{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,1,27]],"date-time":"2026-01-27T14:46:17Z","timestamp":1769525177631,"version":"3.49.0"},"reference-count":34,"publisher":"Springer Science and Business Media LLC","issue":"1","license":[{"start":{"date-parts":[[2016,11,29]],"date-time":"2016-11-29T00:00:00Z","timestamp":1480377600000},"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\/s10772-016-9392-y","type":"journal-article","created":{"date-parts":[[2016,11,29]],"date-time":"2016-11-29T11:01:16Z","timestamp":1480417276000},"page":"109-125","update-policy":"https:\/\/doi.org\/10.1007\/springer_crossmark_policy","source":"Crossref","is-referenced-by-count":9,"title":["Single-channel speech separation using empirical mode decomposition and multi pitch information with estimation of number of speakers"],"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":[[2016,11,29]]},"reference":[{"key":"9392_CR1","first-page":"759","volume":"5163","author":"P Bofill","year":"2008","unstructured":"Bofill, P. (2008). Identifying single source data for mixing matrix estimation in instantaneous blind source separation. Proceedings of the ICANN, 5163, 759\u2013767.","journal-title":"Proceedings of the ICANN"},{"key":"9392_CR2","unstructured":"Boldt, J. B., & Ellis, D. P. W. (2009) A simple correlation based model of intelligibility for nonlinear speech enhancement and separation. Columbia university academic commons, http:\/\/hdl.handle.net\/10022\/AC:P:13660 ."},{"key":"9392_CR3","unstructured":"Digital Speech Processing Course (2015). Time domain methods in speech processing. http:\/\/www.ece.ucsb.edu\/Faculty\/Rabiner\/ece259\/speech20course.html ."},{"issue":"1","key":"9392_CR4","doi-asserted-by":"crossref","first-page":"92","DOI":"10.1109\/TSA.2004.838538","volume":"13","author":"SC Douglas","year":"2005","unstructured":"Douglas, S. C., Sawada, H., & Makino, S. (2005). Natural gradient Multichannel blind deconvolution and speech separation using causal FIR filters. IEEE Transactions on Speech Audio Processing, 13(1), 92\u2013104.","journal-title":"IEEE Transactions on Speech Audio Processing"},{"key":"9392_CR5","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. Wang & G. Brown (Eds.), Computational auditory scene analysis: Principles, algorithms and applications. New York: Wiley."},{"issue":"6","key":"9392_CR6","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":"9392_CR7","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. L., & Dlay, S. S. (2011). Single channel source separation using EMD sub band 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":"9392_CR8","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. L., & Dlay, S. S. (2013). Unsupervised single Channel separation of non stationary signals using Gammatone filter bank and Itakura-Satio nonnegative matrix two-dimensional factorizations. IEEE Transactions on Circuits and Systems, 60(3), 662\u2013675.","journal-title":"IEEE Transactions on Circuits and Systems"},{"key":"9392_CR13","unstructured":"Greenwood M., & Kinghorn, A. (1999). SUVing: Automatic Silence\/Unvoiced\/Voiced Classification of Speech. Undergraduate Coursework, Department of Computer Science, The University of Sheffield, http:\/\/www.dcs.shef.ac.uk\/mark\/uni\/ ."},{"key":"9392_CR9","unstructured":"Hershey, J.R., Olsen, P.A., Rennie, S. J., & Aron, A. (2011). Audio Alchemy: Getting computers to understand overlapping speech. Scientific American Online, http:\/\/www.scientificamerican.com\/article\/speech-gettingcomputersunderstand-overlapping ."},{"key":"9392_CR10","doi-asserted-by":"crossref","first-page":"903","DOI":"10.1098\/rspa.1998.0193","volume":"454","author":"NE Huang","year":"1998","unstructured":"Huang, N. E., Shen, Z., & Long, S. R. (1998). The empirical mode decomposition and Hilbert spectrum for nonlinear and non-stationary time series analysis. Proceedings of Royal Society of London, 454, 903\u2013995.","journal-title":"Proceedings of Royal Society of London"},{"key":"9392_CR11","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. Journal of Machine Learning Research, 4, 1365\u20131392.","journal-title":"Journal of Machine Learning Research"},{"key":"9392_CR12","volume-title":"Independent component analysis","author":"J Karhunen","year":"2001","unstructured":"Karhunen, J., & Oja, E. (2001). Independent component analysis. New York: John Wiley Sons."},{"key":"9392_CR14","doi-asserted-by":"crossref","unstructured":"Kristjansson, T., Attias, H., & Hershey, J. (2004) Single microphone source separation using high resolution signal reconstruction. In Proceedings of International Conference on Acoustics, Speech, Signal Processing, (ICASSP\u201904, (Vol. 2, pp. 817\u2013820). Montreal, QC.","DOI":"10.1109\/ICASSP.2004.1326383"},{"issue":"6","key":"9392_CR15","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 multi speaker 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":"9392_CR16","first-page":"423","volume":"54","author":"Y Li","year":"2006","unstructured":"Li, Y., Amari, S., & Cichocki, A. (2006a). Underdetermined 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":"9392_CR17","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":"9392_CR18","unstructured":"Linear Prediction Analysis (2015) http:\/\/iitg.vlab.co.in\/?sub=59&brch=164&sim=616&cnt=1108 ."},{"issue":"3","key":"9392_CR19","first-page":"339","volume":"65","author":"Y Litvin","year":"2009","unstructured":"Litvin, Y., & Cohen, I. (2009). Single channel source separation of audio signals using Bark Scale Wavlet Packet Decomposition. IEEE International Workshop on Machine Learning for Signal Processing, 65(3), 339\u20139350.","journal-title":"IEEE International Workshop on Machine Learning for Signal Processing"},{"issue":"9","key":"9392_CR20","doi-asserted-by":"crossref","first-page":"2188","DOI":"10.1109\/TBME.2010.2051440","volume":"57","author":"Bogdan Mijovic","year":"2010","unstructured":"Mijovic, Bogdan, & De Vos, Maarten. (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":"9392_CR21","doi-asserted-by":"crossref","first-page":"893","DOI":"10.1109\/TASL.2006.885254","volume":"15","author":"MK Molla","year":"2007","unstructured":"Molla, M. K., & 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"},{"issue":"3","key":"9392_CR22","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":"9392_CR23","doi-asserted-by":"crossref","first-page":"623","DOI":"10.1007\/978-3-642-19551-8_23","volume":"346","author":"C Philipos","year":"2011","unstructured":"Philipos, C. (2011). Loizou. Speech Quality Assessment, Multimedia Analysis, Processing & Communications, 346, 623\u2013654.","journal-title":"Speech Quality Assessment, Multimedia Analysis, Processing & Communications"},{"key":"9392_CR24","doi-asserted-by":"crossref","unstructured":"Reys, M. J., Ellis, D., & Jojic, N. (2004). Multiband audio modelling for single channel acoustic source separation. In Proceedings of International Conference on Acoustics, Speech, Signal Processing (ICASSP\u201904) (Vol. 5, pp. 641\u2013644). Montreal, QC.","DOI":"10.1109\/ICASSP.2004.1327192"},{"key":"9392_CR26","unstructured":"Schmidt, M. N., & Olsson, R. K. (2006). Single channel speech separation using sparse non negative matrix factorization\u201d, In Proceedings of International Conference on Spoken Language Processing (INTERSPEECH), (pp. 2614\u20132617). Pittsburgh, PA."},{"key":"9392_CR27","unstructured":"Schobben, D., Torkkola, K., & Smaragdis, P. (1999). Evaluation of blind signal separation methods. In Proceedings of ICA BSS, Aussois."},{"issue":"2","key":"9392_CR28","doi-asserted-by":"crossref","first-page":"242","DOI":"10.1109\/TASL.2010.2047419","volume":"19","author":"Michael Stark","year":"2011","unstructured":"Stark, Michael, Wohlmayr, Michael, & Pernkopf, Franz. (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"},{"issue":"11","key":"9392_CR29","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. L. (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"},{"issue":"3","key":"9392_CR30","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":"9392_CR31","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":"9392_CR32","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":"9392_CR33","doi-asserted-by":"crossref","first-page":"159","DOI":"10.1016\/j.physa.2014.01.020","volume":"400","author":"YH Wang","year":"2014","unstructured":"Wang, Y. H., Yeh, C. H., & Young, H. W. (2014). On the Computational complexity of the empirical mode decomposition algorithm. Physica A: Statistical Mechanics and its Applications, 400(15), 159\u2013167.","journal-title":"Physica A: Statistical Mechanics and its Applications"},{"key":"9392_CR34","unstructured":"Wu, K-H., & Chen, C-P., & Yeh, B-F. (2011). Noise-robust speech feature processing with empirical mode decomposition. EURASIP journal on audio, speech and music processing, http:\/\/asmp.eurasipjournals.com\/content\/2011\/1\/9 ."},{"issue":"7","key":"9392_CR37","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 time-frequency 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\/s10772-016-9392-y.pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"text-mining"},{"URL":"http:\/\/link.springer.com\/article\/10.1007\/s10772-016-9392-y\/fulltext.html","content-type":"text\/html","content-version":"vor","intended-application":"text-mining"},{"URL":"http:\/\/link.springer.com\/content\/pdf\/10.1007\/s10772-016-9392-y.pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2017,6,25]],"date-time":"2017-06-25T00:45:21Z","timestamp":1498351521000},"score":1,"resource":{"primary":{"URL":"http:\/\/link.springer.com\/10.1007\/s10772-016-9392-y"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2016,11,29]]},"references-count":34,"journal-issue":{"issue":"1","published-print":{"date-parts":[[2017,3]]}},"alternative-id":["9392"],"URL":"https:\/\/doi.org\/10.1007\/s10772-016-9392-y","relation":{},"ISSN":["1381-2416","1572-8110"],"issn-type":[{"value":"1381-2416","type":"print"},{"value":"1572-8110","type":"electronic"}],"subject":[],"published":{"date-parts":[[2016,11,29]]}}}