基于时-频分析的语音盲分离算法
摘要
在时-频分析算法中,窗长的选择对分离语音信号的性能有着重要的影响。文章详细介绍了基于时-频分析的语音盲分离算法,并用MATLAB仿真分析了不同窗函数、窗长的选择对分离信号性能的影响。实验证明,对于语音这种短时平稳信号,用时-频分析盲分离算法分离混合语音信号时,窗长选择为256时可取得最佳的分离效果。
出处
《计算机时代》
2009年第5期28-30,共3页
Computer Era
参考文献10
-
1Bell A J. Sejnowski T J. An information maximization approach to blind separation and blind deconvolution[J].Nerual Computation, 1995.7(6): 1129-1159.
-
2D.P.Morgan etal, Cochannel speaker separation by harmonic enhancement and suppression'[J].IEEE Trans On Speech and Audio Processing,1997.9.5.
-
3T.W.Lee, A.J.BelI, and R.Lambert. Blind separation of delayed and convolved source[J].Adavances in Neural Inf. Proc. Systems 9, 1997:758-764.
-
4T.W.Lee,A contextual blind source separation of delayed and convoled sources[J].Proc. ICASSP, Munich, Germany,1997.4: 1199-1202.
-
5L. B. ALMEIDA, Linear and Nonlinear ICA Based on Mutual Information-the MISEP Method[J].Signal Processing,2004.84 (2):231-245.
-
6D. Smith, J. Lukasiak, I. S. Burnett An analysis of the limitations of blind signal separation application with speech[J].Signal Processing 86,2006:353-359.
-
7Y. Deville, Temporal and time-frequency correlation-based blind source separation methods[A].Proceedings of the Fourth International Symposium on Independent Component Analysis and Blind Signal Separation (ICA 2003), Nara, Japan, 2003.4: 1059-1064.
-
8Matthieu Puigt, Yannick Deville Time-frequency ratio-based blind separation methods for attenuated and time-delayed source Mechanical[J].Systems and Signal Processing 19,2005:1348- 1379.
-
9F. Abrard, Y. Deville, "A time-frequency blind signal separation method applicable to underdetermined mixtures of dependent sources" [J].Signal Processing.http://authors .elsevier.com/sd/ srticle/S016516840500054X,2005.85(7): 1389-1402.
-
10Y. Deville, M. Puigt, B. Albouy, Time-frequency blind signal separation: extended methods, performance evaluation for speech sources[C].Proceedings of the International Joint Conference on Neural Networks (IJCNN 2004), Budapest, Hungary,IEEE Catalog Number:04CH37541C,ISBN:0-7803- 8360-5,2004.7:255-260.
-
1王国鹏,刘郁林,罗颖光.弱时频正交性条件下的混合矩阵盲估计[J].数据采集与处理,2010,25(1):18-22. 被引量：4
-
2王国鹏,刘郁林,罗颖光.结合主分量分析与DOA估计的语音盲分离[J].声学技术,2009,28(5):624-628.
-
3职振华,马建芬,张雪英.一种新的用于语音分离的盲源分离算法[J].计算机工程与应用,2007,43(30):77-78.
-
4王继曾,王婵飞.基于小波变换的自适应语音盲分离新算法[J].电声技术,2008,32(5):54-56. 被引量：1
-
5邹长满.基于小波变换图像处理的快速匹配算法[J].产业与科技论坛,2013(16):90-91.
-
6刘伯权,曾以成,邬鑫锋.独立分量分析与时频掩蔽结合的语音盲分离[J].计算机工程与应用,2010,46(32):130-132.
-
7王国鹏,刘郁林,罗颖光.弱稀疏性下的欠定语音盲分离方法[J].计算机工程,2009,35(18):246-248. 被引量：2
-
8张祖兴,刘军,汤谊兵,王威廉.连续小波变换和匹配追踪算法在心音信号分析上的应用和对比[J].生物医学工程学杂志,2008(4):756-761. 被引量：7
-
9夏秀渝,何培宇,周激流.一种基于时域解相关的双通道语音分离算法[J].电子技术应用,2008,34(2):113-115.
-
10王凯旋,戴志强,伍龙山.卷积混合语音信号的盲分离研究[J].中国科技纵横,2010(7):96-97.
