{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2024,10,9]],"date-time":"2024-10-09T18:10:02Z","timestamp":1728497402837},"reference-count":26,"publisher":"Springer Science and Business Media LLC","issue":"1","license":[{"start":{"date-parts":[[2022,11,29]],"date-time":"2022-11-29T00:00:00Z","timestamp":1669680000000},"content-version":"tdm","delay-in-days":0,"URL":"https:\/\/www.springernature.com\/gp\/researchers\/text-and-data-mining"},{"start":{"date-parts":[[2022,11,29]],"date-time":"2022-11-29T00:00:00Z","timestamp":1669680000000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/www.springernature.com\/gp\/researchers\/text-and-data-mining"}],"funder":[{"name":"Science and Engineering Research Board (SERB), Department of Science and Technology (DST), Government of India","award":["EEQ\/2018\/001338"],"award-info":[{"award-number":["EEQ\/2018\/001338"]}]}],"content-domain":{"domain":["link.springer.com"],"crossmark-restriction":false},"short-container-title":["SN COMPUT. SCI."],"DOI":"10.1007\/s42979-022-01484-4","type":"journal-article","created":{"date-parts":[[2022,11,29]],"date-time":"2022-11-29T12:08:48Z","timestamp":1669723728000},"update-policy":"http:\/\/dx.doi.org\/10.1007\/springer_crossmark_policy","source":"Crossref","is-referenced-by-count":0,"title":["Single Channel Speech Enhancement Using Masking Based on Sinusoidal Modeling"],"prefix":"10.1007","volume":"4","author":[{"given":"Ashishkumar","family":"Gudmalwar","sequence":"first","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Ch V. Rama","family":"Rao","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"297","published-online":{"date-parts":[[2022,11,29]]},"reference":[{"key":"1484_CR1","volume-title":"Speech enhancement","author":"S Makino","year":"2005","unstructured":"Makino S. Speech enhancement. Berlin: Springer; 2005."},{"issue":"2","key":"1484_CR2","doi-asserted-by":"publisher","first-page":"113","DOI":"10.1109\/TASSP.1979.1163209","volume":"27","author":"S Boll","year":"1979","unstructured":"Boll S. Suppression of acoustic noise in speech using spectral subtraction. IEEE Trans Acoust Speech Signal Process. 1979;27(2):113\u201320.","journal-title":"IEEE Trans Acoust Speech Signal Process"},{"issue":"6","key":"1484_CR3","doi-asserted-by":"publisher","first-page":"1109","DOI":"10.1109\/TASSP.1984.1164453","volume":"32","author":"Y Ephraim","year":"1984","unstructured":"Ephraim Y, Malah D. Speech enhancement using a minimum-mean square error short-time spectral amplitude estimator. IEEE Trans Acoust Speech Signal Process. 1984;32(6):1109\u201321.","journal-title":"IEEE Trans Acoust Speech Signal Process"},{"issue":"2","key":"1484_CR4","doi-asserted-by":"publisher","first-page":"443","DOI":"10.1109\/TASSP.1985.1164550","volume":"33","author":"Y Ephraim","year":"1985","unstructured":"Ephraim Y, Malah D. Speech enhancement using a minimum mean-square error log-spectral amplitude estimator. IEEE Trans Acoust Speech Signal Process. 1985;33(2):443\u20135.","journal-title":"IEEE Trans Acoust Speech Signal Process"},{"issue":"1","key":"1484_CR5","doi-asserted-by":"publisher","first-page":"12","DOI":"10.1109\/97.988717","volume":"9","author":"I Cohen","year":"2002","unstructured":"Cohen I, Berdugo B. Noise estimation by minima controlled recursive averaging for robust speech enhancement. IEEE Signal Process Lett. 2002;9(1):12\u20135.","journal-title":"IEEE Signal Process Lett"},{"issue":"5","key":"1484_CR6","doi-asserted-by":"publisher","first-page":"466","DOI":"10.1109\/TSA.2003.811544","volume":"11","author":"I Cohen","year":"2003","unstructured":"Cohen I. Noise spectrum estimation in adverse environments: improved minima controlled recursive averaging. IEEE Trans Speech Audio Process. 2003;11(5):466\u201375.","journal-title":"IEEE Trans Speech Audio Process"},{"issue":"3","key":"1484_CR7","doi-asserted-by":"publisher","first-page":"197","DOI":"10.1109\/TASSP.1978.1163086","volume":"26","author":"J Lim","year":"1978","unstructured":"Lim J, Oppenheim A. All-pole modeling of degraded speech. IEEE Trans Acoust Speech Signal Process. 1978;26(3):197\u2013210.","journal-title":"IEEE Trans Acoust Speech Signal Process"},{"doi-asserted-by":"crossref","unstructured":"Scalart P. et\u00a0al. Speech enhancement based on a priori signal to noise estimation. In: 1996 IEEE international conference on acoustics, speech, and signal processing conference proceedings, vol 2. IEEE; 1996. p. 629\u201332.","key":"1484_CR8","DOI":"10.1109\/ICASSP.1996.543199"},{"issue":"7","key":"1484_CR9","doi-asserted-by":"publisher","first-page":"1","DOI":"10.1155\/ASP.2005.1110","volume":"2005","author":"T Lotter","year":"2005","unstructured":"Lotter T, Vary P. Speech enhancement by map spectral amplitude estimation using a super-gaussian speech model. EURASIP J Adv Signal Process. 2005;2005(7):1\u201317.","journal-title":"EURASIP J Adv Signal Process"},{"doi-asserted-by":"crossref","unstructured":"Fodor B, Fingscheidt T. Speech enhancement using a joint map estimator with gaussian mixture model for (non-) stationary noise. In: IEEE international conference on acoustics, speech and signal processing (ICASSP). IEEE. 2011. p. 4768\u201371.","key":"1484_CR10","DOI":"10.1109\/ICASSP.2011.5947421"},{"issue":"3","key":"1484_CR11","doi-asserted-by":"publisher","first-page":"336","DOI":"10.1016\/j.specom.2005.02.011","volume":"47","author":"I Cohen","year":"2005","unstructured":"Cohen I. Speech enhancement using super-gaussian speech models and noncausal a priori snr estimation. Speech Commun. 2005;47(3):336\u201350.","journal-title":"Speech Commun"},{"issue":"1","key":"1484_CR12","doi-asserted-by":"publisher","first-page":"186","DOI":"10.1109\/TASL.2010.2045799","volume":"19","author":"S Suhadi","year":"2010","unstructured":"Suhadi S, Last C, Fingscheidt T. A data-driven approach to a priori snr estimation. IEEE Trans Audio Speech Lang Process. 2010;19(1):186\u201395.","journal-title":"IEEE Trans Audio Speech Lang Process"},{"doi-asserted-by":"crossref","unstructured":"Elshamy S, Madhu N, Tirry W, Fingscheidt T. An iterative speech model-based a priori snr estimator. In: Sixteenth annual conference of the international speech communication association; 2015.","key":"1484_CR13","DOI":"10.21437\/Interspeech.2015-405"},{"issue":"8","key":"1484_CR14","doi-asserted-by":"publisher","first-page":"1592","DOI":"10.1109\/TASLP.2017.2702385","volume":"25","author":"S Elshamy","year":"2017","unstructured":"Elshamy S, Madhu N, Tirry W, Fingscheidt T. Instantaneous a priori snr estimation by cepstral excitation manipulation. IEEE\/ACM Trans Audio Speech Lang Process. 2017;25(8):1592\u2013605.","journal-title":"IEEE\/ACM Trans Audio Speech Lang Process"},{"issue":"5","key":"1484_CR15","doi-asserted-by":"publisher","first-page":"910","DOI":"10.1109\/TASL.2008.921764","volume":"16","author":"T Gerkmann","year":"2008","unstructured":"Gerkmann T, Breithaupt C, Martin R. Improved a posteriori speech presence probability estimation based on a likelihood ratio with fixed priors. IEEE Trans Audio Speech Lang Process. 2008;16(5):910\u20139.","journal-title":"IEEE Trans Audio Speech Lang Process"},{"issue":"12","key":"1484_CR16","doi-asserted-by":"publisher","first-page":"1849","DOI":"10.1109\/TASLP.2014.2352935","volume":"22","author":"Y Wang","year":"2014","unstructured":"Wang Y, Narayanan A, Wang D. On training targets for supervised speech separation. IEEE\/ACM Trans Audio Speech Lang Process. 2014;22(12):1849\u201358.","journal-title":"IEEE\/ACM Trans Audio Speech Lang Process"},{"issue":"3","key":"1484_CR17","doi-asserted-by":"publisher","first-page":"483","DOI":"10.1109\/TASLP.2015.2512042","volume":"24","author":"DS Williamson","year":"2015","unstructured":"Williamson DS, Wang Y, Wang D. Complex ratio masking for monaural speech separation. IEEE\/ACM Trans Audio Speech Lang Process. 2015;24(3):483\u201392.","journal-title":"IEEE\/ACM Trans Audio Speech Lang Process"},{"key":"1484_CR18","doi-asserted-by":"publisher","first-page":"181","DOI":"10.1007\/0-387-22794-6_12","volume-title":"Speech separation by humans and machines","author":"D Wang","year":"2005","unstructured":"Wang D. On ideal binary mask as the computational goal of auditory scene analysis. In: Speech separation by humans and machines. Berlin: Springer; 2005. p. 181\u201397."},{"issue":"4","key":"1484_CR19","doi-asserted-by":"publisher","first-page":"744","DOI":"10.1109\/TASSP.1986.1164910","volume":"34","author":"R McAulay","year":"1986","unstructured":"McAulay R, Quatieri T. Speech analysis\/synthesis based on a sinusoidal representation. IEEE Trans Acoust Speech Signal Process. 1986;34(4):744\u201354.","journal-title":"IEEE Trans Acoust Speech Signal Process"},{"issue":"15","key":"1484_CR20","doi-asserted-by":"publisher","first-page":"1077","DOI":"10.1587\/elex.6.1077","volume":"6","author":"P Mowlaee","year":"2009","unstructured":"Mowlaee P, Sayadiuan A, Sheikhzadeh H. Fdmsm robust signal representation for speech mixtures and noise corrupted audio signals. IEICE Electron Expr. 2009;6(15):1077\u201383.","journal-title":"IEICE Electron Expr"},{"key":"1484_CR21","doi-asserted-by":"publisher","first-page":"380","DOI":"10.1109\/TASLP.2019.2955276","volume":"28","author":"K Tan","year":"2019","unstructured":"Tan K, Wang D. Learning complex spectral mapping with gated convolutional recurrent networks for monaural speech enhancement. IEEE\/ACM Trans Audio Speech Lang Process. 2019;28:380\u201390.","journal-title":"IEEE\/ACM Trans Audio Speech Lang Process"},{"issue":"6","key":"1484_CR22","doi-asserted-by":"publisher","first-page":"459","DOI":"10.1016\/j.aeue.2011.10.007","volume":"66","author":"CVR Rao","year":"2012","unstructured":"Rao CVR, Murthy MR, Rao KS. Speech enhancement using sub-band cross-correlation compensated wiener filter combined with harmonic regeneration. AEU Int J Electron Commun. 2012;66(6):459\u201364.","journal-title":"AEU Int J Electron Commun"},{"unstructured":"https:\/\/ecs.utdallas.edu\/loizou\/speech\/noizeus\/","key":"1484_CR23"},{"doi-asserted-by":"crossref","unstructured":"Panayotov V, Chen G, Povey D, Khudanpur S. Librispeech: an ASR corpus based on public domain audio books. In: 2015 IEEE international conference on acoustics, speech and signal processing (ICASSP). IEEE; 2015. p. 5206\u20135210","key":"1484_CR24","DOI":"10.1109\/ICASSP.2015.7178964"},{"doi-asserted-by":"crossref","unstructured":"Rix AW, Beerends JG, Hollier MP, Hekstra AP. Perceptual evaluation of speech quality (pesq)-a new method for speech quality assessment of telephone networks and codecs. In: 2001 IEEE international conference on acoustics, speech, and signal processing. Proceedings (Cat. No. 01CH37221), vol 2. IEEE; 2001. p. 749\u2013752.","key":"1484_CR25","DOI":"10.1109\/ICASSP.2001.941023"},{"issue":"1","key":"1484_CR26","doi-asserted-by":"publisher","first-page":"229","DOI":"10.1109\/TASL.2007.911054","volume":"16","author":"Y Hu","year":"2007","unstructured":"Hu Y, Loizou PC. Evaluation of objective quality measures for speech enhancement. IEEE Trans Audio Speech Lang Process. 2007;16(1):229\u201338.","journal-title":"IEEE Trans Audio Speech Lang Process"}],"container-title":["SN Computer Science"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/link.springer.com\/content\/pdf\/10.1007\/s42979-022-01484-4.pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/link.springer.com\/article\/10.1007\/s42979-022-01484-4\/fulltext.html","content-type":"text\/html","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/link.springer.com\/content\/pdf\/10.1007\/s42979-022-01484-4.pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2024,10,9]],"date-time":"2024-10-09T17:47:27Z","timestamp":1728496047000},"score":1,"resource":{"primary":{"URL":"https:\/\/link.springer.com\/10.1007\/s42979-022-01484-4"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2022,11,29]]},"references-count":26,"journal-issue":{"issue":"1","published-online":{"date-parts":[[2023,1]]}},"alternative-id":["1484"],"URL":"https:\/\/doi.org\/10.1007\/s42979-022-01484-4","relation":{},"ISSN":["2661-8907"],"issn-type":[{"type":"electronic","value":"2661-8907"}],"subject":[],"published":{"date-parts":[[2022,11,29]]},"assertion":[{"value":"24 April 2022","order":1,"name":"received","label":"Received","group":{"name":"ArticleHistory","label":"Article History"}},{"value":"31 October 2022","order":2,"name":"accepted","label":"Accepted","group":{"name":"ArticleHistory","label":"Article History"}},{"value":"29 November 2022","order":3,"name":"first_online","label":"First Online","group":{"name":"ArticleHistory","label":"Article History"}},{"order":1,"name":"Ethics","group":{"name":"EthicsHeading","label":"Declarations"}},{"value":"Authors have received the Science and Engineering Research Board (SERB), Department of Science and Technology (DST), Government of India and, file no. is EEQ\/2018\/001338, dated 27th February 2019.","order":2,"name":"Ethics","group":{"name":"EthicsHeading","label":"Conflict of interest"}}],"article-number":"71"}}