Skip to content

Learning to separate vocals from polyphonic mixtures via ensemble methods and structured output prediction

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

Original languageEnglish
Title of host publication2016 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)
Publisher or commissioning bodyInstitute of Electrical and Electronics Engineers (IEEE)
Number of pages5
ISBN (Electronic)9781479999880
ISBN (Print)9781479999873
DateAccepted/In press - 21 Dec 2015
DatePublished (current) - 19 May 2016

Publication series

ISSN (Electronic)2379-190X


Separating the singing from a polyphonic mixed audio signal is a challenging but important task, with a wide range of applications across the music industry and music informatics research. Various methods have been devised over the years, ranging from Deep Learning approaches to dedicated ad hoc solutions. In this paper, we present a novel machine learning method for the task, using a Conditional Random Field (CRF) approach for structured output prediction. We exploit the diversity of previously proposed approaches by using their predictions as input features to our method - thus effectively developing an ensemble method. Our empirical results demonstrate the potential of integrating predictions from different previously-proposed methods into one ensemble method, and additionally show that CRF models with larger complexities generally lead to superior performance.

    Research areas

  • Ensemble method, Singing voice separation, Conditional random fields, Spectogram, Hidden markov model, Time-frequency analysis, Computational modeling, Machine learning, Harmonic analysis, Radio frequency

Download statistics

No data available



  • Full-text PDF (accepted author manuscript)

    Rights statement: This is the author accepted manuscript (AAM). The final published version (version of record) is available online via IEEE at . Please refer to any applicable terms of use of the publisher.

    Accepted author manuscript, 2 MB, PDF document


View research connections

Related faculties, schools or groups