{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2023,7,28]],"date-time":"2023-07-28T11:35:42Z","timestamp":1690544142408},"reference-count":46,"publisher":"Springer Science and Business Media LLC","issue":"1","license":[{"start":{"date-parts":[[2019,5,6]],"date-time":"2019-05-06T00:00:00Z","timestamp":1557100800000},"content-version":"tdm","delay-in-days":0,"URL":"http:\/\/www.springer.com\/tdm"}],"content-domain":{"domain":["link.springer.com"],"crossmark-restriction":false},"short-container-title":["J Ambient Intell Human Comput"],"published-print":{"date-parts":[[2020,1]]},"DOI":"10.1007\/s12652-019-01309-y","type":"journal-article","created":{"date-parts":[[2019,5,7]],"date-time":"2019-05-07T15:53:31Z","timestamp":1557244411000},"page":"433-446","update-policy":"http:\/\/dx.doi.org\/10.1007\/springer_crossmark_policy","source":"Crossref","is-referenced-by-count":13,"title":["A new Genetic Algorithm based fusion scheme in monaural CASA system to improve the performance of the speech"],"prefix":"10.1007","volume":"11","author":[{"given":"S.","family":"Shoba","sequence":"first","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"R.","family":"Rajavel","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"297","published-online":{"date-parts":[[2019,5,6]]},"reference":[{"key":"1309_CR1","doi-asserted-by":"publisher","first-page":"113","DOI":"10.1109\/TASSP.1979.1163209","volume":"27","author":"SF Boll","year":"1979","unstructured":"Boll SF (1979) Suppression of acoustic noise in speech using spectral subtraction. IEEE Trans Audio Speech Signal Process 27:113\u2013120","journal-title":"IEEE Trans Audio Speech Signal Process"},{"key":"1309_CR2","doi-asserted-by":"publisher","first-page":"297","DOI":"10.1006\/csla.1994.1016","volume":"8","author":"GJ Brown","year":"1994","unstructured":"Brown GJ, Cooke MP (1994) Computational auditory scene analysis. Comput Speech Lang 8:297\u2013336","journal-title":"Comput Speech Lang"},{"key":"1309_CR3","doi-asserted-by":"publisher","first-page":"371","DOI":"10.1007\/3-540-27489-8_16","volume-title":"Speech enhancement","author":"GJ Brown","year":"2005","unstructured":"Brown GJ, Wang DL (2005) Separation of speech by computational auditory scene analysis. In: Benesty J, Makino S, Chen J (eds) Speech enhancement. Springer, Berlin, pp 371\u2013402"},{"key":"1309_CR30","unstructured":"Cooke MP (1993) Modeling auditory processing and organization. Dissertation, University of Sheffield, UK"},{"issue":"3","key":"1309_CR4","first-page":"259","volume":"13","author":"M Dharmalingam","year":"2017","unstructured":"Dharmalingam M, JohnWiselin MC (2017) CASA for improving speech intelligibility in monaural speech separation. Int J Perform Eng 13(3):259\u2013263","journal-title":"Int J Perform Eng"},{"issue":"7","key":"1309_CR5","doi-asserted-by":"publisher","first-page":"1492","DOI":"10.1109\/TASLP.2017.2696307","volume":"25","author":"S Donald","year":"2017","unstructured":"Donald S, Wang D (2017) Time-frequency masking in the complex domain for speech dereverberation and denoising. IEEE\/ACM Trans Audio Speech Lang Process 25(7):1492\u20131501","journal-title":"IEEE\/ACM Trans Audio Speech Lang Process"},{"key":"1309_CR6","doi-asserted-by":"publisher","first-page":"251","DOI":"10.1109\/89.397090","volume":"3","author":"Y Ephraim","year":"1995","unstructured":"Ephraim Y, Trees HL (1995) A signal subspace approach for speech enhancement. IEEE Trans Speech Audio Process 3:251\u2013266","journal-title":"IEEE Trans Speech Audio Process"},{"key":"1309_CR7","unstructured":"Ellis DPW, Weiss RJ (2006) Model-based monaural source separation using a vector-quantized phase-vocoder representation. In Proceedings on IEEE international conference on acoust speech and signal processing (ICASSP,) pp 957\u2013960"},{"issue":"8","key":"1309_CR8","doi-asserted-by":"publisher","first-page":"2080","DOI":"10.1109\/TASL.2010.2041116","volume":"18","author":"K Gibak","year":"2010","unstructured":"Gibak K, Loizou PC (2010) Improving speech intelligibility in noise using environment-optimized algorithms. IEEE Trans Audio Speech Lang Process 18(8):2080\u20132090","journal-title":"IEEE Trans Audio Speech Lang Process"},{"key":"1309_CR9","doi-asserted-by":"publisher","DOI":"10.1109\/ICCIC.2014.7238420","author":"N Harish","year":"2014","unstructured":"Harish N, Rajavel R (2014) Monaural speech separation system based on optimum soft mask. IEEE Int Conf Comput Intell Comput Res. \nhttps:\/\/doi.org\/10.1109\/ICCIC.2014.7238420","journal-title":"IEEE Int Conf Comput Intell Comput Res"},{"key":"1309_CR10","first-page":"485","volume-title":"Topics in acoustic echo and noise control","author":"G Hu","year":"2006","unstructured":"Hu G, Wang D (2006) An auditory scene analysis approach to monaural speech segregation. In: Hansler E, Schmidt G (eds) Topics in acoustic echo and noise control. Springer, New York, pp 485\u2013515"},{"issue":"2","key":"1309_CR11","doi-asserted-by":"publisher","first-page":"396","DOI":"10.1109\/TASL.2006.881700","volume":"15","author":"G Hu","year":"2007","unstructured":"Hu G, Wang D (2007) Auditory segmentation based on onset and offset analysis. IEEE Trans Audio Speech Lang Process 15(2):396\u2013405","journal-title":"IEEE Trans Audio Speech Lang Process"},{"issue":"6","key":"1309_CR12","doi-asserted-by":"publisher","first-page":"1600","DOI":"10.1109\/TASL.2010.2093893","volume":"19","author":"K Hu","year":"2011","unstructured":"Hu K, Wang D (2011) Unvoiced speech segregation from non-speech interference via CASA and spectral subtraction. IEEE Trans Audio Speech Lang Process 19(6):1600\u20131609","journal-title":"IEEE Trans Audio Speech Lang Process"},{"issue":"5","key":"1309_CR13","doi-asserted-by":"publisher","first-page":"1135","DOI":"10.1109\/TNN.2004.832812","volume":"15","author":"K Hu","year":"2004","unstructured":"Hu K, Wang D (2004) Monaural speech segregation based on pitch tracking and amplitude modulation. IEEE Trans Neural Netw 15(5):1135\u20131150","journal-title":"IEEE Trans Neural Netw"},{"key":"1309_CR14","doi-asserted-by":"crossref","unstructured":"Hu Y, Loizou PC (2007) A comparative intelligibility study of speech enhancement algorithms. In: Proceedings of IEEE international conference on acoustics speech and signal processing (ICASSP), pp 561\u2013564","DOI":"10.1109\/ICASSP.2007.366974"},{"key":"1309_CR15","doi-asserted-by":"publisher","DOI":"10.1002\/0471221317","volume-title":"Independent component analysis","author":"A Hyvarinen","year":"2001","unstructured":"Hyvarinen A, Karhunen J, Oja E (2001) Independent component analysis. Wiley, New York"},{"key":"1309_CR16","doi-asserted-by":"publisher","first-page":"731","DOI":"10.1109\/89.952491","volume":"9","author":"J Jensen","year":"2001","unstructured":"Jensen J, Hansen HL (2001) Speech enhancement using a constrained iterative sinusoidal model. IEEE Trans Speech Audio Process 9:731\u2013740","journal-title":"IEEE Trans Speech Audio Process"},{"issue":"1","key":"1309_CR17","doi-asserted-by":"publisher","first-page":"122","DOI":"10.1109\/TASL.2012.2215591","volume":"21","author":"K Hu","year":"2013","unstructured":"Hu K, Wang D (2013) An unsupervised approach to cochannel speech separation. IEEE Trans Audio Speech Lang Process 21(1):122\u2013131","journal-title":"IEEE Trans Audio Speech Lang Process"},{"issue":"1","key":"1309_CR18","first-page":"44","volume":"30","author":"L Yi-nan","year":"2014","unstructured":"Yi-nan L, xiong-wei Zhang, Zeng L, Huang JJ (2014) An improved monaural speech enhancement algorithm based on sparse dictionary learning. J Signal Process 30(1):44\u201350","journal-title":"J Signal Process"},{"issue":"5","key":"1309_CR19","doi-asserted-by":"publisher","first-page":"3387","DOI":"10.1121\/1.3097493","volume":"125","author":"J Ma","year":"2009","unstructured":"Ma J, Hu Y, Loizou P (2009) Objective measures for predicting speech intelligibility in noisy conditions based on new band-importance functions. J Acoust Soc Am 125(5):3387\u20133405","journal-title":"J Acoust Soc Am"},{"issue":"3","key":"1309_CR20","doi-asserted-by":"publisher","first-page":"1056","DOI":"10.1121\/1.396050","volume":"83","author":"R Meddis","year":"1988","unstructured":"Meddis R (1988) Simulation of auditory-neural transduction: further studies. J Acoust Soc Am 83(3):1056\u20131063","journal-title":"J Acoust Soc Am"},{"issue":"10","key":"1309_CR21","doi-asserted-by":"publisher","first-page":"1333","DOI":"10.1080\/00207217.2011.582450","volume":"99","author":"R Naik","year":"2012","unstructured":"Naik R, Ganesh R, Wang W (2012) Audio analysis of statistically instantaneous signals with mixed Gaussian probability distributions. Int J Electron 99(10):1333\u20131350","journal-title":"Int J Electron"},{"issue":"4","key":"1309_CR22","doi-asserted-by":"crossref","first-page":"581","DOI":"10.15388\/Informatica.2012.376","volume":"23","author":"R Naik","year":"2012","unstructured":"Naik R, Ganesh R (2012) Measure of quality of source separation for sub and super-Gaussian audio mixtures. Informatica 23(4):581\u2013599","journal-title":"Informatica"},{"issue":"1","key":"1309_CR23","doi-asserted-by":"publisher","first-page":"63","DOI":"10.1109\/TASL.2012.2213248","volume":"21","author":"M Nilesh","year":"2013","unstructured":"Nilesh M, Ann S et al (2013) The potential for speech intelligibility improvement using the ideal binary mask and the ideal Wiener filter in single channel noise reduction systems: application to auditory prostheses. IEEE Trans Audio Speech Lang Process 21(1):63\u201372","journal-title":"IEEE Trans Audio Speech Lang Process"},{"key":"1309_CR24","unstructured":"Patterson RD, Nimmo-Smith I, Holdsworth J et al (1988) An efficient auditory filterbank based on the gammatone function. MRC Applied Psych Unit"},{"issue":"6","key":"1309_CR25","doi-asserted-by":"publisher","first-page":"845","DOI":"10.1007\/s12652-017-0482-8","volume":"8","author":"K Phapatanaburi","year":"2017","unstructured":"Phapatanaburi K, Wang L, Oo Z et al (2017) Noise robust voice activity detection using joint phase and magnitude based feature enhancement. J Ambient Intell Hum Comput 8(6):845\u2013859","journal-title":"J Ambient Intell Hum Comput"},{"key":"1309_CR26","series-title":"Lecture notes in computer science","doi-asserted-by":"publisher","first-page":"430","DOI":"10.1007\/11520153_23","volume-title":"Nonlinear speech modeling and applications","author":"R Pichevar","year":"2005","unstructured":"Pichevar R, Rouat J (2005) A quantitative evaluation of a bio-inspired sound segregation technique for two and three-source mixtures. In: Chollet G, Esposito A, Faundez-Zanuy M, Marinaro M (eds) Nonlinear speech modeling and applications, vol 3445. Lecture notes in computer science. Springer, Berlin, pp 430\u2013435"},{"issue":"3","key":"1309_CR27","doi-asserted-by":"publisher","first-page":"e0194151","DOI":"10.1371\/journal.pone.0194151","volume":"13","author":"KA Qazi","year":"2018","unstructured":"Qazi KA, Nawaz T, Mehmood Z, Rashid M, Habib HA (2018) A hybrid technique for speech segregation and classification using a sophisticated deep neural network. PLoS ONE 13(3):e0194151. \nhttps:\/\/doi.org\/10.1371\/journal.pone.0194151","journal-title":"PLoS ONE"},{"issue":"1","key":"1309_CR28","doi-asserted-by":"publisher","first-page":"83","DOI":"10.1007\/s11265-011-0578-x","volume":"68","author":"R Rajavel","year":"2012","unstructured":"Rajavel R, Sathidevi PS (2012) Adaptive reliability measure and optimum integration weight for decision fusion audio-visual speech recognition. J Signal Process System 68(1):83\u201393","journal-title":"J Signal Process System"},{"issue":"2","key":"1309_CR29","doi-asserted-by":"publisher","first-page":"123","DOI":"10.1504\/IJSISE.2011.041605","volume":"4","author":"R Rajavel","year":"2011","unstructured":"Rajavel R, Sathidevi PS (2011) A new GA optimised reliability ratio based integration weight estimation scheme for decision fusion audio-visual speech recognition. Int J Signal Imaging Syst Eng 4(2):123\u2013131","journal-title":"Int J Signal Imaging Syst Eng"},{"key":"1309_CR31","doi-asserted-by":"publisher","first-page":"445","DOI":"10.1109\/89.709670","volume":"6","author":"H Sameti","year":"1998","unstructured":"Sameti H, Sheikhzadeh H, Deng L, Brennan RL (1998) HMM-based strategies for enhancement of speech signals embedded in non-stationary noise. IEEE Trans Speech Audio Process 6:445\u2013455","journal-title":"IEEE Trans Speech Audio Process"},{"key":"1309_CR32","unstructured":"Shoba S, Rajavel R (2017) Adaptive energy threshold selection for monaural speech separation. In: International conference on communication and signal processing (ICCSP), India, pp 905\u2013908"},{"issue":"8","key":"1309_CR33","doi-asserted-by":"publisher","first-page":"3651","DOI":"10.1007\/s00034-017-0728-x","volume":"37","author":"S Shoba","year":"2017","unstructured":"Shoba S, Rajavel R (2017) Image processing techniques for segments grouping in monaural speech separation. Circ Syst Signal Process 37(8):3651\u20133670","journal-title":"Circ Syst Signal Process"},{"key":"1309_CR34","doi-asserted-by":"publisher","DOI":"10.1007\/s00034-018-1005-3","author":"S Shoba","year":"2018","unstructured":"Shoba S, Rajavel R (2018) Improving speech intelligibility in monaural segregation system by fusing voiced and unvoiced speech segments circuits systems and signal process. Circ Syst Signal Process. \nhttps:\/\/doi.org\/10.1007\/s00034-018-1005-3","journal-title":"Circ Syst Signal Process"},{"issue":"7","key":"1309_CR35","doi-asserted-by":"publisher","first-page":"896","DOI":"10.1049\/iet-spr.2017.0375","volume":"12","author":"S Shoba","year":"2018","unstructured":"Shoba S, Rajavel R (2018) Performance improvement of monaural speech separation system using image analysis techniques. IET Signal Process 12(7):896\u2013906","journal-title":"IET Signal Process"},{"key":"1309_CR36","doi-asserted-by":"publisher","DOI":"10.1007\/s12652-018-1146-z","author":"S Singhal","year":"2018","unstructured":"Singhal S, Passricha V, Sharma P et al (2018) Multi-level region-of-interest CNNs for end to end speech recognition. J Ambient Intell Hum Comput. \nhttps:\/\/doi.org\/10.1007\/s12652-018-1146-z","journal-title":"J Ambient Intell Hum Comput"},{"issue":"7","key":"1309_CR37","doi-asserted-by":"publisher","first-page":"2125","DOI":"10.1109\/TASL.2011.2114881","volume":"19","author":"CH Taal","year":"2011","unstructured":"Taal CH, Hendriks RC, Heusdens R et al (2011) An algorithm for intelligibility prediction of time frequency weighted noisy speech. IEEE Trans Audio Speech Lang Process 19(7):2125\u20132136","journal-title":"IEEE Trans Audio Speech Lang Process"},{"key":"1309_CR38","doi-asserted-by":"publisher","DOI":"10.1007\/s12652-017-0653-7","author":"SS Therese","year":"2017","unstructured":"Therese SS, Lingam C (2017) A linear visual assessment tendency based clustering with power normalized cepstral coefficients for audio signal recognition system. J Ambient Intell Hum Comput. \nhttps:\/\/doi.org\/10.1007\/s12652-017-0653-7","journal-title":"J Ambient Intell Hum Comput"},{"issue":"6","key":"1309_CR39","doi-asserted-by":"publisher","first-page":"1344","DOI":"10.1109\/TASLP.2017.2690573","volume":"25","author":"Ivo Trowitzsch","year":"2017","unstructured":"Trowitzsch Ivo (2017) Robust detection of environmental sounds in binaural auditory scenes. IEEE\/ACM Trans Audio Speech Lang Process 25(6):1344\u20131356","journal-title":"IEEE\/ACM Trans Audio Speech Lang Process"},{"issue":"1","key":"1309_CR40","first-page":"68","volume":"21","author":"DL Wang","year":"2013","unstructured":"Wang DL, Kun H (2013) Towards generalizing classification based speech separation. IEEE Trans Audio Speech Lang Process 21(1):68\u201377","journal-title":"IEEE Trans Audio Speech Lang Process"},{"issue":"8","key":"1309_CR41","first-page":"2067","volume":"18","author":"D Wang","year":"2012","unstructured":"Wang D (2012) Tandem algorithm for pitch estimation and voiced speech segregation. IEEE Trans Audio Speech Lang Process 18(8):2067\u20132079","journal-title":"IEEE Trans Audio Speech Lang Process"},{"key":"1309_CR42","doi-asserted-by":"publisher","first-page":"684","DOI":"10.1109\/72.761727","volume":"10","author":"DL Wang","year":"1999","unstructured":"Wang DL, Brown GJ (1999) Separation of speech from interfering sounds based on oscillatory correlation. IEEE Trans Neural Netw 10:684\u2013697","journal-title":"IEEE Trans Neural Netw"},{"key":"1309_CR43","doi-asserted-by":"publisher","DOI":"10.1186\/1687-4722-2013-2","author":"Y Wang","year":"2013","unstructured":"Wang Y, Lin J, Chen N, Yuan W (2013) Improved monaural speech segregation based on computational auditory scene analysis. J Audio Speech Music Process. \nhttps:\/\/doi.org\/10.1186\/1687-4722-2013-2","journal-title":"J Audio Speech Music Process"},{"key":"1309_CR44","unstructured":"Weintraub M (1985) A theory and computational model of auditory monaural sound separation. Ph.D. dissertation, Dept Elect Eng, Stanford University"},{"issue":"6","key":"1309_CR45","doi-asserted-by":"publisher","first-page":"925","DOI":"10.1007\/s12652-017-0501-9","volume":"8","author":"J Yu","year":"2017","unstructured":"Yu J, Xie L, Xiao X et al (2017) A hybrid neural network hidden Markov model approach for automatic story segmentation. J Ambient Intell Hum Comput 8(6):925\u2013936","journal-title":"J Ambient Intell Hum Comput"},{"issue":"5","key":"1309_CR46","doi-asserted-by":"publisher","first-page":"1075","DOI":"10.1109\/TASLP.2017.2687104","volume":"25","author":"X Zhang","year":"2017","unstructured":"Zhang X, Wang DL (2017) Deep learning based binaural speech separation in reverberant environments. IEEE\/ACM Trans Audio Speech Lang Process 25(5):1075\u20131084","journal-title":"IEEE\/ACM Trans Audio Speech Lang Process"}],"container-title":["Journal of Ambient Intelligence and Humanized Computing"],"original-title":[],"language":"en","link":[{"URL":"http:\/\/link.springer.com\/content\/pdf\/10.1007\/s12652-019-01309-y.pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"text-mining"},{"URL":"http:\/\/link.springer.com\/article\/10.1007\/s12652-019-01309-y\/fulltext.html","content-type":"text\/html","content-version":"vor","intended-application":"text-mining"},{"URL":"http:\/\/link.springer.com\/content\/pdf\/10.1007\/s12652-019-01309-y.pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2020,5,4]],"date-time":"2020-05-04T23:29:36Z","timestamp":1588634976000},"score":1,"resource":{"primary":{"URL":"http:\/\/link.springer.com\/10.1007\/s12652-019-01309-y"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2019,5,6]]},"references-count":46,"journal-issue":{"issue":"1","published-print":{"date-parts":[[2020,1]]}},"alternative-id":["1309"],"URL":"https:\/\/doi.org\/10.1007\/s12652-019-01309-y","relation":{},"ISSN":["1868-5137","1868-5145"],"issn-type":[{"value":"1868-5137","type":"print"},{"value":"1868-5145","type":"electronic"}],"subject":[],"published":{"date-parts":[[2019,5,6]]},"assertion":[{"value":"30 May 2018","order":1,"name":"received","label":"Received","group":{"name":"ArticleHistory","label":"Article History"}},{"value":"28 April 2019","order":2,"name":"accepted","label":"Accepted","group":{"name":"ArticleHistory","label":"Article History"}},{"value":"6 May 2019","order":3,"name":"first_online","label":"First Online","group":{"name":"ArticleHistory","label":"Article History"}}]}}