Parallel multichannel music source separation system

This paper presents a parallel low-latency multichannel source separation system designed to recover the original signals of the instruments that compound a multichannel music recording. Our approach is suitable for many applications based on interactive live broadcast classical music, where a latency of a few seconds can be assumed by online users. The obtained results show that it is possible to reach real time in the tested scenarios assuming a low-latency and combining multi-core architectures with parallel and high-performance techniques.

[1]  Guillaume Lemaitre,et al.  Real-time Polyphonic Music Transcription with Non-negative Matrix Factorization and Beta-divergence , 2010, ISMIR.

[2]  Nicolás Ruiz-Reyes,et al.  An Audio to Score Alignment Framework Using Spectral Factorization and Dynamic Time Warping , 2015, ISMIR.

[3]  Ed Anderson,et al.  LAPACK Users' Guide , 1995 .

[4]  Maximo Cobos,et al.  Nonnegative signal factorization with learnt instrument models for sound source separation in close-microphone recordings , 2013, EURASIP J. Adv. Signal Process..

[5]  Ricard Marxer Piñón.  Audio source separation for music in low-latency and high-latency scenarios , 2013 .

[6]  G. Elwyn,et al.  One hundred years ago: Should milk be boiled? , 2002, BMJ : British Medical Journal.

[7]  Harald Viste,et al.  Sound Source Separation: Preprocessing for Hearing Aids and Structured Audio Coding , 2001 .

[8]  Fabian J. Theis,et al.  The signal separation evaluation campaign (2007-2010): Achievements and remaining challenges , 2012, Signal Process..

[9]  Roland Badeau,et al.  Score informed audio source separation using a parametric model of non-negative spectrogram , 2011, 2011 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP).

[10]  Gaurav Sharma,et al.  Creating a Multitrack Classical Music Performance Dataset for Multimodal Music Analysis: Challenges, Insights, and Applications , 2016, IEEE Transactions on Multimedia.

[11]  José Ranilla,et al.  An efficient musical accompaniment parallel system for mobile devices , 2016, The Journal of Supercomputing.

[12]  Bryan Pardo,et al.  Online Score-Informed Source Separation with Adaptive Instrument Models , 2015 .

[13]  Elías F. Combarro,et al.  HReMAS: hybrid real-time musical alignment system , 2018, The Journal of Supercomputing.

[14]  José Ranilla,et al.  Parallel online time warping for real-time audio-to-score alignment in multi-core systems , 2016, The Journal of Supercomputing.

[15]  Guillaume Lemaitre,et al.  Real-Time Detection of Overlapping Sound Events with Non-Negative Matrix Factorization , 2013 .

[16]  Nicolás Ruiz-Reyes,et al.  Monophonic constrained non-negative sparse coding using instrument models for audio separation and transcription of monophonic source-based polyphonic mixtures , 2013, Multimedia Tools and Applications.

[17]  Daniel P. W. Ellis,et al.  Ground-truth transcriptions of real music from force-aligned MIDI syntheses , 2003, ISMIR.

[18]  L. Dagum,et al.  OpenMP: an industry standard API for shared-memory programming , 1998 .

[19]  Masataka Goto,et al.  RWC Music Database: Popular, Classical and Jazz Music Databases , 2002, ISMIR.

[20]  Rémi Gribonval,et al.  Performance measurement in blind audio source separation , 2006, IEEE Transactions on Audio, Speech, and Language Processing.

[21]  Jordi Janer,et al.  Score-Informed Source Separation for Multichannel Orchestral Recordings , 2016, J. Electr. Comput. Eng..

[22]  Tuomas Virtanen,et al.  Musical Instrument Sound Multi-Excitation Model for Non-Negative Spectrogram Factorization , 2011, IEEE Journal of Selected Topics in Signal Processing.

[23]  Meinard Müller,et al.  Estimating note intensities in music recordings , 2011, 2011 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP).

[24]  Rémi Gribonval,et al.  Under-Determined Reverberant Audio Source Separation Using a Full-Rank Spatial Covariance Model , 2009, IEEE Transactions on Audio, Speech, and Language Processing.

[25]  Bryan Pardo,et al.  Soundprism: An Online System for Score-Informed Source Separation of Music Audio , 2011, IEEE Journal of Selected Topics in Signal Processing.

[26]  Tapio Lokki,et al.  Anechoic recording system for symphony orchestra , 2008 .

[27]  Parag Chordia,et al.  Using Source Separation to Improve Tempo Detection , 2009, ISMIR.

[28]  Nicolás Ruiz-Reyes,et al.  Online/offline score informed music signal decomposition: application to minus one , 2019 .

[29]  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..

[30]  Jordi Janer,et al.  Improving Score-Informed Source Separation for Classical Music through Note Refinement , 2015, ISMIR.

[31]  Jürgen Herre,et al.  Spatial Audio Coding: Next-generation efficient and compatible coding of multi-channel audio , 2005 .

[32]  Roger B. Dannenberg,et al.  Remixing Stereo Music with Score-Informed Source Separation , 2006, ISMIR.

[33]  Nicolás Ruiz-Reyes,et al.  Constrained non-negative matrix factorization for score-informed piano music restoration , 2016, Digit. Signal Process..

[34]  Matteo Frigo,et al.  A fast Fourier transform compiler , 1999, SIGP.

[35]  José Ranilla,et al.  Real-time Soundprism , 2018, The Journal of Supercomputing.

[36]  Masataka Goto,et al.  Instrument Equalizer for Query-by-Example Retrieval: Improving Sound Source Separation Based on Integrated Harmonic and Inharmonic Models , 2008, ISMIR.

[37]  Paris Smaragdis,et al.  Singing-voice separation from monaural recordings using robust principal component analysis , 2012, 2012 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP).

[38]  Masataka Goto,et al.  Development of the RWC Music Database , 2004 .