Single-channel blind source separation based on joint dictionary with common sub-dictionary
作者： Linhui Sun , Cheng Zhao , Min Su , Fu Wang
DOI: 10.1007/S10772-017-9469-2
关键词:
摘要: The cross projection engenders when mixed speech signal is represented over joint dictionary because of the bad distinguishing ability in single-channel blind source separation (SBSS) using sparse representation theory, which leads to performance. A new algorithm constructing with common sub-dictionary put forward this paper problem. can effectively avoid being projected another a dictionary. In algorithm, firstly we learn identify sub-dictionaries signals corresponding each speaker. And then discard similar atoms between two identity and construct these atoms. Finally, combine those three together into Euclidean distance among used measure correlation them different sub-dictionaries, are searched based on correlation. testing stage, be reconstructed coefficients individual sub-dictionary. Contrast experiments tested database show that proposed performs better, Signal-to-Noise Ratio (SNR) effect. set out has lower time complexity as well.
springer.com
sci-hub.se 参考文章(18)
Sirisha Rambhatla, Jarvis Haupt, Semi-blind source separation via sparse representations and online dictionary learning 2013 Asilomar Conference on Signals, Systems and Computers. pp. 1687- 1691 ,(2013) , 10.1109/ACSSC.2013.6810587
Guangzhao Bao, Yangfei Xu, Zhongfu Ye, Learning a discriminative dictionary for single-channel speech separation IEEE Transactions on Audio, Speech, and Language Processing. ,vol. 22, pp. 1130- 1138 ,(2014) , 10.1109/TASLP.2014.2320575
Miloud Frikel, Victor Barroso, Joao Xavier, Blind source separation Journal of the Acoustical Society of America. ,vol. 105, pp. 1101- 1102 ,(1999) , 10.1121/1.425160
Meng Yang, Lei Zhang, Jian Yang, David Zhang, Metaface learning for sparse representation based face recognition international conference on image processing. pp. 1601- 1604 ,(2010) , 10.1109/ICIP.2010.5652363
Pau Bofill, Michael Zibulevsky, Underdetermined blind source separation using sparse representations Signal Processing. ,vol. 81, pp. 2353- 2362 ,(2001) , 10.1016/S0165-1684(01)00120-7
Shahrzad Shapoori, Saeid Sanei, Wenwu Wang, Blind source separation of medial temporal discharges via partial dictionary learning international workshop on machine learning for signal processing. pp. 1- 5 ,(2015) , 10.1109/MLSP.2015.7324342
Longting Xu, Zhen Yang, Xi Shao, Dictionary design in subspace model for speaker identification International Journal of Speech Technology. ,vol. 18, pp. 177- 186 ,(2015) , 10.1007/S10772-014-9258-0
E. Vincent, R. Gribonval, C. Fevotte, Performance measurement in blind audio source separation IEEE Transactions on Audio, Speech, and Language Processing. ,vol. 14, pp. 1462- 1469 ,(2006) , 10.1109/TSA.2005.858005
A. Agrawal, R. Raskar, R. Chellappa, Edge Suppression by Gradient Field Transformation Using Cross-Projection Tensors computer vision and pattern recognition. ,vol. 2, pp. 2301- 2308 ,(2006) , 10.1109/CVPR.2006.106
M. Aharon, M. Elad, A. Bruckstein, $rm K$ -SVD: An Algorithm for Designing Overcomplete Dictionaries for Sparse Representation IEEE Transactions on Signal Processing. ,vol. 54, pp. 4311- 4322 ,(2006) , 10.1109/TSP.2006.881199