Nonlinear Postprocessing for Blind Speech Separation

  title={Nonlinear Postprocessing for Blind Speech Separation},
  author={Dorothea Kolossa and Reinhold Orglmeister},
Frequency domain ICA has been used successfully to separate the utterances of interfering speakers in convolutive environments, see e.g. [6],[7]. Improved separation results can be obtained by applying a time frequency mask to the ICA outputs. After using the direction of arrival information for permutation correction, the time frequency mask is obtained with little computational effort. The proposed postprocessing is applied in conjunction with two frequency domain ICA methods and a… CONTINUE READING
Highly Cited
This paper has 78 citations. REVIEW CITATIONS

From This Paper

Figures, tables, and topics from this paper.


Publications citing this paper.
Showing 1-10 of 40 extracted citations

Two-Microphone Separation of Speech Mixtures

IEEE Transactions on Neural Networks • 2008
View 3 Excerpts
Highly Influenced

A hypothesis testing approach for real-time multichannel speech separation using time-frequency masks

2016 IEEE 26th International Workshop on Machine Learning for Signal Processing (MLSP) • 2016
View 2 Excerpts

79 Citations

Citations per Year
Semantic Scholar estimates that this publication has 79 citations based on the available data.

See our FAQ for additional information.


Publications referenced by this paper.
Showing 1-8 of 8 references

Blind separation of speech mixtures via time-frequency masking

IEEE Transactions on Signal Processing • 2004
View 3 Excerpts
Highly Influenced

Maximum Likelihood Permutation Correction for Convolutive Source Separation

W. Baumann, D. Kolossa, R. Orglmeister
Proc. Int. Workshop on Independent Component Analysis and Blind Signal Separation, Nara, Japan • 2003

Similar Papers

Loading similar papers…