Wavelet De-noising of Speech Using Singular Spectrum Analysis for Decomposition Level Selection

被引：0
作者：
蔡铁
朱杰
机构：
[1] China
[2] Dept.of Electronic Eng. Shanghai Jiaotong Univ.
[3] Shanghai 200030
来源：
Journal of Shanghai Jiaotong University | 2007年 / 02期
关键词：
speech enhancement; wavelet de-noising; singular spectrum analysis(SSA); support vector machine(SVM);
D O I：
暂无
中图分类号：
TN912.3 [语音信号处理];
学科分类号：
0711 ;
摘要：
The problem of speech enhancement using threshold de-noising in wavelet domain was considered.The appropriate decomposition level is another key factor pertinent to de-noising performance.This paper proposed a new wavelet-based de-noising scheme that can improve the enhancement performance significantly in the presence of additive white Gaussian noise.The proposed algorithm can adaptively select the optimal decomposition level of wavelet transformation according to the characteristics of noisy speech.The experimental results demonstrate that this proposed algorithm outperforms the classical wavelet-based de-noising method and effectively improves the practicability of this kind of techniques.
引用
收藏
页码：190 / 196
页数：7
相关论文
共 11 条
  • [1] Research on availability of Neymark decomposition applied to separated chaos signal from noise. Wang Y Q,Huang W Y,Duan J H,et al. Journal of Data Acquisition&Processing . 2003
  • [2] Threshold selection for wavelet shrinkage of noisy data//Proceedings of the16th Annual International Conference of the IEEE Engineering in Medicine and Biology Society,Vol1. Donoho D L,Johnstone I M. Baltimore,Maryland,USA:[s.n.] . 1994
  • [3] Adaptive de-noising based on SURE risk. Zhang X P,Desai M T. IEEE Signal Processing Letters . 1998
  • [4] Wavelet de-noising of speech using neural networks for threshold selection. Medina C A,Aleaim A,Apolinario J A. Electronics Letters . 2003
  • [5] An algorithm for de-noising of chaotic data. LIU Y F,ZHAO M. Mechanical Science and Technolo-gy . 2003
  • [6] Speech enhancement with re-duction of noise components in the wavelet domain//Proceedings of the ICASSP1997,Vol2. Seok J W,Bae K S. Mu-nich,Germany:[s.n.] . 1997
  • [7] An adaptive way for improving noise reduction using local geometric projection. Leontitsis A,Bountis T,Pagge J. Chaos . 2004
  • [8] Wavelet threshold estimator for data with correlated noise. Johnstone I M,Silverman B W. Journal of Royal Statistics Society Series(B) . 1997
  • [9] Enhancement of single channel speech based on masking property and wavelet trans-form. Lu C T,Wang H C. Speech Communication . 2003
  • [10] De-noising by soft-thresholding. Donoho D L. IEEE Transactions on Information Theory . 1995
12