基于Hilbert-Huang变换理论的语音增强初探

被引:10
作者
申丽然
李雪耀
王慧强
尹清波
张汝波
机构
[1] 哈尔滨工程大学计算机科学与技术学院
关键词
希尔伯特-黄变换; 非线性非稳态信号处理; 语音增强;
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
希尔伯特-黄变换是新发展起来强有力的非线性、非稳态信号处理方法.它从信号自身出发自适应地产生具有物理意义的基函数,而不是人为地设定变换的基函数.该文将这一全新的方法应用到语音信号处理.希尔伯特-黄变换基于信号的局部特征时间尺度,能把复杂的信号分解为有限的内在模态函数之和,这种自适应的分解方法非常适于非线性和非平稳过程的分析.实验表明,希尔伯特-黄变换适于语音信号处理,有广阔地应用前景.结合小波变换的分析表明,该方法在语音去噪方面优于小波变换.
引用
收藏
页码:220 / 224
页数:5
相关论文
共 10 条
  • [1] IKEDO J.Voice activity detection using neural network. IEEE Transactions on Communications . 1998
  • [2] GRBOC N,NORDHOLM S.Soft constrained subband beamforming for handsfree speech enhancement. IEEE International Conference on Acoustics, Speech and Signal Processing . 2002
  • [3] HUANG E.The empirical mode decomposition and the Hilbert spectrum for nonlinear and non_stastinary time series analysis. Proceedings of the Royal Society of London series A_Mathematical Physical and Engineering Sciences . 1998
  • [4] AMBIKAIRAJAH E,TATTERSALL G.Wavelet transform-based speech enhancement. ICSLP . 1998
  • [5] SOVKAP,POLAKP.Extendedspectralsubtraction. EUSIPCO’’96 . 1996
  • [6] COHEN.Time_frequencyanalysistheoryandapplications. . 1995
  • [7] MCAULAY R,OUATIERI T.Speech analysis/synthesis based on sinusoidal representation. IEEE Transactions on Applied Superconductivity . 1986
  • [8] SHEN Xuemin,DENG Li.A dynamic system approach to speech enhancement using the filtering algorithm. IEEE Transactions on Sepeech and Audio Processing . 1999
  • [9] SHARON G,BURSHTEIN.Signal enhancement using beamforming and nonstationarity with applications to Speech. IEEE Transactions on Signai Processing . 2001
  • [10] SEOK J W,BAE K S.Speech enhancement with reduction of noise components in the wavelet domain. IEEE International Conference on Acoustics Speech and Signal Processing Proceedings . 1997