Beta Divergence for Clustering in Monaural Blind Source Separation

Spiertz M, Gnann V. Beta Divergence for Clustering in Monaural Blind Source Separation. In: AES Convention 128. Audio Engineering Society; 2010. Paper 8130. Available from: https://aes.org/publications/elibrary-page/?id=15427

@inproceedings{Spiertz2010_15427,
  author = {Spiertz, Martin and Gnann, Volke},
  title = {{Beta Divergence for Clustering in Monaural Blind Source Separation}},
  booktitle = {AES Convention 128},
  note = {Paper 8130},
  year = {2010},
  month = may,
  publisher = {Audio Engineering Society},
  url = {https://aes.org/publications/elibrary-page/?id=15427}
}

TY  - CPAPER
TI  - Beta Divergence for Clustering in Monaural Blind Source Separation
AU  - Spiertz, Martin
AU  - Gnann, Volke
T2  - AES Convention 128
M1  - Paper 8130
PY  - 2010
DA  - 2010/05/06
UR  - https://aes.org/publications/elibrary-page/?id=15427
PB  - Audio Engineering Society
LA  - en
AB  - General purpose audio blind source separation algorithms have to deal with a large dynamic range for the different sources to be separated. In our algorithm the mixture is separated into single notes. These notes are clustered to construct the melodies played by the active sources. The non-negative matrix factorization (NMF) leads to good results in clustering the notes according to spectral features. The cost function for the NMF is controlled by a parameter beta. The choice of beta depends on the dynamic difference of the sources. The novelty of this paper is to propose a simple classifier to adjust the parameter beta to current dynamic ranges for increasing the separation quality.
ER  -