Abstract | ||
---|---|---|
Single-channel source separation is an approach to decomposing a single-channel recording into its sources without understanding how the sources are mixed. This work develops a sparse regularized nonnegative matrix factorization scheme with spatial dispersion penalty (SpaSNMF). To preserve spatial locality structured information on the basis for sound source separation, intra-sample structure constraints that are learnt from the input data are utilized. Based on the hypothesis that adjacent spectrogram points should not be dispersed in basis spectra, this framework is provided for supervised source separation. To improve the separation performance, group sparse penalties are simultaneously constructed. A multiple-update-rule optimization scheme was used to solve the objective function of the proposed SpaSNMF. Experiments on single-channel source separation reveal that the proposed method provides more robust basis factors and achieves better results than standard NMF and its extensions. |
Year | DOI | Venue |
---|---|---|
2016 | 10.1109/ISCSLP.2016.7918452 | 2016 10th International Symposium on Chinese Spoken Language Processing (ISCSLP) |
Keywords | Field | DocType |
graph regularization,non-negative matrix factorization,source separation,multiple update rule | Locality,Pattern recognition,Computer science,Spectrogram,Signal-to-noise ratio,Speech recognition,Artificial intelligence,Non-negative matrix factorization,Linear programming,Blind signal separation,Sparse matrix,Source separation | Conference |
ISBN | Citations | PageRank |
978-1-5090-4295-1 | 0 | 0.34 |
References | Authors | |
0 | 6 |
Name | Order | Citations | PageRank |
---|---|---|---|
Viet-Hang Duong | 1 | 2 | 2.75 |
Yuan-Shan Lee | 2 | 23 | 8.51 |
Bach-Tung Pham | 3 | 1 | 1.37 |
Seksan Mathulaprangsan | 4 | 2 | 1.71 |
Pham The Bao | 5 | 22 | 7.70 |
Jia-Ching Wang | 6 | 515 | 58.13 |