Monaural Sound Source Separation by Nonnegative Matrix Factorization With Temporal Continuity and Sparseness Criteria

@article{Virtanen2007MonauralSS,
  title={Monaural Sound Source Separation by Nonnegative Matrix Factorization With Temporal Continuity and Sparseness Criteria},
  author={Tuomas Virtanen},
  journal={IEEE Transactions on Audio, Speech, and Language Processing},
  year={2007},
  volume={15},
  pages={1066-1074}
}
An unsupervised learning algorithm for the separation of sound sources in one-channel music signals is presented. The algorithm is based on factorizing the magnitude spectrogram of an input signal into a sum of components, each of which has a fixed magnitude spectrum and a time-varying gain. Each sound source, in turn, is modeled as a sum of one or more components. The parameters of the components are estimated by minimizing the reconstruction error between the input spectrogram and the model… CONTINUE READING
Highly Influential
This paper has highly influenced 62 other papers. REVIEW HIGHLY INFLUENTIAL CITATIONS
Highly Cited
This paper has 935 citations. REVIEW CITATIONS

Citations

Publications citing this paper.
Showing 1-10 of 607 extracted citations

Monaural speaker separation using source-contrastive estimation

2017 IEEE International Workshop on Signal Processing Systems (SiPS) • 2017
View 6 Excerpts
Highly Influenced

Adaptive weights for NMF with additional priors

2015 International Symposium on Intelligent Signal Processing and Communication Systems (ISPACS) • 2015
View 6 Excerpts
Highly Influenced

Component-Adaptive Priors for NMF

View 13 Excerpts
Highly Influenced

936 Citations

050100'08'11'14'17
Citations per Year
Semantic Scholar estimates that this publication has 936 citations based on the available data.

See our FAQ for additional information.

Similar Papers

Loading similar papers…