Comprehensive Survey on Single Channel Source Separation (SCSS)

  Jasreen Kaur,  Shailaja Gaikwad

In applications such as audio denoising, music transcription, music remixing, and audio based forensics, Speech denoising and enhancement, it is desirable to segregate a single-channel recording into its respective sources. The aim of getting the desired source from a mixture of sources and noise poses a great difficulty for researchers, especially when each source is highly correlated with one another. The research has been ongoing about the various solutions to be given for the single channel source separation. These works are motivated by the fact that real world sounds are inherently constructed by many individual sounds (e.g., human speakers, musical instruments, background noise, etc.). So, this paper has described various types of methods that have been used for Single Channel Source Separation (SCSS).In addition to this various model has been discussed in the paper. A brief introduction and literature review on the various methodologies is given in this paper. Different designs of experiment techniques available for the optimization of experimental runs have been reviewed.

Keywords- SCSS, Blind Source Separation, BSS, NMF, Single channel

Unique Identification Number - IJEDR1602037
Page Number(s) - 214-217
Pubished in - Volume 4 | Issue 2 | April 2016
DOI (Digital Object Identifier) -   
Publisher - IJEDR (ISSN - 2321-9939)

  Jasreen Kaur,  Shailaja Gaikwad,   "Comprehensive Survey on Single Channel Source Separation (SCSS)", International Journal of Engineering Development and Research (IJEDR), ISSN:2321-9939, Volume.4, Issue 2, pp.214-217, April 2016, Available at :http://www.ijedr.org/papers/IJEDR1602037.pdf