{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,3,2]],"date-time":"2026-03-02T21:46:06Z","timestamp":1772487966661,"version":"3.50.1"},"reference-count":40,"publisher":"Springer Science and Business Media LLC","issue":"2","license":[{"start":{"date-parts":[[2019,10,24]],"date-time":"2019-10-24T00:00:00Z","timestamp":1571875200000},"content-version":"tdm","delay-in-days":0,"URL":"http:\/\/www.springer.com\/tdm"},{"start":{"date-parts":[[2019,10,24]],"date-time":"2019-10-24T00:00:00Z","timestamp":1571875200000},"content-version":"vor","delay-in-days":0,"URL":"http:\/\/www.springer.com\/tdm"}],"content-domain":{"domain":["link.springer.com"],"crossmark-restriction":false},"short-container-title":["Wireless Pers Commun"],"published-print":{"date-parts":[[2020,3]]},"DOI":"10.1007\/s11277-019-06902-0","type":"journal-article","created":{"date-parts":[[2019,10,25]],"date-time":"2019-10-25T18:31:21Z","timestamp":1572028281000},"page":"1073-1087","update-policy":"https:\/\/doi.org\/10.1007\/springer_crossmark_policy","source":"Crossref","is-referenced-by-count":9,"title":["Speech Intelligibility Based Enhancement System Using Modified Deep Neural Network and Adaptive Multi-band Spectral Subtraction"],"prefix":"10.1007","volume":"111","author":[{"ORCID":"https:\/\/orcid.org\/0000-0002-7964-7485","authenticated-orcid":false,"given":"Tusar Kanti","family":"Dash","sequence":"first","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Sandeep Singh","family":"Solanki","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"297","published-online":{"date-parts":[[2019,10,24]]},"reference":[{"issue":"7","key":"6902_CR1","doi-asserted-by":"publisher","first-page":"588","DOI":"10.1016\/j.specom.2006.12.006","volume":"49","author":"Y Hu","year":"2007","unstructured":"Hu, Y., & Loizou, P. C. (2007). Subjective comparison and evaluation of speech enhancement algorithms. Speech Communication,49(7), 588\u2013601.","journal-title":"Speech Communication"},{"key":"6902_CR2","first-page":"588","volume":"49","author":"P Loizou","year":"2017","unstructured":"Loizou, P. (2017). NOIZEUS: A noisy speech corpus for evaluation of speech enhancement algorithms. Speech Communication, 49, 588\u2013601.","journal-title":"Speech Communication"},{"issue":"1","key":"6902_CR3","doi-asserted-by":"publisher","first-page":"229","DOI":"10.1109\/TASL.2007.911054","volume":"16","author":"Y Hu","year":"2008","unstructured":"Hu, Y., & Loizou, P. C. (2008). Evaluation of objective quality measures for speech enhancement. IEEE Transactions on Audio, Speech and Language Processing,16(1), 229\u2013238.","journal-title":"IEEE Transactions on Audio, Speech and Language Processing"},{"issue":"5","key":"6902_CR4","doi-asserted-by":"publisher","first-page":"845","DOI":"10.1109\/TSA.2005.851927","volume":"13","author":"R Martin","year":"2005","unstructured":"Martin, R. (2005). Speech enhancement based on minimum mean-square error estimation and supergaussian priors. IEEE Transactions on Speech and Audio Processing,13(5), 845\u2013856.","journal-title":"IEEE Transactions on Speech and Audio Processing"},{"key":"6902_CR5","first-page":"1110","volume":"2005","author":"T Lotter","year":"2005","unstructured":"Lotter, T., & Vary, P. (2005). Speech enhancement by MAP spectral amplitude estimation using a super-Gaussian speech model. EURASIP Journal on Applied Signal Processing,2005, 1110\u20131126.","journal-title":"EURASIP Journal on Applied Signal Processing"},{"issue":"5","key":"6902_CR6","doi-asserted-by":"publisher","first-page":"857","DOI":"10.1109\/TSA.2005.851929","volume":"13","author":"PC Loizou","year":"2005","unstructured":"Loizou, P. C. (2005). Speech enhancement based on perceptually motivated Bayesian estimators of the magnitude spectrum. IEEE Transactions on Speech and Audio Processing,13(5), 857\u2013869.","journal-title":"IEEE Transactions on Speech and Audio Processing"},{"issue":"1","key":"6902_CR7","doi-asserted-by":"publisher","first-page":"47","DOI":"10.1109\/TASL.2010.2045180","volume":"19","author":"PC Loizou","year":"2011","unstructured":"Loizou, P. C., & Kim, G. (2011). Reasons why current speech-enhancement algorithms do not improve speech intelligibility and) suggested solutions. IEEE Transactions on Audio, Speech and Language Processing,19(1), 47\u201356.","journal-title":"IEEE Transactions on Audio, Speech and Language Processing"},{"issue":"5","key":"6902_CR8","doi-asserted-by":"publisher","first-page":"870","DOI":"10.1109\/TSA.2005.851940","volume":"13","author":"I Cohen","year":"2005","unstructured":"Cohen, I. (2005). Relaxed statistical model for speech enhancement and a priori SNR estimation. IEEE Transactions on Speech and Audio Processing,13(5), 870\u2013881.","journal-title":"IEEE Transactions on Speech and Audio Processing"},{"issue":"8","key":"6902_CR9","doi-asserted-by":"publisher","first-page":"927","DOI":"10.1016\/j.specom.2005.12.002","volume":"48","author":"Y Ghanbari","year":"2006","unstructured":"Ghanbari, Y., & Karami-Mollaei, M. R. (2006). A new approach for speech enhancement based on the adaptive thresholding of the wavelet packets. Speech Communication,48(8), 927\u2013940.","journal-title":"Speech Communication"},{"issue":"10","key":"6902_CR10","doi-asserted-by":"publisher","first-page":"2140","DOI":"10.1109\/TASL.2013.2270369","volume":"21","author":"N Mohammadiha","year":"2013","unstructured":"Mohammadiha, N., Smaragdis, P., & Leijon, A. (2013). Supervised and unsupervised speech enhancement using nonnegative matrix factorization. IEEE Transactions on Audio, Speech and Language Processing,21(10), 2140\u20132151.","journal-title":"IEEE Transactions on Audio, Speech and Language Processing"},{"issue":"3","key":"6902_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. (2005). Speech enhancement using super-Gaussian speech models and noncausal a priori SNR estimation. Speech Communication,47(3), 336\u2013350.","journal-title":"Speech Communication"},{"issue":"5","key":"6902_CR12","doi-asserted-by":"publisher","first-page":"549","DOI":"10.1016\/j.specom.2005.09.003","volume":"48","author":"MD Skowronski","year":"2006","unstructured":"Skowronski, M. D., & Harris, J. G. (2006). Applied principles of clear and Lombard speech for automated intelligibility enhancement in noisy environments. Speech Communication,48(5), 549\u2013558.","journal-title":"Speech Communication"},{"issue":"7","key":"6902_CR13","doi-asserted-by":"publisher","first-page":"2125","DOI":"10.1109\/TASL.2011.2114881","volume":"19","author":"CH Taal","year":"2011","unstructured":"Taal, C. H., Hendriks, R. C., Heusdens, R., & Jensen, J. (2011). An algorithm for intelligibility prediction of time\u2013frequency weighted noisy speech. IEEE Transactions on Audio, Speech and Language Processing,19(7), 2125\u20132136.","journal-title":"IEEE Transactions on Audio, Speech and Language Processing"},{"issue":"4","key":"6902_CR14","doi-asserted-by":"publisher","first-page":"877","DOI":"10.1109\/TSMCB.2007.895365","volume":"37","author":"Y Shao","year":"2007","unstructured":"Shao, Y., & Chang, C.-H. (2007). A generalized time\u2013frequency subtraction method for robust speech enhancement based on wavelet filter banks modeling of the human auditory system. IEEE Transactions on Systems, Man, and Cybernetics, Part B (Cybernetics),37(4), 877\u2013889.","journal-title":"IEEE Transactions on Systems, Man, and Cybernetics, Part B (Cybernetics)"},{"issue":"12","key":"6902_CR15","doi-asserted-by":"publisher","first-page":"1253","DOI":"10.1016\/j.specom.2009.07.002","volume":"51","author":"Y Lu","year":"2009","unstructured":"Lu, Y., & Cooke, M. (2009). The contribution of changes in F0 and spectral tilt to increased intelligibility of speech produced in noise. Speech Communication,51(12), 1253\u20131262.","journal-title":"Speech Communication"},{"issue":"6","key":"6902_CR16","doi-asserted-by":"publisher","first-page":"2049","DOI":"10.1109\/TASL.2006.876883","volume":"14","author":"JH Hansen","year":"2006","unstructured":"Hansen, J. H., Radhakrishnan, V., & Arehart, K. H. (2006). Speech enhancement based on generalized minimum mean square error estimators and masking properties of the auditory system. IEEE Transactions on Audio, Speech and Language Processing,14(6), 2049\u20132063.","journal-title":"IEEE Transactions on Audio, Speech and Language Processing"},{"issue":"1","key":"6902_CR17","doi-asserted-by":"publisher","first-page":"6","DOI":"10.1109\/TASL.2013.2281574","volume":"22","author":"J Taghia","year":"2014","unstructured":"Taghia, J., & Martin, R. (2014). Objective intelligibility measures based on mutual information for speech subjected to speech enhancement processing. IEEE\/ACM Transactions on Audio, Speech and Language Processing (TASLP),22(1), 6\u201316.","journal-title":"IEEE\/ACM Transactions on Audio, Speech and Language Processing (TASLP)"},{"issue":"1","key":"6902_CR18","doi-asserted-by":"publisher","first-page":"7","DOI":"10.1109\/TASLP.2014.2364452","volume":"23","author":"Y Xu","year":"2015","unstructured":"Xu, Y., Du, J., Dai, L.-R., & Lee, C.-H. (2015). A regression approach to speech enhancement based on deep neural networks. IEEE\/ACM Transactions on Audio, Speech and Language Processing (TASLP),23(1), 7\u201319.","journal-title":"IEEE\/ACM Transactions on Audio, Speech and Language Processing (TASLP)"},{"issue":"8","key":"6902_CR19","doi-asserted-by":"publisher","first-page":"2080","DOI":"10.1109\/TASL.2010.2041116","volume":"18","author":"G Kim","year":"2010","unstructured":"Kim, G., & Loizou, P. C. (2010). Improving speech intelligibility in noise using environment-optimized algorithms. IEEE Transactions on Audio, Speech and Language Processing,18(8), 2080\u20132090.","journal-title":"IEEE Transactions on Audio, Speech and Language Processing"},{"issue":"2","key":"6902_CR20","doi-asserted-by":"publisher","first-page":"619","DOI":"10.1016\/j.csl.2013.03.005","volume":"28","author":"E Jokinen","year":"2014","unstructured":"Jokinen, E., Takanen, M., Vainio, M., & Alku, P. (2014). An adaptive post-filtering method producing an artificial Lombard-like effect for intelligibility enhancement of narrowband telephone speech. Computer Speech & Language,28(2), 619\u2013628.","journal-title":"Computer Speech & Language"},{"issue":"5","key":"6902_CR21","doi-asserted-by":"publisher","first-page":"1035","DOI":"10.1109\/TASL.2013.2244089","volume":"21","author":"PN Petkov","year":"2013","unstructured":"Petkov, P. N., Henter, G. E., & Kleijn, W. B. (2013). Maximizing phoneme recognition accuracy for enhanced speech intelligibility in noise. IEEE Transactions on Audio, Speech and Language Processing,21(5), 1035\u20131045.","journal-title":"IEEE Transactions on Audio, Speech and Language Processing"},{"key":"6902_CR22","doi-asserted-by":"publisher","first-page":"112","DOI":"10.1016\/j.specom.2015.10.003","volume":"76","author":"Yu Tsao","year":"2016","unstructured":"Tsao, Yu., & Lai, Y.-H. (2016). Generalized maximum a posteriori spectral amplitude estimation for speech enhancement. Speech Communication,76, 112\u2013126.","journal-title":"Speech Communication"},{"key":"6902_CR23","doi-asserted-by":"publisher","first-page":"109","DOI":"10.1016\/j.bspc.2015.09.007","volume":"24","author":"F Chen","year":"2016","unstructured":"Chen, F. (2016). Predicting the intelligibility of noise-corrupted speech non-intrusively by across-band envelope correlation. Biomedical Signal Processing and Control,24, 109\u2013113.","journal-title":"Biomedical Signal Processing and Control"},{"issue":"10","key":"6902_CR24","doi-asserted-by":"publisher","first-page":"1808","DOI":"10.1109\/TASLP.2016.2585864","volume":"24","author":"T-C Zoril\u0103","year":"2016","unstructured":"Zoril\u0103, T.-C., Stylianou, Y., Ishihara, T., & Akamine, M. (2016). Near and far field speech-in-noise intelligibility improvements based on a time\u2013frequency energy reallocation approach. IEEE\/ACM Transactions on Audio, Speech, and Language Processing,24(10), 1808\u20131818.","journal-title":"IEEE\/ACM Transactions on Audio, Speech, and Language Processing"},{"key":"6902_CR25","doi-asserted-by":"publisher","first-page":"183","DOI":"10.1016\/j.heares.2016.11.012","volume":"344","author":"T Goehring","year":"2017","unstructured":"Goehring, T., Bolner, F., Monaghan, J. J. M., Dijk, B. V., Zarowski, A., & Bleeck, S. (2017). Speech enhancement based on neural networks improves speech intelligibility in noise for cochlear implant users. Hearing Research,344, 183\u2013194.","journal-title":"Hearing Research"},{"issue":"1","key":"6902_CR26","doi-asserted-by":"publisher","first-page":"153","DOI":"10.1109\/TASLP.2016.2628641","volume":"25","author":"M Kolb\u00e6k","year":"2017","unstructured":"Kolb\u00e6k, M., Tan, Z.-H., & Jensen, J. (2017). Speech intelligibility potential of general and specialized deep neural network based speech enhancement systems. IEEE\/ACM Transactions on Audio, Speech, and Language Processing,25(1), 153\u2013167.","journal-title":"IEEE\/ACM Transactions on Audio, Speech, and Language Processing"},{"key":"6902_CR27","doi-asserted-by":"publisher","DOI":"10.1201\/b14529","volume-title":"Speech enhancement: Theory and practice","author":"PC Loizou","year":"2013","unstructured":"Loizou, P. C. (2013). Speech enhancement: Theory and practice. New York: CRC Press."},{"issue":"6","key":"6902_CR28","doi-asserted-by":"publisher","first-page":"641","DOI":"10.1049\/iet-spr.2015.0182","volume":"10","author":"S Samui","year":"2016","unstructured":"Samui, S., Chakrabarti, I., & Ghosh, S. K. (2016). Improved single channel phase-aware speech enhancement technique for low signal-to-noise ratio signal. IET Signal Processing,10(6), 641\u2013650.","journal-title":"IET Signal Processing"},{"key":"6902_CR29","doi-asserted-by":"publisher","first-page":"20","DOI":"10.1186\/s41074-017-0030-7","volume":"9","author":"Y Ozaki","year":"2017","unstructured":"Ozaki, Y., Yano, M., & Onishi, M. (2017). Effective hyperparameter optimization using Nelder-Mead method in deep learning. IPSJ Transactions on Computer Vision and Applications, 9, 20.","journal-title":"IPSJ Transactions on Computer Vision and Applications"},{"key":"6902_CR30","doi-asserted-by":"publisher","DOI":"10.1016\/j.csl.2017.01.013","volume-title":"Multi-microphone speech recognition integrating beamforming, robust feature extraction, and advanced DNN\/RNN backend","author":"T Hori","year":"2017","unstructured":"Hori, T., Chen, Z., Erdogan, H., Hershey, J. R., Roux, J. L., Mitra, V., et al. (2017). Multi-microphone speech recognition integrating beamforming, robust feature extraction, and advanced DNN\/RNN backend. Berlin: Springer."},{"key":"6902_CR31","unstructured":"An efficient MFCC extraction method in speech recognition"},{"key":"6902_CR32","doi-asserted-by":"crossref","unstructured":"Xu, Y., Du, J., Dai, L.-R., & Lee, C.-H. (2014). Global variance equalization for improving deep neural network based speech enhancement. In IEEE China summit & international conference on signal and information processing (China SIP), 2014 (pp. 71\u201375). IEEE.","DOI":"10.1109\/ChinaSIP.2014.6889204"},{"key":"6902_CR33","doi-asserted-by":"publisher","first-page":"351","DOI":"10.1016\/0167-6393(90)90010-7","volume":"9","author":"V Zue","year":"1990","unstructured":"Zue, V., Seneff, S., & Glass, J. (1990). Speech database development at MIT: Timit and beyond. Speech Communication, 9(4), 351\u2013356.","journal-title":"Speech Communication"},{"key":"6902_CR34","doi-asserted-by":"crossref","unstructured":"Kavalekalam, S. M., Christensen, M. G., Gran, F., & Boldt, J. B. (2016). Kalman filter for speech enhancement in cocktail party scenarios using a codebook-based approach. In IEEE international conference on acoustics, speech and signal processing (ICASSP), 2016 (pp. 191\u2013195). IEEE.","DOI":"10.1109\/ICASSP.2016.7471663"},{"key":"6902_CR35","doi-asserted-by":"crossref","unstructured":"Kirubagari, B., Palanivel, S., & Subathra, N. (2014). Speech enhancement using minimum mean square error filter and spectral subtraction filter. In International conference on information communication and embedded systems (ICICES), 2014 (pp. 1\u20137). IEEE.","DOI":"10.1109\/ICICES.2014.7034042"},{"key":"6902_CR36","doi-asserted-by":"publisher","first-page":"334","DOI":"10.1109\/TSA.2003.814458","volume":"11","author":"Y Hu","year":"2003","unstructured":"Hu, Y., & Loizou, P. C. (2003). A generalized subspace approach for enhancing speech corrupted by colored noise. IEEE Transactions on Speech and Audio Processing, 11(4), 334\u2013341.","journal-title":"IEEE Transactions on Speech and Audio Processing"},{"key":"6902_CR37","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. (1985). Speech enhancement using a minimum mean-square error log-spectral amplitude estimator. IEEE Transactions on Acoustics, Speech, and Signal Processing, 33(2), 443\u2013445.","journal-title":"IEEE Transactions on Acoustics, Speech, and Signal Processing"},{"issue":"2","key":"6902_CR38","doi-asserted-by":"publisher","first-page":"141","DOI":"10.1007\/s11265-015-1025-1","volume":"82","author":"B Liu","year":"2016","unstructured":"Liu, B., Tao, J., Wen, Z., & Mo, F. (2016). Speech enhancement based on analysis-synthesis framework with improved parameter domain enhancement. Journal of Signal Processing Systems,82(2), 141\u2013150.","journal-title":"Journal of Signal Processing Systems"},{"key":"6902_CR39","unstructured":"Hirsch, H. G., & Pearce, D. (2000). The Aurora experimental framework for the performance evaluation of speech recognition systems under noisy conditions. In ASR2000-automatic speech recognition: Challenges for the new Millenium ISCA tutorial and research workshop (ITRW)."},{"key":"6902_CR40","doi-asserted-by":"crossref","unstructured":"Rix, A. W., Beerends, J. G., Hollier, M. P., & Hekstra, A. P. (2001). 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, pp. 749\u2013752).","DOI":"10.1109\/ICASSP.2001.941023"}],"container-title":["Wireless Personal Communications"],"original-title":[],"language":"en","link":[{"URL":"http:\/\/link.springer.com\/content\/pdf\/10.1007\/s11277-019-06902-0.pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"text-mining"},{"URL":"http:\/\/link.springer.com\/article\/10.1007\/s11277-019-06902-0\/fulltext.html","content-type":"text\/html","content-version":"vor","intended-application":"text-mining"},{"URL":"http:\/\/link.springer.com\/content\/pdf\/10.1007\/s11277-019-06902-0.pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2020,10,22]],"date-time":"2020-10-22T23:14:48Z","timestamp":1603408488000},"score":1,"resource":{"primary":{"URL":"http:\/\/link.springer.com\/10.1007\/s11277-019-06902-0"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2019,10,24]]},"references-count":40,"journal-issue":{"issue":"2","published-print":{"date-parts":[[2020,3]]}},"alternative-id":["6902"],"URL":"https:\/\/doi.org\/10.1007\/s11277-019-06902-0","relation":{},"ISSN":["0929-6212","1572-834X"],"issn-type":[{"value":"0929-6212","type":"print"},{"value":"1572-834X","type":"electronic"}],"subject":[],"published":{"date-parts":[[2019,10,24]]},"assertion":[{"value":"24 October 2019","order":1,"name":"first_online","label":"First Online","group":{"name":"ArticleHistory","label":"Article History"}}]}}