{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2024,1,26]],"date-time":"2024-01-26T11:22:03Z","timestamp":1706268123854},"reference-count":35,"publisher":"Springer Science and Business Media LLC","issue":"1","license":[{"start":{"date-parts":[[2016,10,20]],"date-time":"2016-10-20T00:00:00Z","timestamp":1476921600000},"content-version":"unspecified","delay-in-days":0,"URL":"http:\/\/www.springer.com\/tdm"}],"content-domain":{"domain":["link.springer.com"],"crossmark-restriction":false},"short-container-title":["Int J Speech Technol"],"published-print":{"date-parts":[[2017,3]]},"DOI":"10.1007\/s10772-016-9381-1","type":"journal-article","created":{"date-parts":[[2016,10,20]],"date-time":"2016-10-20T07:17:09Z","timestamp":1476947829000},"page":"1-13","update-policy":"http:\/\/dx.doi.org\/10.1007\/springer_crossmark_policy","source":"Crossref","is-referenced-by-count":3,"title":["An unsupervised approach for co-channel speech separation using Hilbert\u2013Huang transform and Fuzzy C-Means clustering"],"prefix":"10.1007","volume":"20","author":[{"given":"M. K.","family":"Prasanna Kumar","sequence":"first","affiliation":[]},{"given":"R.","family":"Kumaraswamy","sequence":"additional","affiliation":[]}],"member":"297","published-online":{"date-parts":[[2016,10,20]]},"reference":[{"key":"9381_CR1","unstructured":"A simple correlation based model of intelligibility for nonlinear speech enhancement and separation (2009). Columbia University academic commons. http:\/\/hdl.handle.net\/10022\/AC:P:13660 ."},{"key":"9381_CR2","doi-asserted-by":"crossref","unstructured":"Bofill, P. (2008). Identifying single source data for mixing matrix estimation in instantaneous blind source separation. In Proceedings of the ICANN (pp. 759\u2013767).","DOI":"10.1007\/978-3-540-87536-9_78"},{"issue":"1","key":"9381_CR3","doi-asserted-by":"crossref","first-page":"92","DOI":"10.1109\/TSA.2004.838538","volume":"13","author":"S Douglas","year":"2005","unstructured":"Douglas, S., Sawada, H., & Makino, S. (2005). Natural gradient Multichannel blind deconvolution and speech separation using causal FIR filters. IEEE Transactions on Speech and Audio Processing, 13(1), 92\u2013104.","journal-title":"IEEE Transactions on Speech and Audio Processing"},{"key":"9381_CR4","volume-title":"Computational auditory scene analysis: Principles, Algorithms and Applications","author":"D Ellis","year":"2006","unstructured":"Ellis, D. (2006). Model based scene analysis. In D. L. Wang & G. J. Brown (Eds.), Computational auditory scene analysis: Principles, Algorithms and Applications. NewYork: Wiley."},{"issue":"6","key":"9381_CR5","doi-asserted-by":"crossref","first-page":"2174","DOI":"10.1109\/TSA.2005.858523","volume":"14","author":"C Fevotte","year":"2006","unstructured":"Fevotte, C., & Godsill, S. J. (2006). A Baysean approach for blind separation of sparse sources. IEEE Transactions on Audio, Speech and Language Processing, 14(6), 2174\u20132188.","journal-title":"IEEE Transactions on Audio, Speech and Language Processing"},{"issue":"4","key":"9381_CR6","doi-asserted-by":"crossref","first-page":"961","DOI":"10.1109\/TASL.2010.2072500","volume":"19","author":"B Gao","year":"2011","unstructured":"Gao, B., Woo, W., & Dlay, S. (2011). Single channel source separation using EMD subband variable regularized sparse features. IEEE Transactions on Audio, Speech and Language Processing, 19(4), 961\u2013976.","journal-title":"IEEE Transactions on Audio, Speech and Language Processing"},{"issue":"3","key":"9381_CR7","doi-asserted-by":"crossref","first-page":"662","DOI":"10.1109\/TCSI.2012.2215735","volume":"60","author":"B Gao","year":"2013","unstructured":"Gao, B., Woo, W., & Dlay, S. (2013). Unsupervised single channel separation of non stationary signals using Gammatone filterbank and Itakura-Satio non negative matrix two-dimensional factorizations. IEEE Transactions on Circuits and Systems, 60(3), 662\u2013675.","journal-title":"IEEE Transactions on Circuits and Systems"},{"key":"9381_CR8","doi-asserted-by":"crossref","unstructured":"Huang, N., Shen, Z., & Long, S. (1998). The empirical mode decomposition and Hilbert spectrum for nonlinear and non-stationary time analysis. In Proceedings of the Royal Society, London, pp 903\u2013995.","DOI":"10.1098\/rspa.1998.0193"},{"key":"9381_CR9","first-page":"1365","volume":"4","author":"GJ Jang","year":"2003","unstructured":"Jang, G. J., & Lee, T. W. (2003). A maximum likelihood approach to single channel source separation\u2019. Journal of Machine Learning Research, 4, 1365\u20131392.","journal-title":"Journal of Machine Learning Research"},{"key":"9381_CR10","volume-title":"Independent component analysis","author":"J Karhunen","year":"2001","unstructured":"Karhunen, J., & Oja, E. (2001). Independent component analysis. Hoboken: Wiley."},{"key":"9381_CR11","doi-asserted-by":"crossref","unstructured":"Kristjansson, T., Attias, H., Hershey, J. (2004, May). Single microphone source separation using high resolution signal reconstruction. In Proceedings of the international conference on acoustics, speech, and signal processing (pp 817\u2013820), Montreal.","DOI":"10.1109\/ICASSP.2004.1326383"},{"issue":"6","key":"9381_CR12","doi-asserted-by":"crossref","first-page":"1196","DOI":"10.1109\/TASL.2009.2016230","volume":"17","author":"R Kumaraswamy","year":"2009","unstructured":"Kumaraswamy, R., Yegnanarayana, B., & Sri Ramamurty, K. (2009). Determining mixing parameters from multispeaker data using speech specific information. IEEE Transactions on Audio Speech and Language Processing, 17(6), 1196\u20131207.","journal-title":"IEEE Transactions on Audio Speech and Language Processing"},{"issue":"2","key":"9381_CR13","first-page":"423","volume":"54","author":"Y Li","year":"2006","unstructured":"Li, Y., Amari, S., & Cichocki, A. (2006a). Under determined blind source separation based on sparse representation. IEEE Transactions on Audio, Speech and Language Processing, 54(2), 423\u2013437.","journal-title":"IEEE Transactions on Audio, Speech and Language Processing"},{"issue":"6","key":"9381_CR14","doi-asserted-by":"crossref","first-page":"2014","DOI":"10.1109\/TASL.2006.883258","volume":"14","author":"P Li","year":"2006","unstructured":"Li, P., Guan, Y., & Xu, B. (2006b). Monaural speech separation based on computational auditory scene analysis and objective quality assessment of speech. IEEE Transactions on Audio, Speech and Language Processing, 14(6), 2014\u20132023.","journal-title":"IEEE Transactions on Audio, Speech and Language Processing"},{"key":"9381_CR15","doi-asserted-by":"crossref","unstructured":"Litvin, Y., & Cohen, I. (2009). Single channel source separation of audio signals using bark scale wavelet packet decomposition. In IEEE international workshop on machine learning for signal processing.","DOI":"10.1109\/MLSP.2009.5306232"},{"issue":"9","key":"9381_CR16","doi-asserted-by":"crossref","first-page":"2188","DOI":"10.1109\/TBME.2010.2051440","volume":"57","author":"B Mijovic","year":"2010","unstructured":"Mijovic, B., & De Vos, M. (2010). Source separation from single channel recordings by combining empirical mode decomposition and independent component analysis. IEEE Transactions on Biomedical Engineering, 57(9), 2188\u20132196.","journal-title":"IEEE Transactions on Biomedical Engineering"},{"issue":"3","key":"9381_CR17","doi-asserted-by":"crossref","first-page":"893","DOI":"10.1109\/TASL.2006.885254","volume":"15","author":"M Molla","year":"2007","unstructured":"Molla, M., & Hirose, K. (2007). Single mixture audio source separation by subspace decomposition of Hilbert spectrum. IEEE Transactions on Audio, Speech and Language Processing, 15(3), 893\u2013900.","journal-title":"IEEE Transactions on Audio, Speech and Language Processing"},{"key":"9381_CR18","volume-title":"Hilbert\u2013Huang transform and its applications","author":"E Nordan","year":"2005","unstructured":"Nordan, E. (2005). Introduction to Hilbert\u2013Huang transform and its related mathematical problems. In E. Nordan (Ed.), Hilbert\u2013Huang transform and its applications. Singapore: World Scientific Publishing."},{"issue":"3","key":"9381_CR19","doi-asserted-by":"crossref","first-page":"550","DOI":"10.1109\/TASL.2009.2031510","volume":"18","author":"A Ozerov","year":"2010","unstructured":"Ozerov, A., & Fevotte, C. (2010). Multichannel non-negative matrix factorization in convolutive mixtures for audio source separation. IEEE Transactions on Audio, Speech and Language Processing, 18(3), 550\u2013563.","journal-title":"IEEE Transactions on Audio, Speech and Language Processing"},{"key":"9381_CR21","unstructured":"Reys, M., Ellis, D., Jojic, N. (2004). Multiband audio modeling for single channel acoustic source separation. In Proceedings of the international conference on acoustics, speech, and signal processing, Montreal, QC, May 2004, pp 641\u2013644."},{"key":"9381_CR20","unstructured":"Scientific American Online. (2011) Retrieved April, 2011, from http:\/\/www.scientificamerican.com\/article\/speech-getting-computers-understand-overlapping"},{"key":"9381_CR22","doi-asserted-by":"crossref","unstructured":"Schmidt, M., & Olsson, R. (2006). Single channel speech separation using sparse non negative matrix factorization. In Proceedings of the international conference on spoken language processing, Pittsburgh, PA, pp 2614\u20132617.","DOI":"10.21437\/Interspeech.2006-655"},{"key":"9381_CR23","unstructured":"Schobben, D., Torkkola, K., & Smaragdis, P. (1999, Jan). Evaluation of blind signal separation methods. In Proceedings of the ICA BSS, Aussois, France."},{"issue":"2","key":"9381_CR24","doi-asserted-by":"crossref","first-page":"242","DOI":"10.1109\/TASL.2010.2047419","volume":"19","author":"M Stark","year":"2011","unstructured":"Stark, M., Wohlmayr, M., & Pernkopf, F. (2011). Source-filter based single channel speech separation using pitch information. IEEE Transactions on Audio, Speech and Language Processing, 19(2), 242\u2013254.","journal-title":"IEEE Transactions on Audio, Speech and Language Processing"},{"key":"9381_CR25","doi-asserted-by":"crossref","unstructured":"Taal, C., Hendriks, R., Heusdens, R., & Jensen, J. (2010). A short-time objective intelligibility measure for time\u2013frequency weighted noisy speech. ICASSP 2010, Dallas, TX.","DOI":"10.1109\/ICASSP.2010.5495701"},{"issue":"7","key":"9381_CR26","doi-asserted-by":"crossref","first-page":"2125","DOI":"10.1109\/TASL.2011.2114881","volume":"19","author":"C Taal","year":"2011","unstructured":"Taal, C., Hendriks, R., Heusdens, R., & Jensen, J. (2011). An algorithm for intelligibility prediction of time\u2013frequency weighted noisy speech. IEEE Transactions on Audio, Speech and Language Processing, 19(7), 2125\u20132136.","journal-title":"IEEE Transactions on Audio, Speech and Language Processing"},{"issue":"11","key":"9381_CR27","doi-asserted-by":"crossref","first-page":"1722","DOI":"10.1109\/TNNLS.2013.2258680","volume":"24","author":"N Tengtrairat","year":"2013","unstructured":"Tengtrairat, N., Gao, B., & Woo, W. (2013). Single channel blind separation using pseudo stereo mixture and complex 2-D histogram. IEEE Transactions on Neural Networks and Learning Systems, 24(11), 1722\u20131735.","journal-title":"IEEE Transactions on Neural Networks and Learning Systems"},{"key":"9381_CR32","unstructured":"Tutorial on K-Means clustering. http:\/\/home.deib.polimi.it\/matteucc\/Clustering\/tutorial_html\/kmeans.html"},{"key":"9381_CR33","unstructured":"Tutorial on Fuzzy C-Means clustering. http:\/\/home.deib.polimi.it\/matteucc\/Clustering\/tutorial_html\/cmeans.html"},{"key":"9381_CR34","unstructured":"Tutorial on agglomerative clustering. http:\/\/home.deib.polimi.it\/matteucc\/Clustering\/tutorial_html\/hierarchical.html"},{"issue":"3","key":"9381_CR28","doi-asserted-by":"crossref","first-page":"107","DOI":"10.1109\/MSP.2013.2297440","volume":"31","author":"E Vincent","year":"2014","unstructured":"Vincent, E., & Bertin, N. (2014). From blind to guided audio source separation. IEEE Signal Processing Magazine, 31(3), 107\u2013115.","journal-title":"IEEE Signal Processing Magazine"},{"issue":"4","key":"9381_CR29","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., & Fevotte, C. (2006). Performance measurement in blind audio source separation. IEEE Transactions on Speech and Audio Processing, 14(4), 1462\u20131469.","journal-title":"IEEE Transactions on Speech and Audio Processing"},{"issue":"3","key":"9381_CR30","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 non negative 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":"15","key":"9381_CR31","doi-asserted-by":"crossref","first-page":"159","DOI":"10.1016\/j.physa.2014.01.020","volume":"400","author":"H Wang","year":"2014","unstructured":"Wang, H., Yeh, C., & Young, H. (2014). On the computational complexity of the empirical mode decomposition algorithm. Physica A: Statistical Mechanics and its Applications, 400(15), 159\u20131672014.","journal-title":"Physica A: Statistical Mechanics and its Applications"},{"issue":"7","key":"9381_CR35","doi-asserted-by":"crossref","first-page":"1830","DOI":"10.1109\/TSP.2004.828896","volume":"52","author":"O Yilmaz","year":"2004","unstructured":"Yilmaz, O., & Rickard, S. (2004). Blind separation of speech mixtures via timefrequency masking. IEEE Transactions on Signal Processing, 52(7), 1830\u20131847.","journal-title":"IEEE Transactions on Signal Processing"}],"container-title":["International Journal of Speech Technology"],"original-title":[],"language":"en","link":[{"URL":"http:\/\/link.springer.com\/content\/pdf\/10.1007\/s10772-016-9381-1.pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"text-mining"},{"URL":"http:\/\/link.springer.com\/article\/10.1007\/s10772-016-9381-1\/fulltext.html","content-type":"text\/html","content-version":"vor","intended-application":"text-mining"},{"URL":"http:\/\/link.springer.com\/content\/pdf\/10.1007\/s10772-016-9381-1.pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2022,7,10]],"date-time":"2022-07-10T20:21:43Z","timestamp":1657484503000},"score":1,"resource":{"primary":{"URL":"http:\/\/link.springer.com\/10.1007\/s10772-016-9381-1"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2016,10,20]]},"references-count":35,"journal-issue":{"issue":"1","published-print":{"date-parts":[[2017,3]]}},"alternative-id":["9381"],"URL":"https:\/\/doi.org\/10.1007\/s10772-016-9381-1","relation":{},"ISSN":["1381-2416","1572-8110"],"issn-type":[{"value":"1381-2416","type":"print"},{"value":"1572-8110","type":"electronic"}],"subject":[],"published":{"date-parts":[[2016,10,20]]}}}