A Method for Under-determined Blind Source Separation Based on New Mixture Model
-
摘要: 针对欠定盲分离问题,提出了一种新的源恢复方法. 在时频域局部区域采用复高斯分布对源信号进行建模,将语音信号的稀疏性和局部平稳性结合在一起,提出了一种新的混合模型来描述观测信号在局部区域的概率分布.通过该模型,将每个时频点的源信号状态的判断问题转换成模型的参数估计和后验概率的计算问题,最后通过子混合矩阵的逆恢复出源信号. 实验结果表明,该方法具有很快的收敛速度,并且比已有方法具有更好的分离性能.Abstract: To solve the problem of under-determined blind source separation, we propose a new source recovery method. By utilizing the complex valued Gaussian model to characterize the local distribution of source signals in each micro-region in the time-frequency domain and combining speech signals' sparsity with their local stability, a new mixture model is derived to characterize the local distribution of observed signals. We convert the problem of judging the state of each source signal at each time-frequency point into a problem of model's parameters estimation and posterior probability computation. Finally, the source signals are recovered by sub-mixing matrix's inverse. Experiment results show that the proposed method converges very fast and has better separation performance compared with the existing methods.
-
[1] Chien J T, Hsieh H L. Convex divergence ICA for blind source separation. IEEE Transactions on Audio, Speech, and Language Processing, 2012, 20(1): 302-313 [2] Kang Chun-Yu, Zhang Xin-Hua, Han Dong. DOA estimation and signal recovery combined blind source separation with high resolution. Acta Automatica Sinica, 2010, 36(3): 442-445(康春玉, 章新华, 韩东. 盲源分离与高分辨融合的DOA估计与信号恢复方法. 自动化学报, 2010, 36(3): 442-445) [3] Yilmz O, Rickard S. Blind separation of speech mixtures via time-frequency masking. IEEE Transactions on Signal Processing, 2004, 52(7): 1830-1847 [4] Arakia S, Sawada H, Mukai R, Makino S. Underdetermined blind sparse source separation for arbitrarily arranged multiple sensors. Signal Processing, 2007, 87(8): 1833-1847 [5] Zibulevsky M, Pearlmutter B A. Blind source separation by sparse decomposition in a signal dictionary. Neural Computation, 2001, 13(4): 863-882 [6] O'Grady P D, Pearlmutter B A. The LOST algorithm: finding lines and separating speech mixtures. EURASIP Journal on Advances in Signal Processing, 2008, 784296: 1-17 [7] Cobos M, Lopez J J. Maximum a posteriori binary mask estimation for underdetermined source separation using smoothed posteriors. IEEE Transactions on Audio, Speech, and Language Processing, 2012, 20(7): 2059-2064 [8] Mitianoudis N. A generalized directional Laplacian distribution: estimation, mixture models and audio source separation. IEEE Transactions on Audio, Speech, and Language Processing, 2012, 20(9): 2397-2408 [9] Fevotte C, Cardoso J. Maximum likelihood approach for blind audio source separation using time-frequency Gaussian source models. In: Proceedings of IEEE Workshop on Applications of Signal Processing to Audio and Acoustics. New Paltz, New York, USA: IEEE, 2005. 78-81 [10] Ozerov A, Philippe P, Bimbot F, Gribonval R. Adaptation of bayesian models for single-channel source separation and its application to voice/music separation in popular songs. IEEE Transactions on Audio, Speech and Language Processing, 2007, 15(5): 1564-1578 [11] Benaroya L, Bimbot F, Gribonval R. Audio source separation with a single sensor. IEEE Transactions on Audio, Speech, and Language Processing, 2006, 14(1): 191-199 [12] Kim S G, Yoo C D. Underdetermined blind source separation based on subspace representation. IEEE Transactions on Signal Processing, 2009, 57(7): 2604-2614 [13] Aissa-El-Bey A, Linh-Trung N, Abed-Meraimet K, Belouchrani A, Grenier Y. Underdetermined blind separation of nondisjoint sources in the time-frequency domain. IEEE Transactions on Signal Processing, 2007, 55(3): 897-907 [14] Lu Feng-Bo, Huang Zhi-Tao, Jiang Wen-Li. Underdetermined blind separation of time-delayed non-stationary signal based on single source region in the time-frequency domain. Acta Electronica Sinica, 2011, 39(4): 854-858(陆凤波, 黄知涛, 姜文利. 基于时频域单源区域的延迟欠定混合非平稳信号盲分离. 电子学报, 2011, 39(4): 854-858) [15] Peng D Z, Xiang Y. Underdetermined blind source separation based on relaxed sparsity condition of sources. IEEE Transactions on Signal Processing, 2009, 57(2): 809-814 [16] Xie S, Yang L, Yang J M, Zhou G, Xiang Y. Time-frequency approach to underdetermined blind source separation. IEEE Transactions on Neural Networks and Learning System, 2012, 23(2): 306-316 [17] Lu F B, Huang Z T, Jiang W L. Underdetermined blind separation of non-disjoint signals in time-frequency domain based on matrix diagonalization. Signal Processing, 2011, 91(7): 1568-1577 [18] Reju V G, Koh S N, Soon I Y. An algorithm for mixing matrix estimation in instantaneous blind source separation. Signal Processing, 2009, 89(9): 1762-1773 [19] Zhou G X, Yang Z Y, Xie S L, Yang J M. Mixing matrix estimation from sparse mixtures with unknown number of sources. IEEE Transactions on Neural Networks, 2011, 22(2): 211-221 [20] Xiao Ming, Xie Sheng-Li, Fu Yu-Li. Underdetermined blind source separation algorithm based on normal vector of hyperplane. Acta Automatica Sinica, 2008, 34(2): 142-149(肖明, 谢胜利, 傅予力. 基于超平面法矢量的欠定盲信号分离算法. 自动化学报, 2008, 34(2): 142-149) [21] Chen Yong-Qiang, Wang Hong-Xia. A robust method for mixing matrix estimation in blind source separation. Journal of Electronics & Information Technology, 2012, 34(9): 2039-2044(陈永强, 王宏霞. 一种强鲁棒性的盲分离混合矩阵估计方法. 电子与信息学报, 2012, 34(9): 2039-2044) [22] Van Den Bos A. The multivariate complex normal distribution-a generalization. IEEE Transactions on Information Theory, 1995, 41(2): 537-539 [23] McLachlan G J, Krishnan T. The EM Algorithm and Extensions. New York, USA: Wiley, 1997. 18-27
点击查看大图
计量
- 文章访问数: 1700
- HTML全文浏览量: 25
- PDF下载量: 735
- 被引次数: 0