caa a22 4500 606205527 CHVBK 20210128101007.0 cr unu---uuuuu 210128e20151201xx s 000 0 eng 10.1007/s00034-015-0033-5 doi (NATIONALLICENCE)springer-10.1007/s00034-015-0033-5 Single-channel Speech Separation Using Dictionary-updated Orthogonal Matching Pursuit and Temporal Structure Information [Elektronische Daten] [Haiyan Guo, Xiaoxiong Li, Lin Zhou, Zhenyang Wu] In this paper, we propose a two-stage sparse decomposition-based method for single-channel speech separation in time domain. First, we propose a Dictionary-updated orthogonal matching pursuit (DUOMP) algorithm which is used in both separation stages. In the proposed DUOMP algorithm, all atoms of each source-specific dictionary are updated by subtracting off the current approximation of each source to the original atoms. It is proved that the DUOMP algorithm can limit the separated sources within a region where they are uncorrelated in statistical sense more quickly. Then, we propose an adaptive dictionary generation method followed by a frame labeling method to perform a second-stage separation on the mixed frames having certain temporal structure. Experiments show that the proposed method outperforms a separation method using sparse non-negative matrix factorization (SNMF), a separation method using OMP and a source-filter-based method using pitch information in overall. Additionally, what affects the performance of the proposed method is also shown. Springer Science+Business Media New York, 2015 Single-channel speech separation (SCSS) nationallicence Sparse decomposition nationallicence Orthogonal matching pursuit (OMP) nationallicence Dictionary nationallicence Guo Haiyan School of Information Science and Engineering, Southeast University, 210096, Nanjing, China aut Li Xiaoxiong School of Information Science and Engineering, Southeast University, 210096, Nanjing, China aut Zhou Lin School of Information Science and Engineering, Southeast University, 210096, Nanjing, China aut Wu Zhenyang School of Information Science and Engineering, Southeast University, 210096, Nanjing, China aut Circuits, Systems, and Signal Processing Springer US; http://www.springer-ny.com 34/12(2015-12-01), 3861-3882 0278-081X 34:12<3861 2015 34 34 https://doi.org/10.1007/s00034-015-0033-5 text/html Onlinezugriff via DOI BK010053 XK010053 XK010000 Metadata rights reserved Springer special CC-BY-NC licence nationallicence 1 research-article jats NATIONALLICENCE NATIONALLICENCE NL-springer NATIONALLICENCE 856 40 https://doi.org/10.1007/s00034-015-0033-5 text/html Onlinezugriff via DOI NATIONALLICENCE 700 1- Guo Haiyan School of Information Science and Engineering, Southeast University, 210096, Nanjing, China aut NATIONALLICENCE 700 1- Li Xiaoxiong School of Information Science and Engineering, Southeast University, 210096, Nanjing, China aut NATIONALLICENCE 700 1- Zhou Lin School of Information Science and Engineering, Southeast University, 210096, Nanjing, China aut NATIONALLICENCE 700 1- Wu Zhenyang School of Information Science and Engineering, Southeast University, 210096, Nanjing, China aut NATIONALLICENCE 773 0- Circuits, Systems, and Signal Processing Springer US; http://www.springer-ny.com 34/12(2015-12-01), 3861-3882 0278-081X 34:12<3861 2015 34 34