Towards effective singing voice extraction from stereophonic recordings

Stratis Sofianos, A. Ariyaeeinia, R. Polfreman

Research output: Chapter in Book/Report/Conference proceedingConference contribution

6 Citations (Scopus)
107 Downloads (Pure)


Extracting a singing voice from its music accompaniment can significantly facilitate certain applications of Music Information Retrieval including singer identification and singing melody extraction. In this paper, we present a hybrid approach for this purpose, which combines properties of the Azimuth Discrimination and Resynthesis (ADRess) method with Independent Component Analysis (ICA). Our proposed approach is developed specifically for the case of singing voice separation from stereophonic recordings. The paper presents the characteristics of the proposed method and details an objective evaluation of its effectiveness.
Original languageEnglish
Title of host publicationIEEE Int Conf on Acoustics Speech and Signal Processing
Subtitle of host publicationICASSP 2010
PublisherInstitute of Electrical and Electronics Engineers (IEEE)
ISBN (Print)978-1-4244-4296-6
Publication statusPublished - 2010


Dive into the research topics of 'Towards effective singing voice extraction from stereophonic recordings'. Together they form a unique fingerprint.

Cite this