{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2025,11,2]],"date-time":"2025-11-02T16:59:07Z","timestamp":1762102747461,"version":"3.37.3"},"reference-count":36,"publisher":"Springer Science and Business Media LLC","issue":"12","license":[{"start":{"date-parts":[[2022,7,25]],"date-time":"2022-07-25T00:00:00Z","timestamp":1658707200000},"content-version":"tdm","delay-in-days":0,"URL":"https:\/\/www.springer.com\/tdm"},{"start":{"date-parts":[[2022,7,25]],"date-time":"2022-07-25T00:00:00Z","timestamp":1658707200000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/www.springer.com\/tdm"}],"funder":[{"DOI":"10.13039\/501100001843","name":"science and engineering research board","doi-asserted-by":"publisher","award":["CRG\/2018\/003920"],"award-info":[{"award-number":["CRG\/2018\/003920"]}],"id":[{"id":"10.13039\/501100001843","id-type":"DOI","asserted-by":"publisher"}]}],"content-domain":{"domain":["link.springer.com"],"crossmark-restriction":false},"short-container-title":["Circuits Syst Signal Process"],"published-print":{"date-parts":[[2022,12]]},"DOI":"10.1007\/s00034-022-02106-3","type":"journal-article","created":{"date-parts":[[2022,7,25]],"date-time":"2022-07-25T21:02:31Z","timestamp":1658782951000},"page":"6999-7034","update-policy":"https:\/\/doi.org\/10.1007\/springer_crossmark_policy","source":"Crossref","is-referenced-by-count":4,"title":["Optimal Near-End Speech Intelligibility Improvement Using CLPSO-Based Voice Transformation in Realistic Noisy Environments"],"prefix":"10.1007","volume":"41","author":[{"ORCID":"https:\/\/orcid.org\/0000-0003-4108-1217","authenticated-orcid":false,"given":"Ritujoy","family":"Biswas","sequence":"first","affiliation":[]},{"given":"Karan","family":"Nathwani","sequence":"additional","affiliation":[]}],"member":"297","published-online":{"date-parts":[[2022,7,25]]},"reference":[{"key":"2106_CR1","doi-asserted-by":"publisher","unstructured":"G. Biagetti et al., Speaker identification in noisy conditions using short sequences of speech frames, in Intelligent Decision Technologies 2017 (2018), pp. 43\u201352. ISBN: 978-3-319-59423-1. https:\/\/doi.org\/10.1007\/978-3-319-59424-8_5","DOI":"10.1007\/978-3-319-59424-8_5"},{"key":"2106_CR2","unstructured":"F. Cummins et al., The chains corpus: characterizing individual speakers, in SPECOM, vol. 6, SPC RAS. (2006), pp. 431\u2013435"},{"issue":"6","key":"2106_CR3","doi-asserted-by":"publisher","first-page":"1109","DOI":"10.1109\/TASSP.1984.1164453","volume":"32","author":"Y Ephraim","year":"1984","unstructured":"Y. Ephraim, D. Malah, Speech enhancement using a minimum\u2014mean square error short-time spectral amplitude estimator. IEEE Trans. Acoust. Speech Signal Process. 32(6), 1109\u20131121 (1984). https:\/\/doi.org\/10.1109\/TASSP.1984.1164453","journal-title":"IEEE Trans. Acoust. Speech Signal Process."},{"key":"2106_CR4","doi-asserted-by":"publisher","first-page":"1170","DOI":"10.1109\/LSP.2021.3086405","volume":"28","author":"F Farias","year":"2021","unstructured":"F. Farias, R. Coelho, Blind adaptive mask to improve intelligibility of non-stationary noisy speech. IEEE Signal Process. Lett. 28, 1170\u20131174 (2021). https:\/\/doi.org\/10.1109\/LSP.2021.3086405","journal-title":"IEEE Signal Process. Lett."},{"key":"2106_CR5","unstructured":"E. Fonseca et al., Freesound datasets: a platform for the creation of open audio datasets, in Proceedings of the 18th ISMIR Conference, Suzhou, China [Canada] (2017), pp. 486\u2013493"},{"issue":"1","key":"2106_CR6","doi-asserted-by":"publisher","first-page":"81","DOI":"10.1121\/1.1910768","volume":"43","author":"JD Griffiths","year":"1968","unstructured":"J.D. Griffiths, Optimum linear filter for speech transmission. J. Acoust. Soc. Am. 43(1), 81\u201386 (1968). https:\/\/doi.org\/10.1121\/1.1910768","journal-title":"J. Acoust. Soc. Am."},{"key":"2106_CR7","doi-asserted-by":"publisher","first-page":"851","DOI":"10.1109\/TASLP.2015.2409780","volume":"23","author":"R Hendriks","year":"2015","unstructured":"R. Hendriks et al., Optimal near-end speech intelligibility improvement incorporating additive noise and late reverberation under an approximation of the short-time SII. Trans. Audio Speech Lang. Process. 23, 851\u2013862 (2015). https:\/\/doi.org\/10.1109\/TASLP.2015.2409780","journal-title":"Trans. Audio Speech Lang. Process."},{"key":"2106_CR8","doi-asserted-by":"publisher","unstructured":"Y. Hu, P. Loizou. Subjective comparison of speech enhancement algorithms, in 2006 IEEE International Conference on Acoustics Speech and Signal Processing Proceedings, vol. 1 (2006), pp. I\u2013I. https:\/\/doi.org\/10.1109\/ICASSP.2006.1659980","DOI":"10.1109\/ICASSP.2006.1659980"},{"key":"2106_CR9","doi-asserted-by":"publisher","unstructured":"Y. Jiang, H. Zhou, Z. Feng, Performance analysis of ideal binary masks in speech enhancement, in 4th International Congress on Image and Signal Processing, vol. 5 (IEEE, 2011), pp. 2422\u20132425. https:\/\/doi.org\/10.1109\/CISP.2011.6100732","DOI":"10.1109\/CISP.2011.6100732"},{"key":"2106_CR10","doi-asserted-by":"publisher","unstructured":"J. J. Liang et al. \u201cComprehensive learning particle swarm optimizer for global optimization of multimodal functions\u201d. In: Transactions on Evolutionary Computation 10.3 (2006), pp. 281\u2013295. https:\/\/doi.org\/10.1109\/TEVC.2005.857610","DOI":"10.1109\/TEVC.2005.857610"},{"issue":"8","key":"2106_CR11","first-page":"1182","volume":"6","author":"R Martin","year":"1994","unstructured":"R. Martin, Spectral subtraction based on minimum statistics. Power 6(8), 1182\u20131185 (1994)","journal-title":"Power"},{"key":"2106_CR12","unstructured":"N. McLaughlin, J. Ming, D. Crookes, Speaker recognition in noisy conditions with limited training data, in 2011 19th European Signal Processing Conference (2011), pp. 1294\u20131298"},{"key":"2106_CR13","doi-asserted-by":"publisher","DOI":"10.1109\/TASL.2007.899278","author":"J Ming","year":"2007","unstructured":"J. Ming et al., Robust speaker recognition in noisy conditions. IEEE Trans. Audio Speech Lang. Process. (2007). https:\/\/doi.org\/10.1109\/TASL.2007.899278","journal-title":"IEEE Trans. Audio Speech Lang. Process."},{"key":"2106_CR14","doi-asserted-by":"publisher","unstructured":"K. Nathwani, Intelligibility improvement using kalman filtering & EM approach in formant shifting framework, in International Symposium on Signal Processing and Information Technology (ISSPIT) (IEEE, 2019), pp. 1\u20136. https:\/\/doi.org\/10.1109\/ISSPIT47144.2019.9001849","DOI":"10.1109\/ISSPIT47144.2019.9001849"},{"issue":"6","key":"2106_CR15","doi-asserted-by":"publisher","first-page":"1326","DOI":"10.1109\/TMM.2013.2247391","volume":"15","author":"K Nathwani","year":"2013","unstructured":"K. Nathwani, P. Pandit, R.M. Hegde, Group delay based methods for speaker segregation and its application in multimedia information retrieval. IEEE Trans. Multimed. 15(6), 1326\u20131339 (2013)","journal-title":"IEEE Trans. Multimed."},{"key":"2106_CR16","doi-asserted-by":"publisher","unstructured":"K. Nathwani et al., Formant shifting for speech intelligibility improvement in car noise environment, in International Conference on Acoustics, Speech and Signal Processing (ICASSP) (IEEE, 2016), pp. 5375\u20135379. https:\/\/doi.org\/10.1109\/ICASSP.2016.7472704","DOI":"10.1109\/ICASSP.2016.7472704"},{"key":"2106_CR17","doi-asserted-by":"publisher","first-page":"17","DOI":"10.1016\/j.specom.2017.04.007","volume":"91","author":"K Nathwani","year":"2017","unstructured":"K. Nathwani et al., Speech intelligibility improvement in car noise environment by voice transformation. Speech Commun. 91, 17\u201327 (2017). https:\/\/doi.org\/10.1016\/j.specom.2017.04.007","journal-title":"Speech Commun."},{"issue":"4","key":"2106_CR18","doi-asserted-by":"publisher","first-page":"277","DOI":"10.1109\/TASSP.1976.1162824","volume":"24","author":"RJ Niederjohn","year":"1976","unstructured":"R.J. Niederjohn, J.H. Grotelueschen, The enhancement of speech intelligibility in high noise levels by high-pass filtering followed by rapid amplitude compression. IEEE Trans. Acoust. Speech Signal Process. 24(4), 277\u2013282 (1976). https:\/\/doi.org\/10.1109\/TASSP.1976.1162824","journal-title":"IEEE Trans. Acoust. Speech Signal Process."},{"key":"2106_CR19","doi-asserted-by":"publisher","DOI":"10.1109\/TII.2020.3017744","author":"R Patel","year":"2020","unstructured":"R. Patel et al., Nonlinear excitation control of diesel generator: a command filter backstepping approach. Trans. Ind. Inform. (2020). https:\/\/doi.org\/10.1109\/TII.2020.3017744","journal-title":"Trans. Ind. Inform."},{"key":"2106_CR20","volume-title":"Theory and Applications of Digital Speech Processing","author":"L Rabiner","year":"2010","unstructured":"L. Rabiner, R. Schafer, Theory and Applications of Digital Speech Processing (Prentice Hall Press, Hoboken, 2010)"},{"issue":"3","key":"2106_CR21","doi-asserted-by":"publisher","first-page":"262","DOI":"10.17485\/ijst\/2014\/v7i3.7","volume":"7","author":"M Rahmati","year":"2014","unstructured":"M. Rahmati, R. Effatnejad, A. Safari, Comprehensive learning particle swarm optimization (CLPSO) for multi-objective optimal power flow. Indian J. Sci. Technol. 7(3), 262\u2013270 (2014). https:\/\/doi.org\/10.17485\/ijst\/2014\/v7i3.7","journal-title":"Indian J. Sci. Technol."},{"key":"2106_CR22","volume-title":"Gaussian Processes for Machine Learning","author":"CE Rasmussen","year":"2006","unstructured":"C.E. Rasmussen, C.K.I. Williams, Gaussian Processes for Machine Learning (The MIT Press, Cambridge, 2006)"},{"key":"2106_CR23","unstructured":"A.W. Rix et al., Perceptual evaluation of speech quality (PESQ)-a new method for speech quality assessment of telephone networks and codecs, in IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP) (2001), pp. 749\u2013752"},{"key":"2106_CR24","doi-asserted-by":"publisher","unstructured":"M. Song et al., A time-weighted method for predicting the intelligibility of speech in the presence of interfering sounds, in 2018 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP) (2018), pp. 5589\u20135593. https:\/\/doi.org\/10.1109\/ICASSP.2018.8462124","DOI":"10.1109\/ICASSP.2018.8462124"},{"issue":"5","key":"2106_CR25","doi-asserted-by":"publisher","first-page":"383","DOI":"10.1109\/89.536932","volume":"4","author":"T Sreenivas","year":"1996","unstructured":"T. Sreenivas, P. Kirnapure, Codebook constrained Wiener filtering for speech enhancement. IEEE Trans. Speech Audio Process. 4(5), 383\u2013389 (1996). https:\/\/doi.org\/10.1109\/89.536932","journal-title":"IEEE Trans. Speech Audio Process."},{"issue":"4","key":"2106_CR26","doi-asserted-by":"publisher","first-page":"858","DOI":"10.1016\/j.csl.2013.11.003","volume":"28","author":"C Taal","year":"2014","unstructured":"C. Taal, R. Hendriks, H. Richard, Speech energy redistribution for intelligibility improvement in noise based on a perceptual distortion measure. Comput. Speech Lang. 28(4), 858\u2013872 (2014). https:\/\/doi.org\/10.1016\/j.csl.2013.11.003","journal-title":"Comput. Speech Lang."},{"key":"2106_CR27","doi-asserted-by":"crossref","unstructured":"C. Taal, J. Jensen, SII-based speech preprocessing for intelligibility improvement in noise, in Annual Conference of the International Speech Communication Association. INTERSPEECH (2013), pp. 3582\u20133586","DOI":"10.21437\/Interspeech.2013-770"},{"key":"2106_CR28","doi-asserted-by":"publisher","unstructured":"C.H. Taal et al., A short-time objective intelligibility measure for time-frequency weighted noisy speech, in International Conference on Acoustics, Speech and Signal Processing (IEEE, 2010), pp. 4214\u20134217. https:\/\/doi.org\/10.1109\/ICASSP.2010.5495701","DOI":"10.1109\/ICASSP.2010.5495701"},{"key":"2106_CR29","doi-asserted-by":"crossref","unstructured":"Y. Tang., Background adaptation for improved listening experience in broadcasting, in 2019 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP) (IEEE, 2019), pp. 8008\u20138012","DOI":"10.1109\/ICASSP.2019.8682687"},{"issue":"23","key":"2106_CR30","doi-asserted-by":"publisher","first-page":"175","DOI":"10.1016\/0167-6393(92)90012-V","volume":"11","author":"H Valbret","year":"1992","unstructured":"H. Valbret, E. Moulines, J.-P. Tubach, Voice transformation using PSOLA technique. Speech Commun. 11(23), 175\u2013187 (1992)","journal-title":"Speech Commun."},{"key":"2106_CR31","doi-asserted-by":"publisher","unstructured":"E. Vincent et al., The second \u2018chime\u2019 speech separation and recognition challenge: datasets, tasks and baselines, in 2013 IEEE International Conference on Acoustics, Speech and Signal Processing (2013), pp. 126\u2013130. https:\/\/doi.org\/10.1109\/ICASSP.2013.6637622.","DOI":"10.1109\/ICASSP.2013.6637622."},{"key":"2106_CR32","doi-asserted-by":"crossref","unstructured":"D. Wang, On ideal binary mask as the computational goal of auditory scene analysis, in Speech Separation by Humans and Machines (Springer, 2005), pp. 181\u2013197","DOI":"10.1007\/0-387-22794-6_12"},{"key":"2106_CR33","doi-asserted-by":"publisher","first-page":"13","DOI":"10.1016\/j.specom.2014.02.001","volume":"60","author":"B Xia","year":"2014","unstructured":"B. Xia, C. Bao, Wiener filtering based speech enhancement with weighted denoising auto-encoder and noise classification. Speech Commun. 60, 13\u201329 (2014). https:\/\/doi.org\/10.1016\/j.specom.2014.02.001","journal-title":"Speech Commun."},{"key":"2106_CR34","doi-asserted-by":"crossref","unstructured":"K. Yamamoto et al., Predicting speech intelligibility using a Gammachirp envelope distortion index based on the signal-to-distortion ratio, in INTERSPEECH (2017), pp. 2949\u20132953","DOI":"10.21437\/Interspeech.2017-170"},{"key":"2106_CR35","doi-asserted-by":"publisher","first-page":"4559","DOI":"10.1121\/1.2916590","volume":"123","author":"S Zahorian","year":"2008","unstructured":"S. Zahorian, H. Hu, A spectral\/temporal method for robust fundamental frequency tracking. J. Acoust. Soc. Am. 123, 4559\u20134571 (2008). https:\/\/doi.org\/10.1121\/1.2916590","journal-title":"J. Acoust. Soc. Am."},{"key":"2106_CR36","doi-asserted-by":"publisher","unstructured":"A. Zehtabian et al., A novel speech enhancement approach based on singular value decomposition and genetic algorithm, in IEEE International Conference of Soft Computing and Pattern Recognition (IEEE, 2010), pp. 430\u2013435. https:\/\/doi.org\/10.1109\/SOCPAR.2010.5686627.","DOI":"10.1109\/SOCPAR.2010.5686627."}],"container-title":["Circuits, Systems, and Signal Processing"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/link.springer.com\/content\/pdf\/10.1007\/s00034-022-02106-3.pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/link.springer.com\/article\/10.1007\/s00034-022-02106-3\/fulltext.html","content-type":"text\/html","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/link.springer.com\/content\/pdf\/10.1007\/s00034-022-02106-3.pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2022,10,20]],"date-time":"2022-10-20T18:19:18Z","timestamp":1666289958000},"score":1,"resource":{"primary":{"URL":"https:\/\/link.springer.com\/10.1007\/s00034-022-02106-3"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2022,7,25]]},"references-count":36,"journal-issue":{"issue":"12","published-print":{"date-parts":[[2022,12]]}},"alternative-id":["2106"],"URL":"https:\/\/doi.org\/10.1007\/s00034-022-02106-3","relation":{},"ISSN":["0278-081X","1531-5878"],"issn-type":[{"type":"print","value":"0278-081X"},{"type":"electronic","value":"1531-5878"}],"subject":[],"published":{"date-parts":[[2022,7,25]]},"assertion":[{"value":"25 July 2021","order":1,"name":"received","label":"Received","group":{"name":"ArticleHistory","label":"Article History"}},{"value":"28 June 2022","order":2,"name":"revised","label":"Revised","group":{"name":"ArticleHistory","label":"Article History"}},{"value":"30 June 2022","order":3,"name":"accepted","label":"Accepted","group":{"name":"ArticleHistory","label":"Article History"}},{"value":"25 July 2022","order":4,"name":"first_online","label":"First Online","group":{"name":"ArticleHistory","label":"Article History"}},{"order":1,"name":"Ethics","group":{"name":"EthicsHeading","label":"Declarations"}},{"value":"The author(s) declare that there is no conflict of interest.","order":2,"name":"Ethics","group":{"name":"EthicsHeading","label":"Conflict of interests"}},{"value":"Custom code.","order":3,"name":"Ethics","group":{"name":"EthicsHeading","label":"Code availability"}}]}}