{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,1,31]],"date-time":"2026-01-31T07:43:06Z","timestamp":1769845386866,"version":"3.49.0"},"reference-count":27,"publisher":"Springer Science and Business Media LLC","issue":"9","license":[{"start":{"date-parts":[[2024,3,6]],"date-time":"2024-03-06T00:00:00Z","timestamp":1709683200000},"content-version":"tdm","delay-in-days":0,"URL":"https:\/\/creativecommons.org\/licenses\/by\/4.0"},{"start":{"date-parts":[[2024,3,6]],"date-time":"2024-03-06T00:00:00Z","timestamp":1709683200000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/creativecommons.org\/licenses\/by\/4.0"}],"funder":[{"DOI":"10.13039\/501100004837","name":"Ministerio de Ciencia e Innovaci\u00f3n,Spain","doi-asserted-by":"crossref","award":["PID2020-119082RB-C21,C22"],"award-info":[{"award-number":["PID2020-119082RB-C21,C22"]}],"id":[{"id":"10.13039\/501100004837","id-type":"DOI","asserted-by":"crossref"}]},{"DOI":"10.13039\/100018693","name":"HORIZON EUROPE Framework Programme","doi-asserted-by":"publisher","award":["101095065"],"award-info":[{"award-number":["101095065"]}],"id":[{"id":"10.13039\/100018693","id-type":"DOI","asserted-by":"publisher"}]},{"DOI":"10.13039\/100011941","name":"Gobierno del Principado de Asturias","doi-asserted-by":"publisher","award":["AYUD\/2021\/50994"],"award-info":[{"award-number":["AYUD\/2021\/50994"]}],"id":[{"id":"10.13039\/100011941","id-type":"DOI","asserted-by":"publisher"}]},{"DOI":"10.13039\/501100007210","name":"RWTH Aachen University","doi-asserted-by":"crossref","id":[{"id":"10.13039\/501100007210","id-type":"DOI","asserted-by":"crossref"}]}],"content-domain":{"domain":["link.springer.com"],"crossmark-restriction":false},"short-container-title":["J Supercomput"],"published-print":{"date-parts":[[2024,6]]},"abstract":"<jats:title>Abstract<\/jats:title><jats:p>Sound source separation (SSS) is a fundamental problem in audio signal processing, aiming to recover individual audio sources from a given mixture. A promising approach is multichannel non-negative matrix factorization (MNMF), which employs a Gaussian probabilistic model encoding both magnitude correlations and phase differences between channels through spatial covariance matrices (SCM). In this work, we present a dedicated hardware architecture implemented on field programmable gate arrays (FPGAs) for efficient SSS using MNMF-based techniques. A novel decorrelation constraint is presented to facilitate the factorization of the SCM signal model, tailored to the challenges of multichannel source separation. The performance of this FPGA-based approach is comprehensively evaluated, taking advantage of the flexibility and computational capabilities of FPGAs to create an efficient real-time source separation framework. Our experimental results demonstrate consistent, high-quality results in terms of sound separation.<\/jats:p>","DOI":"10.1007\/s11227-024-05945-w","type":"journal-article","created":{"date-parts":[[2024,3,6]],"date-time":"2024-03-06T18:01:51Z","timestamp":1709748111000},"page":"13411-13433","update-policy":"https:\/\/doi.org\/10.1007\/springer_crossmark_policy","source":"Crossref","is-referenced-by-count":4,"title":["Efficient FPGA implementation for sound source separation using direction-informed multichannel non-negative matrix factorization"],"prefix":"10.1007","volume":"80","author":[{"given":"Philipp","family":"Diel","sequence":"first","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Antonio J.","family":"Mu\u00f1oz-Montoro","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Julio J.","family":"Carabias-Orti","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Jose","family":"Ranilla","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"297","published-online":{"date-parts":[[2024,3,6]]},"reference":[{"issue":"3","key":"5945_CR1","doi-asserted-by":"publisher","first-page":"120","DOI":"10.17743\/jaes.2019.0055","volume":"68","author":"JG Tylka","year":"2020","unstructured":"Tylka JG, Choueiri EY (2020) Fundamentals of a parametric method for virtual navigation within an array of ambisonics microphones. J Audio Eng Soc 68(3):120\u2013137","journal-title":"J Audio Eng Soc"},{"key":"5945_CR2","doi-asserted-by":"publisher","first-page":"2333","DOI":"10.1109\/TASLP.2020.3012058","volume":"28","author":"M Pezzoli","year":"2020","unstructured":"Pezzoli M, Borra F, Antonacci F, Tubaro S, Sarti A (2020) A parametric approach to virtual miking for sources of arbitrary directivity. IEEE\/ACM Trans Audio Speech Lang Process 28:2333\u20132348","journal-title":"IEEE\/ACM Trans Audio Speech Lang Process"},{"key":"5945_CR3","doi-asserted-by":"crossref","unstructured":"FitzGerald D, Cranitch M, Coyle E (2005) Non-negative tensor factorisation for sound source separation. In: IEEE Irish Signals and Systems Conference, vol 2005. IEEE, pp 8\u201312","DOI":"10.1049\/cp:20050279"},{"issue":"3","key":"5945_CR4","doi-asserted-by":"publisher","first-page":"550","DOI":"10.1109\/TASL.2009.2031510","volume":"18","author":"A Ozerov","year":"2010","unstructured":"Ozerov A, Fevotte C (2010) Multichannel nonnegative matrix factorization in convolutive mixtures for audio source separation. IEEE Trans Audio Speech Lang Process 18(3):550\u2013563. https:\/\/doi.org\/10.1109\/TASL.2009.2031510","journal-title":"IEEE Trans Audio Speech Lang Process"},{"issue":"5","key":"5945_CR5","doi-asserted-by":"publisher","first-page":"971","DOI":"10.1109\/TASL.2013.2239990","volume":"21","author":"H Sawada","year":"2013","unstructured":"Sawada H, Kameoka H, Araki S, Ueda N (2013) Multichannel extensions of non-negative matrix factorization with complex-valued data. IEEE Trans Audio Speech Lang Process 21(5):971\u2013982. https:\/\/doi.org\/10.1109\/TASL.2013.2239990","journal-title":"IEEE Trans Audio Speech Lang Process"},{"issue":"3","key":"5945_CR6","doi-asserted-by":"publisher","first-page":"727","DOI":"10.1109\/TASLP.2014.2303576","volume":"22","author":"J Nikunen","year":"2014","unstructured":"Nikunen J, Virtanen T (2014) Direction of arrival based spatial covariance model for blind sound source separation. IEEE\/ACM Trans Audio Speech Lang Process 22(3):727\u2013739. https:\/\/doi.org\/10.1109\/TASLP.2014.2303576","journal-title":"IEEE\/ACM Trans Audio Speech Lang Process"},{"key":"5945_CR7","doi-asserted-by":"crossref","unstructured":"Carabias-Orti JJ, Cabanas-Molero P, Vera-Candeas P, Nikunen J (2018) Multi-source localization using a DOA kernel based spatial covariance model and complex nonnegative matrix factorization. In: 2018 IEEE 10th Sensor Array and Multichannel Signal Processing Workshop (SAM), IEEE, pp 440\u2013444","DOI":"10.1109\/SAM.2018.8448664"},{"issue":"9","key":"5945_CR8","doi-asserted-by":"publisher","first-page":"1626","DOI":"10.1109\/TASLP.2016.2577880","volume":"24","author":"D Kitamura","year":"2016","unstructured":"Kitamura D, Ono N, Sawada H, Kameoka H, Saruwatari H (2016) Determined blind source separation unifying independent vector analysis and nonnegative matrix factorization. IEEE\/ACM Trans Audio Speech Lang Process 24(9):1626\u20131641. https:\/\/doi.org\/10.1109\/TASLP.2016.2577880","journal-title":"IEEE\/ACM Trans Audio Speech Lang Process"},{"key":"5945_CR9","doi-asserted-by":"publisher","first-page":"2610","DOI":"10.1109\/TASLP.2020.3019181","volume":"28","author":"K Sekiguchi","year":"2020","unstructured":"Sekiguchi K, Bando Y, Nugraha AA, Yoshii K, Kawahara T (2020) Fast multichannel nonnegative matrix factorization with directivity-aware jointly-diagonalizable spatial covariance matrices for blind source separation. IEEE\/ACM Trans Audio Speech Lang Process 28:2610\u20132625. https:\/\/doi.org\/10.1109\/TASLP.2020.3019181","journal-title":"IEEE\/ACM Trans Audio Speech Lang Process"},{"key":"5945_CR10","doi-asserted-by":"publisher","first-page":"1670","DOI":"10.1109\/LSP.2021.3101699","volume":"28","author":"Y Bando","year":"2021","unstructured":"Bando Y, Sekiguchi K, Masuyama Y, Nugraha AA, Fontaine M, Yoshii K (2021) Neural full-rank spatial covariance analysis for blind source separation. IEEE Signal Process Lett 28:1670\u20131674. https:\/\/doi.org\/10.1109\/LSP.2021.3101699","journal-title":"IEEE Signal Process Lett"},{"issue":"10","key":"5945_CR11","doi-asserted-by":"publisher","first-page":"12143","DOI":"10.1007\/s11227-021-03771-y","volume":"77","author":"AJ Mu\u00f1oz-Montoro","year":"2021","unstructured":"Mu\u00f1oz-Montoro AJ, Carabias-Orti JJ, Cortina R, Garc\u00eda-Gal\u00e1n S, Ranilla J (2021) Parallel multichannel blind source separation using a spatial covariance model and nonnegative matrix factorization. J Supercomput 77(10):12143\u201312156. https:\/\/doi.org\/10.1007\/s11227-021-03771-y","journal-title":"J Supercomput"},{"key":"5945_CR12","doi-asserted-by":"publisher","first-page":"1","DOI":"10.1007\/s11227-023-05471-1","volume":"79","author":"AJ Mu\u00f1oz-Montoro","year":"2023","unstructured":"Mu\u00f1oz-Montoro AJ, Carabias-Orti JJ, Salvati D, Cortina R (2023) Efficient parallel kernel based on Cholesky decomposition to accelerate multichannel nonnegative matrix factorization. J Supercomput 79:1\u201316","journal-title":"J Supercomput"},{"key":"5945_CR13","doi-asserted-by":"publisher","first-page":"73","DOI":"10.1007\/978-3-319-73031-8_4","volume-title":"Audio Source Sep","author":"A Ozerov","year":"2018","unstructured":"Ozerov A, F\u00e9votte C, Vincent E (2018) An introduction to multichannel NMF for audio source separation. In: Makino S (ed) Audio Source Sep. Springer, Cham, pp 73\u201394"},{"issue":"7","key":"5945_CR14","doi-asserted-by":"publisher","first-page":"1830","DOI":"10.1109\/TASL.2010.2050716","volume":"18","author":"NQK Duong","year":"2010","unstructured":"Duong NQK, Vincent E, Gribonval R (2010) Under-determined reverberant audio source separation using a full-rank spatial covariance model. IEEE Trans Audio Speech Lang Process 18(7):1830\u20131840. https:\/\/doi.org\/10.1109\/TASL.2010.2050716","journal-title":"IEEE Trans Audio Speech Lang Process"},{"issue":"9","key":"5945_CR15","doi-asserted-by":"publisher","first-page":"1512","DOI":"10.1109\/TASLP.2018.2830105","volume":"26","author":"JJ Carabias-Orti","year":"2018","unstructured":"Carabias-Orti JJ, Nikunen J, Virtanen T, Vera-Candeas P (2018) Multichannel blind sound source separation using spatial covariance model with level and time differences and nonnegative matrix factorization. IEEE\/ACM Trans Audio Speech Lang Process 26(9):1512\u20131527. https:\/\/doi.org\/10.1109\/TASLP.2018.2830105","journal-title":"IEEE\/ACM Trans Audio Speech Lang Process"},{"key":"5945_CR16","doi-asserted-by":"publisher","unstructured":"Sekiguchi K, Nugraha AA, Bando Y, Yoshii K (2019) Fast multichannel source separation based on jointly diagonalizable spatial covariance matrices. In: 2019 27th European Signal Processing Conference (EUSIPCO), pp 1\u20135. https:\/\/doi.org\/10.23919\/EUSIPCO.2019.8902557","DOI":"10.23919\/EUSIPCO.2019.8902557"},{"key":"5945_CR17","doi-asserted-by":"crossref","unstructured":"Ito N, Nakatani T (2019) Fastmnmf: joint diagonalization based accelerated algorithms for multichannel nonnegative matrix factorization. In: ICASSP 2019-2019 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP), IEEE, pp 371\u2013375","DOI":"10.1109\/ICASSP.2019.8682291"},{"key":"5945_CR18","doi-asserted-by":"publisher","first-page":"49","DOI":"10.1109\/TASLP.2019.2948770","volume":"28","author":"Y Mitsufuji","year":"2020","unstructured":"Mitsufuji Y, Uhlich S, Takamune N, Kitamura D, Koyama S, Saruwatari H (2020) Multichannel non-negative matrix factorization using banded spatial covariance matrices in wavenumber domain. IEEE\/ACM Trans Audio Speech Lang Process 28:49\u201360. https:\/\/doi.org\/10.1109\/TASLP.2019.2948770","journal-title":"IEEE\/ACM Trans Audio Speech Lang Process"},{"key":"5945_CR19","doi-asserted-by":"publisher","first-page":"607","DOI":"10.1109\/TASLP.2020.3045528","volume":"29","author":"Y Mitsufuji","year":"2021","unstructured":"Mitsufuji Y, Takamune N, Koyama S, Saruwatari H (2021) Multichannel blind source separation based on evanescent-region-aware non-negative tensor factorization in spherical harmonic domain. IEEE\/ACM Trans Audio Speech Lang Process 29:607\u2013617. https:\/\/doi.org\/10.1109\/TASLP.2020.3045528","journal-title":"IEEE\/ACM Trans Audio Speech Lang Process"},{"key":"5945_CR20","doi-asserted-by":"publisher","first-page":"17781","DOI":"10.1109\/ACCESS.2022.3150248","volume":"10","author":"AJ Munoz-Montoro","year":"2022","unstructured":"Munoz-Montoro AJ, Carabias-Orti JJ, Cabanas-Molero P, Canadas-Quesada FJ, Ruiz-Reyes N (2022) Multichannel blind music source separation using directivity-aware MNMF with harmonicity constraints. IEEE Access 10:17781\u201317795. https:\/\/doi.org\/10.1109\/ACCESS.2022.3150248","journal-title":"IEEE Access"},{"key":"5945_CR21","doi-asserted-by":"publisher","unstructured":"Nikunen J, Politis A (2018) Multichannel NMF for source separation with ambisonic signals. In: 2018 16th International Workshop on Acoustic Signal Enhancement (IWAENC), pp 251\u2013255. https:\/\/doi.org\/10.1109\/IWAENC.2018.8521344","DOI":"10.1109\/IWAENC.2018.8521344"},{"key":"5945_CR22","doi-asserted-by":"crossref","unstructured":"Mu\u00f1oz-Montoro AJ, Carabias-Orti JJ, Vera-Candeas P (2021) Ambisonics domain singing voice separation combining deep neural network and direction aware multichannel NMF. In: 2021 IEEE 23rd International Workshop on Multimedia Signal Processing (MMSP), IEEE, pp 1\u20136","DOI":"10.1109\/MMSP53017.2021.9733494"},{"key":"5945_CR23","doi-asserted-by":"publisher","first-page":"619","DOI":"10.1007\/s11227-020-03282-2","volume":"77","author":"AJ Mu\u00f1oz-Montoro","year":"2020","unstructured":"Mu\u00f1oz-Montoro AJ, Suarez-Dou D, Carabias-Orti JJ, Canadas-Quesada FJ, Ranilla J (2020) Parallel multichannel music source separation system. J Supercomput 77:619\u2013637. https:\/\/doi.org\/10.1007\/s11227-020-03282-2","journal-title":"J Supercomput"},{"key":"5945_CR24","doi-asserted-by":"crossref","unstructured":"Liutkus A, St\u00f6ter F-R, Rafii Z, Kitamura D, Rivet B, Ito N, Ono N, Fontecave J (2017) The 2016 signal separation evaluation campaign. In: International Conference on Latent Variable Analysis and Signal Separation, Springer, pp 323\u2013332","DOI":"10.1007\/978-3-319-53547-0_31"},{"key":"5945_CR25","first-page":"48","volume":"9","author":"DR Campbell","year":"2005","unstructured":"Campbell DR, Palomaki KJ, Brown G (2005) A MATLAB simulation of \u201cshoebox\u2019\u2019 room acoustics for use in research and teaching. Comput Inf Syst 9:48\u201351","journal-title":"Comput Inf Syst"},{"issue":"4","key":"5945_CR26","doi-asserted-by":"publisher","first-page":"1462","DOI":"10.1109\/TSA.2005.858005","volume":"14","author":"E Vincent","year":"2006","unstructured":"Vincent E, Gribonval R, Fevotte C (2006) Performance measurement in blind audio source separation. IEEE Trans Audio Speech Lang Process 14(4):1462\u20131469. https:\/\/doi.org\/10.1109\/TSA.2005.858005","journal-title":"IEEE Trans Audio Speech Lang Process"},{"key":"5945_CR27","unstructured":"The MathWorks Inc. (2023) HDL Coder Toolbox (R2023a). https:\/\/www.mathworks.com"}],"container-title":["The Journal of Supercomputing"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/link.springer.com\/content\/pdf\/10.1007\/s11227-024-05945-w.pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/link.springer.com\/article\/10.1007\/s11227-024-05945-w\/fulltext.html","content-type":"text\/html","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/link.springer.com\/content\/pdf\/10.1007\/s11227-024-05945-w.pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2024,6,4]],"date-time":"2024-06-04T10:51:15Z","timestamp":1717498275000},"score":1,"resource":{"primary":{"URL":"https:\/\/link.springer.com\/10.1007\/s11227-024-05945-w"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2024,3,6]]},"references-count":27,"journal-issue":{"issue":"9","published-print":{"date-parts":[[2024,6]]}},"alternative-id":["5945"],"URL":"https:\/\/doi.org\/10.1007\/s11227-024-05945-w","relation":{},"ISSN":["0920-8542","1573-0484"],"issn-type":[{"value":"0920-8542","type":"print"},{"value":"1573-0484","type":"electronic"}],"subject":[],"published":{"date-parts":[[2024,3,6]]},"assertion":[{"value":"28 January 2024","order":1,"name":"accepted","label":"Accepted","group":{"name":"ArticleHistory","label":"Article History"}},{"value":"6 March 2024","order":2,"name":"first_online","label":"First Online","group":{"name":"ArticleHistory","label":"Article History"}},{"order":1,"name":"Ethics","group":{"name":"EthicsHeading","label":"Declarations"}},{"value":"The authors declare no conflicts of interest.","order":2,"name":"Ethics","group":{"name":"EthicsHeading","label":"Conflict of interest"}},{"value":"Not applicable.","order":3,"name":"Ethics","group":{"name":"EthicsHeading","label":"Ethical approval"}}]}}