto-Associate Neural Network (AANN) Embedded
  • 相关文献

参考文献16

  • 1赵力编著..语音信号处理[M].北京:机械工业出版社,2003:316.
  • 2Campbell J P. Speaker recognition: A tutorial. Proceedings of the IEEE, 1997, 85(9): 1437-1462. 被引量:1
  • 3Bimbot F, Bonastre J F, and Fredouille C, et al.. A tutorial on text-independent speaker verification. EURASIP Journal on Applied Signal Processing, 2004, 2004(4): 430-451. 被引量:1
  • 4Reynolds D A and Rose R C. Robust text-independent speaker identification using Gaussian mixture models. IEEE Transactions on Speech Audio Processing, 1995, 3(1): 72-83. 被引量:1
  • 5Reynolds D A, Quatieri T, and Dunn R. Speaker verification using adapted Gaussian mixture models. Digital Signal Processing, 2000, 10(1): 19-41. 被引量:1
  • 6Kwon S and Narayanan S. Robust speaker identification based on selective use of feature vectors. Pattern Recognition Letters, 2007, 28(1): 85-89. 被引量:1
  • 7Campbell W M, Sturim D E, and Reynolds D A. SVM based speaker verification using a GMM supervector kernel and NAP variability compensation. Proceedings of ICASSP,Toulouse, France, 2006: 97-100. 被引量:1
  • 8Yin Shou-chun, Rose R, and Kenny P. A joint factor analysis approach to progressive model adaptation in textindependent speaker verification. IEEE Transactions on Audio, Speech and Language Processing, 2007, 15(7): 1999-2110. 被引量:1
  • 9Mak M W, Allen W G, and Sexton G G. Speaker identification using multilayer perceptron and radial basis function networks. Neurocomputing, 1994, 6(1): 99-117. 被引量:1
  • 10Bennani Y and Gallinari P. On the use of TDNN-extracted features information in talker identification. Proceedings of ICASSP, Toronto, Ont, Canada 1991: 385-388. 被引量:1

同被引文献37

引证文献4

二级引证文献9

相关作者

内容加载中请稍等...

相关机构

内容加载中请稍等...

相关主题

内容加载中请稍等...

浏览历史

内容加载中请稍等...
;
使用帮助 返回顶部