Single-Channel Mixture Decomposition Using Bayesian Harmonic Models

We consider the source separation problem for single-channel music signals. After a brief review of existing methods, we focus on decomposing a mixture into components made of harmonic sinusoidal partials. We address this problem in the Bayesian framework by building a probabilistic model of the mixture combining generic priors for harmonicity, spectral envelope, note duration and continuity. Experiments suggest that the derived blind decomposition method leads to better separation results than nonnegative matrix factorization for certain mixtures.

[1]  Shankar Vembu,et al.  Separation of Vocals from Polyphonic Audio Recordings , 2005, ISMIR.

[2]  Simon J. Godsill,et al.  Bayesian harmonic models for musical pitch estimation and analysis , 2002, 2002 IEEE International Conference on Acoustics, Speech, and Signal Processing.

[3]  Emmanuel Vincent,et al.  Musical source separation using time-frequency source priors , 2006, IEEE Transactions on Audio, Speech, and Language Processing.

[4]  Mark R. Every,et al.  Separation of synchronous pitched notes by spectral filtering of harmonics , 2006, IEEE Transactions on Audio, Speech, and Language Processing.

[5]  P. Smaragdis,et al.  Non-negative matrix factorization for polyphonic music transcription , 2003, 2003 IEEE Workshop on Applications of Signal Processing to Audio and Acoustics (IEEE Cat. No.03TH8684).

[6]  Mark D. Plumbley,et al.  A prototype system for object coding of musical audio , 2005, IEEE Workshop on Applications of Signal Processing to Audio and Acoustics, 2005..

[7]  Shuichi Sakai,et al.  Musical sound source identification based on frequency com-ponent adaptation , 1999, IJCAI 1999.

[8]  James R. Hopgood,et al.  The effect of sensor placement in blind source separation , 2001, Proceedings of the 2001 IEEE Workshop on the Applications of Signal Processing to Audio and Acoustics (Cat. No.01TH8575).

[9]  Richard Heusdens,et al.  A new psychoacoustical masking model for audio coding applications , 2002, 2002 IEEE International Conference on Acoustics, Speech, and Signal Processing.

[10]  Tuomas Virtanen,et al.  Separation of drums from polyphonic music using non-negative matrix factorization and support vector machine , 2005, 2005 13th European Signal Processing Conference.

[11]  Tuomas Virtanen,et al.  ALGORITHM FOR THE SEPARATION OF HARMONIC SOUNDS WITH TIME- FREQUENCY SMOOTHNESS CONSTRAINT , 2003 .

[12]  Rémi Gribonval,et al.  Harmonic decomposition of audio signals with matching pursuit , 2003, IEEE Trans. Signal Process..

[13]  Rémi Gribonval,et al.  Non negative sparse representation for Wiener based source separation with a single sensor , 2003, 2003 IEEE International Conference on Acoustics, Speech, and Signal Processing, 2003. Proceedings. (ICASSP '03)..

[14]  P. Philippe,et al.  One microphone singing voice separation using source-adapted models , 2005, IEEE Workshop on Applications of Signal Processing to Audio and Acoustics, 2005..

[15]  Queen Mary.  MUSICAL AUDIO STREAM SEPARATION BY NON-NEGATIVE MATRIX FACTORIZATION , 2005 .

[16]  Daniel Patrick Whittlesey Ellis,et al.  Prediction-driven computational auditory scene analysis , 1996 .

[17]  Tuomas Virtanen,et al.  Separation of sound sources by convolutive sparse coding , 2004, SAPA@INTERSPEECH.