{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2025,6,26]],"date-time":"2025-06-26T09:30:29Z","timestamp":1750930229282},"reference-count":38,"publisher":"Springer Science and Business Media LLC","issue":"3","license":[{"start":{"date-parts":[[2012,4,27]],"date-time":"2012-04-27T00:00:00Z","timestamp":1335484800000},"content-version":"tdm","delay-in-days":0,"URL":"http:\/\/www.springer.com\/tdm"}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":["J Sign Process Syst"],"published-print":{"date-parts":[[2012,12]]},"DOI":"10.1007\/s11265-012-0673-7","type":"journal-article","created":{"date-parts":[[2012,4,26]],"date-time":"2012-04-26T01:20:59Z","timestamp":1335403259000},"page":"267-277","source":"Crossref","is-referenced-by-count":21,"title":["Optimization and Parallelization of Monaural Source Separation Algorithms in the openBliSSART Toolkit"],"prefix":"10.1007","volume":"69","author":[{"given":"Felix","family":"Weninger","sequence":"first","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Bj\u00f6rn","family":"Schuller","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"297","published-online":{"date-parts":[[2012,4,27]]},"reference":[{"key":"673_CR1","unstructured":"Battenberg, E., & Wessel, D. (2009). Accelerating non-negative matrix factorization for audio source separation on multi-core and many-core architectures. In Proc. of 10th International Society for Music Information Retrieval conference (ISMIR) (pp.\u00a0501\u2013506). Kobe, Japan."},{"key":"673_CR2","doi-asserted-by":"crossref","unstructured":"Cichocki, A., Zdunek, R., Phan, A.\u00a0H., & Amari, S.\u00a0I. (2009). Nonnegative matrix and tensor factorizations. Wiley.","DOI":"10.1002\/9780470747278"},{"key":"673_CR3","doi-asserted-by":"crossref","first-page":"1","DOI":"10.1016\/j.csl.2009.02.006","volume":"24","author":"M Cooke","year":"2010","unstructured":"Cooke, M., Hershey, J.\u00a0R., & Rennie, S.\u00a0J. (2010). Monaural speech separation and recognition challenge. Computer Speech and Language, 24, 1\u201315.","journal-title":"Computer Speech and Language"},{"issue":"3","key":"673_CR4","doi-asserted-by":"crossref","first-page":"564","DOI":"10.1109\/TASL.2010.2041114","volume":"18","author":"JL Durrieu","year":"2010","unstructured":"Durrieu, J.\u00a0L., Richard, G., David, B., & F\u00e9votte, C. (2010). Source\/filter model for unsupervised main melody extraction from polyphonic audio signals. IEEE Transactions on Audio, Speech, and Language Processing, 18(3), 564\u2013575.","journal-title":"IEEE Transactions on Audio, Speech, and Language Processing"},{"issue":"3","key":"673_CR5","doi-asserted-by":"crossref","first-page":"793","DOI":"10.1162\/neco.2008.04-08-771","volume":"21","author":"C F\u00e9votte","year":"2009","unstructured":"F\u00e9votte, C., Bertin, N., & Durrieu, J.\u00a0L. (2009). Nonnegative matrix factorization with the Itakura\u2013Saito divergence: With application to music analysis. Neural Computation, 21(3), 793\u2013830.","journal-title":"Neural Computation"},{"issue":"2","key":"673_CR6","doi-asserted-by":"crossref","first-page":"216","DOI":"10.1109\/JPROC.2004.840301","volume":"93","author":"M Frigo","year":"2005","unstructured":"Frigo, M., & Johnson, S.\u00a0G. (2005). The design and implementation of FFTW3. Proceedings of the IEEE, 93(2), 216\u2013231.","journal-title":"Proceedings of the IEEE"},{"issue":"7","key":"673_CR7","doi-asserted-by":"crossref","first-page":"2067","DOI":"10.1109\/TASL.2011.2112350","volume":"19","author":"J Gemmeke","year":"2011","unstructured":"Gemmeke, J., Virtanen, T., & Hurmalainen, A. (2011). Exemplar-based sparse representations for noise robust automatic speech recognition. IEEE Transactions on Audio, Speech, and Language Processing, 19(7), 2067\u20132080.","journal-title":"IEEE Transactions on Audio, Speech, and Language Processing"},{"key":"673_CR8","unstructured":"Gemmeke, J.\u00a0F., Hurmalainen, A., Virtanen, T., & Sun, Y. (2011). Toward a practical implementation of exemplar-based noise robust ASR. In Proc. of EUSIPCO (pp.\u00a01490\u20131494)."},{"key":"673_CR9","doi-asserted-by":"crossref","first-page":"10","DOI":"10.1145\/1656274.1656278","volume":"11","author":"M Hall","year":"2009","unstructured":"Hall, M., Frank, E., Holmes, G., Pfahringer, B., Reutemann, P., & Witten, I.\u00a0H. (2009). The WEKA data mining software: An update. ACM SIGKDD Explorations Newsletter, 11, 10\u201318.","journal-title":"ACM SIGKDD Explorations Newsletter"},{"key":"673_CR10","unstructured":"Heittola, T., Mesaros, A., Virtanen, T., & Eronen, A. (2011). Sound event detection in multisource environments using source separation. In Proc. of CHiME workshop (pp.\u00a086\u201390). Florence, Italy."},{"key":"673_CR11","unstructured":"Helen, M., & Virtanen, T. (2005). Separation of drums from polyphonic music using non-negative matrix factorization and support vector machine. In Proc. of EUSIPCO. Antalya, Turkey."},{"key":"673_CR12","doi-asserted-by":"crossref","unstructured":"Hurmalainen, A., Gemmeke, J., & Virtanen, T. (2011). Non-negative matrix deconvolution in noise robust speech recognition. In Proc. of ICASSP (pp.\u00a04588\u20134591). Prague, Czech Republic.","DOI":"10.1109\/ICASSP.2011.5947376"},{"key":"673_CR13","doi-asserted-by":"crossref","DOI":"10.1002\/0471221317","volume-title":"Independent component analysis","author":"A Hyv\u00e4rinen","year":"2001","unstructured":"Hyv\u00e4rinen, A., Karhunen, J., & Oja, E. (2001). Independent component analysis. New York: Wiley."},{"key":"673_CR14","unstructured":"Lee, D.\u00a0D., & Seung, H.\u00a0S. (2001). Algorithms for non-negative matrix factorization. In Proc. of NIPS (pp.\u00a0556\u2013562). Vancouver, Canada."},{"key":"673_CR15","unstructured":"Mesaros, A., & Virtanen, T. (2009). Automatic recognition of lyrics in singing. EURASIP Journal on Audio, Speech, and Music Processing, Article ID 546047."},{"key":"673_CR16","unstructured":"O\u2019Grady, P.\u00a0D., & Pearlmutter, B.\u00a0A. (2007). Discovering convolutive speech phones using sparseness and non-negativity constraints. In Proc. of ICA. London, UK."},{"key":"673_CR17","doi-asserted-by":"crossref","unstructured":"Ozerov, A., F\u00e9votte, C., & Charbit, M. (2009). Factorial scaled hidden Markov model for polyphonic audio representation and source separation. In Proc. of WASPAA (pp.\u00a0121\u2013124). Mohonk, NY, United States.","DOI":"10.1109\/ASPAA.2009.5346527"},{"key":"673_CR18","unstructured":"Ozerov, A., & Vincent, E. (2011). Using the FASST source separation toolbox for noise robust speech recognition. In Proc. of CHiME workshop (pp.\u00a086\u201387). Florence, Italy."},{"key":"673_CR19","doi-asserted-by":"crossref","unstructured":"Raj, B., Virtanen, T., Chaudhuri, S., & Singh, R. (2010). Non-negative matrix factorization based compensation of music for automatic speech recognition. In Proc. of Interspeech. Makuhari, Japan.","DOI":"10.21437\/Interspeech.2010-268"},{"key":"673_CR20","doi-asserted-by":"crossref","unstructured":"Schmidt, M.\u00a0N., & Olsson, R.\u00a0K. (2006). Single-channel speech separation using sparse non-negative matrix factorization. In Proc. of Interspeech. Pittsburgh, PA, USA.","DOI":"10.21437\/Interspeech.2006-655"},{"key":"673_CR21","first-page":"361","volume-title":"Proc. of the international conference on acoustics (NAG\/DAGA 2009)","author":"G Rigoll","year":"2009","unstructured":"Schuller, B., Lehmann, A., Weninger, F., Eyben, F., & Rigoll, G. (2009). Blind enhancement of the rhythmic and harmonic sections by NMF: Does it help? In Proc. of the international conference on acoustics (NAG\/DAGA 2009) (pp.\u00a0361\u2013364). DEGA, Rotterdam, Netherlands."},{"key":"673_CR22","doi-asserted-by":"crossref","unstructured":"Schuller, B., & Weninger, F. (2010). Discrimination of speech and non-linguistic vocalizations by non-negative matrix factorization. In Proc. of ICASSP (pp.\u00a05054\u20135057). Dallas, TX, USA.","DOI":"10.1109\/ICASSP.2010.5495061"},{"key":"673_CR23","doi-asserted-by":"crossref","unstructured":"Schuller, B., Weninger, F., W\u00f6llmer, M., Sun, Y., & Rigoll, G. (2010). Non-negative matrix factorization as noise-robust feature extractor for speech recognition. In Proc. of ICASSP (pp.\u00a04562\u20134565). Dallas, TX, USA.","DOI":"10.1109\/ICASSP.2010.5495567"},{"issue":"1","key":"673_CR24","doi-asserted-by":"crossref","first-page":"1","DOI":"10.1109\/TASL.2006.876726","volume":"15","author":"P Smaragdis","year":"2007","unstructured":"Smaragdis, P. (2007). Convolutive speech bases and their application to supervised speech separation. IEEE Transactions on Audio, Speech and Language Processing, 15(1), 1\u201314.","journal-title":"IEEE Transactions on Audio, Speech and Language Processing"},{"key":"673_CR25","doi-asserted-by":"crossref","unstructured":"Smaragdis, P., & Brown, J.\u00a0C. (2003). Non-negative matrix factorization for polyphonic music transcription. In Proc. of IEEE workshop on applications of signal processing to audio and acoustics (pp.\u00a0177\u2013180). New Paltz, NY, USA.","DOI":"10.1109\/ASPAA.2003.1285860"},{"key":"673_CR26","first-page":"414","volume-title":"Proc. of ICA","author":"P Smaragdis","year":"2007","unstructured":"Smaragdis, P., Raj, B., & Shashanka, M. (2007). Supervised and semi-supervised separation of sounds from single-channel mixtures. In Proc. of ICA (pp.\u00a0414\u2013421). Berlin: Springer."},{"key":"673_CR27","unstructured":"Uhle, C., Dittmar, C., & Sporer, T. (2003). Extraction of drum tracks from polyphonic music using independent subspace analysis. In Proc. of ICA. Nara, Japan."},{"issue":"4","key":"673_CR28","doi-asserted-by":"crossref","first-page":"1462","DOI":"10.1109\/TSA.2005.858005","volume":"14","author":"E Vincent","year":"2006","unstructured":"Vincent, E., Gribonval, R., & F\u00e9votte, C. (2006). Performance measurement in blind audio source separation. IEEE Transactions on Audio, Speech and Language Processing, 14(4), 1462\u20131469.","journal-title":"IEEE Transactions on Audio, Speech and Language Processing"},{"issue":"3","key":"673_CR29","doi-asserted-by":"crossref","first-page":"1066","DOI":"10.1109\/TASL.2006.885253","volume":"15","author":"T Virtanen","year":"2007","unstructured":"Virtanen, T. (2007). Monaural sound source separation by nonnegative matrix factorization with temporal continuity and sparseness criteria. IEEE Transactions on Audio, Speech and Language Processing, 15(3), 1066\u20131074.","journal-title":"IEEE Transactions on Audio, Speech and Language Processing"},{"issue":"7","key":"673_CR30","doi-asserted-by":"crossref","first-page":"2858","DOI":"10.1109\/TSP.2009.2016881","volume":"57","author":"W Wang","year":"2009","unstructured":"Wang, W., Cichocki, A., & Chambers, J.\u00a0A. (2009). A multiplicative algorithm for convolutive non-negative matrix factorization based on squared Euclidean distance. IEEE Transactions on Signal Processing, 57(7), 2858\u20132864.","journal-title":"IEEE Transactions on Signal Processing"},{"key":"673_CR31","unstructured":"Weninger, F., Geiger, J., W\u00f6llmer, M., Schuller, B., & Rigoll, G. (2011). The Munich 2011 CHiME challenge contribution: NMF-BLSTM speech enhancement and recognition for reverberated multisource environments. In Proc. of CHiME workshop (pp.\u00a024\u201329). Florence, Italy."},{"key":"673_CR32","doi-asserted-by":"crossref","unstructured":"Weninger, F., Lehmann, A., & Schuller, B. (2011). openBliSSART: Design and evaluation of a research toolkit for blind source separation in audio recognition tasks. In Proc. of ICASSP (pp.\u00a01625\u20131628). Prague, Czech Republic.","DOI":"10.1109\/ICASSP.2011.5946809"},{"key":"673_CR33","doi-asserted-by":"crossref","unstructured":"Weninger, F., Schuller, B., Batliner, A., Steidl, S., & Seppi, D. (2011). Recognition of nonprototypical emotions in reverberated and noisy speech by nonnegative matrix factorization. EURASIP Journal on Advances in Signal Processing, Special Issue on Emotion and Mental State Recognition from Speech, Article ID 838790, 16 pp.","DOI":"10.1155\/2011\/838790"},{"key":"673_CR34","doi-asserted-by":"crossref","unstructured":"Weninger, F., Schuller, B., W\u00f6llmer, M., & Rigoll, G. (2011). Localization of non-linguistic events in spontaneous speech by non-negative matrix factorization and long short-term memory. In Proc. of ICASSP (pp.\u00a05840\u20135843). Prague, Czech Republic.","DOI":"10.1109\/ICASSP.2011.5947689"},{"issue":"1\u20132","key":"673_CR35","doi-asserted-by":"crossref","first-page":"3","DOI":"10.1016\/S0167-8191(00)00087-9","volume":"27","author":"RC Whaley","year":"2001","unstructured":"Whaley, R.\u00a0C., Petitet, A., & Dongarra, J. (2001). Automated empirical optimization of software and the ATLAS project. Parallel Computing, 27(1\u20132), 3\u201335.","journal-title":"Parallel Computing"},{"key":"673_CR36","doi-asserted-by":"crossref","unstructured":"Wilson, K.\u00a0W., Raj, B., & Smaragdis, P. (2008). Regularized non-negative matrix factorization with temporal dependencies for speech denoising. In Proc. of Interspeech. Brisbane, Australia.","DOI":"10.21437\/Interspeech.2008-49"},{"key":"673_CR37","doi-asserted-by":"crossref","first-page":"1230","DOI":"10.1021\/ct8001046","volume":"4","author":"K Yasuda","year":"2008","unstructured":"Yasuda, K. (2008). Accelerating density functional calculations with graphics processing unit. Journal of Chemical Theory and Computation, 4, 1230\u20131236.","journal-title":"Journal of Chemical Theory and Computation"},{"key":"673_CR38","volume-title":"The HTK book version 3.4","author":"SJ Young","year":"2006","unstructured":"Young, S.\u00a0J., Evermann, G., Gales, M.\u00a0J.\u00a0F., Kershaw, D., Moore, G., Odell, J.\u00a0J., et al. (2006). The HTK book version 3.4. Cambridge University Engineering Department, Cambridge, UK."}],"container-title":["Journal of Signal Processing Systems"],"original-title":[],"language":"en","link":[{"URL":"http:\/\/link.springer.com\/content\/pdf\/10.1007\/s11265-012-0673-7.pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"text-mining"},{"URL":"http:\/\/link.springer.com\/article\/10.1007\/s11265-012-0673-7\/fulltext.html","content-type":"text\/html","content-version":"vor","intended-application":"text-mining"},{"URL":"http:\/\/link.springer.com\/content\/pdf\/10.1007\/s11265-012-0673-7","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2022,1,14]],"date-time":"2022-01-14T05:29:58Z","timestamp":1642138198000},"score":1,"resource":{"primary":{"URL":"http:\/\/link.springer.com\/10.1007\/s11265-012-0673-7"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2012,4,27]]},"references-count":38,"journal-issue":{"issue":"3","published-print":{"date-parts":[[2012,12]]}},"alternative-id":["673"],"URL":"https:\/\/doi.org\/10.1007\/s11265-012-0673-7","relation":{},"ISSN":["1939-8018","1939-8115"],"issn-type":[{"value":"1939-8018","type":"print"},{"value":"1939-8115","type":"electronic"}],"subject":[],"published":{"date-parts":[[2012,4,27]]}}}