{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2025,6,29]],"date-time":"2025-06-29T00:10:01Z","timestamp":1751155801822,"version":"3.41.0"},"reference-count":29,"publisher":"Springer Science and Business Media LLC","issue":"8","license":[{"start":{"date-parts":[[2017,12,18]],"date-time":"2017-12-18T00:00:00Z","timestamp":1513555200000},"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":["Circuits Syst Signal Process"],"published-print":{"date-parts":[[2018,8]]},"DOI":"10.1007\/s00034-017-0728-x","type":"journal-article","created":{"date-parts":[[2017,12,18]],"date-time":"2017-12-18T19:52:00Z","timestamp":1513626720000},"page":"3651-3670","update-policy":"https:\/\/doi.org\/10.1007\/springer_crossmark_policy","source":"Crossref","is-referenced-by-count":20,"title":["Image Processing Techniques for Segments Grouping in Monaural Speech Separation"],"prefix":"10.1007","volume":"37","author":[{"given":"S.","family":"Shoba","sequence":"first","affiliation":[]},{"given":"R.","family":"Rajavel","sequence":"additional","affiliation":[]}],"member":"297","published-online":{"date-parts":[[2017,12,18]]},"reference":[{"key":"728_CR1","doi-asserted-by":"publisher","DOI":"10.1109\/ACCESS.2017.2728801","author":"AKH Al-Ali","year":"2017","unstructured":"A.K.H. Al-Ali, D. David, S. Bouchra, C. Vinod, G.R. Naik, Enhanced forensic speaker verification using a combination of DWT and MFCC feature warping in the presence of noise and reverberation conditions. IEEE Access (2017). https:\/\/doi.org\/10.1109\/ACCESS.2017.2728801","journal-title":"IEEE Access"},{"issue":"5","key":"728_CR2","doi-asserted-by":"crossref","first-page":"679","DOI":"10.1111\/ejn.13524","volume":"45","author":"A Bednar","year":"2017","unstructured":"A. Bednar, M.B. Francis, C.L. Edmund, Different spatio-temporal electroencephalography features drive the successful decoding of binaural and monaural cues for sound localization. Eur. J. Neurosci. 45(5), 679\u2013689 (2017)","journal-title":"Eur. J. Neurosci."},{"key":"728_CR3","doi-asserted-by":"crossref","first-page":"113","DOI":"10.1109\/TASSP.1979.1163209","volume":"27","author":"SF Boll","year":"1979","unstructured":"S.F. Boll, Suppression of acoustic noise in speech using spectral subtraction. IEEE Trans. Acoust. Speech Signal Process. 27, 113\u2013120 (1979)","journal-title":"IEEE Trans. Acoust. Speech Signal Process."},{"issue":"4","key":"728_CR4","doi-asserted-by":"crossref","first-page":"297","DOI":"10.1006\/csla.1994.1016","volume":"8","author":"GJ Brown","year":"1994","unstructured":"G.J. Brown, M.P. Cooke, Computational auditory scene analysis. Comput. Speech Lang. 8(4), 297\u2013336 (1994)","journal-title":"Comput. Speech Lang."},{"key":"728_CR5","doi-asserted-by":"crossref","first-page":"371","DOI":"10.1007\/3-540-27489-8_16","volume-title":"Speech Enhancement","author":"GJ Brown","year":"2005","unstructured":"G.J. Brown, D.L. Wang, Separation of speech by computational auditory scene analysis, in Speech Enhancement, ed. by J. Benesty, S. Makino, J. Chen (Springer, New York, 2005), pp. 371\u2013402"},{"key":"728_CR6","doi-asserted-by":"crossref","unstructured":"M. Dharmalingam, M.C. JohnWiselin, R. Rajavel, Optimizing the objective measure of speech quality in monaural speech separation, in Proceedings of 3rd International Conference on Advanced Computing, Networking and Informatics, pp. 545\u2013552 (2016)","DOI":"10.1007\/978-81-322-2538-6_56"},{"issue":"4","key":"728_CR7","doi-asserted-by":"crossref","first-page":"251","DOI":"10.1109\/89.397090","volume":"3","author":"Y Ephraim","year":"1995","unstructured":"Y. Ephraim, H.L. Trees, A signal subspace approach for speech enhancement. IEEE Trans. Speech Audio Process. 3(4), 251\u2013266 (1995)","journal-title":"IEEE Trans. Speech Audio Process."},{"key":"728_CR8","doi-asserted-by":"crossref","unstructured":"N. Harish, R. Rajavel, Monaural speech separation system based on optimum soft mask, in Proceedings of IEEE International Conference on Computational Intelligence and Computing Research, Coimbatore, India, pp. 1\u20135 (2014)","DOI":"10.1109\/ICCIC.2014.7238420"},{"issue":"5","key":"728_CR9","doi-asserted-by":"crossref","first-page":"1135","DOI":"10.1109\/TNN.2004.832812","volume":"15","author":"G Hu","year":"2004","unstructured":"G. Hu, D. Wang, Monaural speech segregation based on pitch tracking and amplitude modulation. IEEE Trans. Neural Netw. 15(5), 1135\u20131150 (2004)","journal-title":"IEEE Trans. Neural Netw."},{"key":"728_CR10","first-page":"485","volume-title":"Topics in Acoustic Echo and Noise Control","author":"G Hu","year":"2006","unstructured":"G. Hu, D. Wang, An auditory scene analysis approach to monaural speech segregation, in Topics in Acoustic Echo and Noise Control, ed. by E. Hansler, G. Schmidt (Springer, New York, 2006), pp. 485\u2013515"},{"issue":"2","key":"728_CR11","doi-asserted-by":"crossref","first-page":"396","DOI":"10.1109\/TASL.2006.881700","volume":"15","author":"G Hu","year":"2007","unstructured":"G. Hu, D. Wang, Auditory segmentation based on onset and offset analysis. IEEE Trans. Audio Speech Lang. Process. 15(2), 396\u2013405 (2007)","journal-title":"IEEE Trans. Audio Speech Lang. Process."},{"issue":"6","key":"728_CR12","doi-asserted-by":"crossref","first-page":"1600","DOI":"10.1109\/TASL.2010.2093893","volume":"19","author":"K Hu","year":"2011","unstructured":"K. Hu, D. Wang, Unvoiced speech segregation from non-speech interference via CASA and spectral subtraction. IEEE Trans. Audio Speech Lang. Process. 19(6), 1600\u20131609 (2011)","journal-title":"IEEE Trans. Audio Speech Lang. Process."},{"key":"728_CR13","doi-asserted-by":"crossref","DOI":"10.1002\/0471221317","volume-title":"Independent Component Analysis","author":"A Hyvarinen","year":"2001","unstructured":"A. Hyvarinen, J. Karhunen, E. Oja, Independent Component Analysis (Wiley, New York, 2001)"},{"issue":"7","key":"728_CR14","doi-asserted-by":"crossref","first-page":"731","DOI":"10.1109\/89.952491","volume":"9","author":"J Jensen","year":"2001","unstructured":"J. Jensen, J.H.L. Hansen, Speech enhancement using a constrained iterative sinusoidal model. IEEE Trans. Speech Audio Process. 9(7), 731\u2013740 (2001)","journal-title":"IEEE Trans. Speech Audio Process."},{"key":"728_CR15","unstructured":"F.L. Lamel, R.H. Kassel, S. Seneff, Speech database development: design and analysis of the acoustic-phonetic corpus, in Proceedings of DARPA Speech Recognition Workshop, Report No SAIC -86\/1546 (1986)"},{"issue":"3","key":"728_CR16","doi-asserted-by":"crossref","first-page":"1056","DOI":"10.1121\/1.396050","volume":"83","author":"R Meddis","year":"1988","unstructured":"R. Meddis, Simulation of auditory-neural transduction: further studies. J. Acoust. Soc. Am. 83(3), 1056\u20131063 (1988)","journal-title":"J. Acoust. Soc. Am."},{"issue":"10","key":"728_CR17","doi-asserted-by":"crossref","first-page":"1333","DOI":"10.1080\/00207217.2011.582450","volume":"99","author":"GR Naik","year":"2012","unstructured":"G.R. Naik, W. Wang, Audio analysis of statistically instantaneous signals with mixed Gaussian probability distributions. Int. J. Electron. 99(10), 1333\u2013135 (2012)","journal-title":"Int. J. Electron."},{"issue":"4","key":"728_CR18","doi-asserted-by":"crossref","first-page":"581","DOI":"10.15388\/Informatica.2012.376","volume":"23","author":"GR Naik","year":"2012","unstructured":"G.R. Naik, Measure of quality of source separation for sub-and super-Gaussian audio mixtures. Informatica 23(4), 581\u2013599 (2012)","journal-title":"Informatica"},{"key":"728_CR19","unstructured":"R.D. Patterson, I. Nimmo-Smith, J. Holdsworth, et al., An efficient auditory filterbank based on the gammatone function. MRC Applied Psychology Unit (1988)"},{"key":"728_CR20","first-page":"430","volume-title":"Nonlinear Speech Modeling and Applications (Lecture Notes in Computer Science)","author":"R Pichevar","year":"2005","unstructured":"R. Pichevar, J. Rouat, A quantitative evaluation of a bio-inspired sound segregation technique for two- and three-source mixtures, in Nonlinear Speech Modeling and Applications (Lecture Notes in Computer Science), ed. by G. Chollet, A. Esposito, M. Faundez-Zanuy, M. Marinaro (Springer, Berlin, 2005), pp. 430\u2013435"},{"issue":"5","key":"728_CR21","doi-asserted-by":"crossref","first-page":"445","DOI":"10.1109\/89.709670","volume":"6","author":"H Sameti","year":"1998","unstructured":"H. Sameti, H. Sheikhzadeh, L. Deng et al., HMM-based strategies for enhancement of speech signals embedded in non-stationary noise. IEEE Trans. Speech Audio Process. 6(5), 445\u2013455 (1998)","journal-title":"IEEE Trans. Speech Audio Process."},{"key":"728_CR22","doi-asserted-by":"crossref","unstructured":"S. Shoba, R. Rajavel, Adaptive energy threshold selection for monaural speech separation, in Proceedings of IEEE International Conference on Communication and Signal Process, Melmaruvathur, India (2017)","DOI":"10.1109\/ICCSP.2017.8286500"},{"issue":"6","key":"728_CR23","doi-asserted-by":"crossref","first-page":"1344","DOI":"10.1109\/TASLP.2017.2690573","volume":"25","author":"I Trowitzsch","year":"2017","unstructured":"I. Trowitzsch, Robust detection of environmental sounds in binaural auditory scenes. IEEE\/ACM Trans. Audio Speech Lang. Process. 25(6), 1344\u20131356 (2017)","journal-title":"IEEE\/ACM Trans. Audio Speech Lang. Process."},{"issue":"1","key":"728_CR24","first-page":"68","volume":"21","author":"DL Wang","year":"2013","unstructured":"D.L. Wang, H. Kun, Towards generalizing classification based speech separation. IEEE Trans. Audio Speech Lang. Process 21(1), 68\u2013177 (2013)","journal-title":"IEEE Trans. Audio Speech Lang. Process"},{"issue":"8","key":"728_CR25","first-page":"2067","volume":"18","author":"D Wang","year":"2012","unstructured":"D. Wang, Tandem algorithm for pitch estimation and voiced speech segregation. IEEE Trans. Audio Speech Lang. Process 18(8), 2067\u20132079 (2012)","journal-title":"IEEE Trans. Audio Speech Lang. Process"},{"key":"728_CR26","doi-asserted-by":"crossref","first-page":"684","DOI":"10.1109\/72.761727","volume":"10","author":"DL Wang","year":"1999","unstructured":"D.L. Wang, G.J. Brown, Separation of speech from interfering sounds based on oscillatory correlation. IEEE Trans. Neural Netw. 10, 684\u2013697 (1999)","journal-title":"IEEE Trans. Neural Netw."},{"key":"728_CR27","doi-asserted-by":"publisher","DOI":"10.1186\/1687-4722-2013-2","author":"Y Wang","year":"2013","unstructured":"Y. Wang, J. Lin, Improved monaural speech segregation based on computational auditory scene analysis. J. Audio Speech Music Process. (2013). https:\/\/doi.org\/10.1186\/1687-4722-2013-2","journal-title":"J. Audio Speech Music Process."},{"key":"728_CR28","unstructured":"M. Weintraub, A Theory and Computational Model of Auditory Monaural Sound Separation. Ph.D. dissertation (Stanford University, Standford, CA, 1985)"},{"issue":"5","key":"728_CR29","doi-asserted-by":"crossref","first-page":"1075","DOI":"10.1109\/TASLP.2017.2687104","volume":"25","author":"X Zhang","year":"2017","unstructured":"X. Zhang, D. Wang, Deep learning based binaural speech separation in reverberant environments. IEEE\/ACM Trans. Audio Speech Lang. Process. 25(5), 1075\u20131084 (2017)","journal-title":"IEEE\/ACM Trans. Audio Speech Lang. Process."}],"container-title":["Circuits, Systems, and Signal Processing"],"original-title":[],"language":"en","link":[{"URL":"http:\/\/link.springer.com\/article\/10.1007\/s00034-017-0728-x\/fulltext.html","content-type":"text\/html","content-version":"vor","intended-application":"text-mining"},{"URL":"http:\/\/link.springer.com\/content\/pdf\/10.1007\/s00034-017-0728-x.pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"text-mining"},{"URL":"http:\/\/link.springer.com\/content\/pdf\/10.1007\/s00034-017-0728-x.pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,6,28]],"date-time":"2025-06-28T23:44:22Z","timestamp":1751154262000},"score":1,"resource":{"primary":{"URL":"http:\/\/link.springer.com\/10.1007\/s00034-017-0728-x"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2017,12,18]]},"references-count":29,"journal-issue":{"issue":"8","published-print":{"date-parts":[[2018,8]]}},"alternative-id":["728"],"URL":"https:\/\/doi.org\/10.1007\/s00034-017-0728-x","relation":{},"ISSN":["0278-081X","1531-5878"],"issn-type":[{"type":"print","value":"0278-081X"},{"type":"electronic","value":"1531-5878"}],"subject":[],"published":{"date-parts":[[2017,12,18]]}}}