{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,5,2]],"date-time":"2026-05-02T06:38:03Z","timestamp":1777703883558,"version":"3.51.4"},"reference-count":57,"publisher":"SAGE Publications","issue":"4","license":[{"start":{"date-parts":[[2019,9,11]],"date-time":"2019-09-11T00:00:00Z","timestamp":1568160000000},"content-version":"tdm","delay-in-days":0,"URL":"https:\/\/journals.sagepub.com\/page\/policies\/text-and-data-mining-license"}],"content-domain":{"domain":["journals.sagepub.com"],"crossmark-restriction":true},"short-container-title":["Journal of Intelligent &amp; Fuzzy Systems"],"published-print":{"date-parts":[[2019,10,25]]},"abstract":"<jats:p>In real-world situation, speech signals reaching our ears are usually degraded by the background noise. These distortions are detrimental to the speech quality and intelligibility and also cause a serious problem to many speech-related applications, such as automatic speech recognition and speaker identification. In order to deal with the background noise distortions, we propose a strategy to enhance the degraded speech in this paper, where speech enhancement is conducted using supervised deep neural network models. The models are trained to learn a mapping from the features of noisy speech to estimate the ideal-ratio mask (IRM). The estimated IRM is then applied to the noisy speech in order to obtain an enhanced version of the degraded speech. The mean square error (MSE) is used as an objective cost function. Additionally, Global Variance Equalization is performed as a post-processing step to equalize variances of the features. Systematic evaluations and comparisons show that the proposed supervised method improves objective metrics of speech quality and intelligibility substantially and significantly outperforms the competing and baseline speech enhancement methods. Finally, the proposed method is examined in speaker identification task in noisy situations. The proposed method leads to the highest speaker identification rates when compare to the competing and baseline speech enhancement methods.<\/jats:p>","DOI":"10.3233\/jifs-190047","type":"journal-article","created":{"date-parts":[[2019,9,13]],"date-time":"2019-09-13T11:42:55Z","timestamp":1568374975000},"page":"5187-5201","update-policy":"https:\/\/doi.org\/10.1177\/sage-journals-update-policy","source":"Crossref","is-referenced-by-count":14,"title":["Supervised speech enhancement based on deep neural network"],"prefix":"10.1177","volume":"37","author":[{"given":"Nasir","family":"Saleem","sequence":"first","affiliation":[{"name":"Department of Electrical Engineering, FET, Gomal University, Dera Ismail Khan, Pakistan"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Muhammad Irfan","family":"Khattak","sequence":"additional","affiliation":[{"name":"Department of Electrical Engineering, University of Engineering &amp; Technology, Peshawar, Kohat Campus, Pakistan"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Abdul Baser","family":"Qazi","sequence":"additional","affiliation":[{"name":"Department of Software Engineering, Bahria University, Islamabad, Pakistan"}],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"179","published-online":{"date-parts":[[2019,9,11]]},"reference":[{"key":"e_1_3_1_2_2","doi-asserted-by":"publisher","DOI":"10.1109\/TASSP.1979.1163209"},{"key":"e_1_3_1_3_2","unstructured":"ScalartP. Speech enhancement based on a priori signal to noise estimation IEEE International Conference on Acoustics Speech and Signal Processing (1996) ICASSP96."},{"key":"e_1_3_1_4_2","doi-asserted-by":"publisher","DOI":"10.1109\/TASSP.1985.1164550"},{"key":"e_1_3_1_5_2","first-page":"1","article-title":"Noise Reduction Based on Soft Masks by Incorporating SNR Uncertainty in Frequency Domain","author":"Saleem N.","year":"2017","unstructured":"SaleemN. and IrfanM., Noise Reduction Based on Soft Masks by Incorporating SNR Uncertainty in Frequency Domain, Circuits, Systems, and Signal Processing (2017), 1\u201322.","journal-title":"Circuits, Systems, and Signal Processing"},{"key":"e_1_3_1_6_2","doi-asserted-by":"publisher","DOI":"10.1109\/TSA.2005.851940"},{"key":"e_1_3_1_7_2","doi-asserted-by":"publisher","DOI":"10.1109\/LSP.2004.833478"},{"key":"e_1_3_1_8_2","doi-asserted-by":"publisher","DOI":"10.1109\/97.1001645"},{"key":"e_1_3_1_9_2","doi-asserted-by":"publisher","DOI":"10.1109\/89.397090"},{"key":"e_1_3_1_10_2","doi-asserted-by":"publisher","DOI":"10.1109\/LSP.2004.824017"},{"key":"e_1_3_1_11_2","doi-asserted-by":"publisher","DOI":"10.1049\/iet-spr:20070008"},{"key":"e_1_3_1_12_2","doi-asserted-by":"publisher","DOI":"10.1109\/TASL.2013.2270369"},{"key":"e_1_3_1_13_2","doi-asserted-by":"publisher","DOI":"10.1016\/j.csl.2008.11.001"},{"key":"e_1_3_1_14_2","doi-asserted-by":"publisher","DOI":"10.1109\/TASL.2007.901310"},{"key":"e_1_3_1_15_2","doi-asserted-by":"publisher","DOI":"10.1109\/TASL.2013.2263144"},{"key":"e_1_3_1_16_2","doi-asserted-by":"crossref","unstructured":"WangY. and WangD. A structure-preserving training target for supervised speech separation. (ICASSP) 2014.","DOI":"10.1109\/ICASSP.2014.6854777"},{"key":"e_1_3_1_17_2","doi-asserted-by":"crossref","unstructured":"WangD. On ideal binary mask as the computational goal of auditory scene analysis Speech separation by humans and machines (2005) 181\u2013197.","DOI":"10.1007\/0-387-22794-6_12"},{"key":"e_1_3_1_18_2","article-title":"An analysis of a noise reduction neural network, International Conference on the Acoustics, Speech, and Signal Processing","author":"Tamura S.","year":"1989","unstructured":"TamuraS., An analysis of a noise reduction neural network, International Conference on the Acoustics, Speech, and Signal Processing, ICASSP-89. 1989.","journal-title":"ICASSP-89"},{"key":"e_1_3_1_19_2","article-title":"Noise reduction using connectionist models, International Conference on the Acoustics, Speech, and Signal Processing","author":"Tamura S.i.","year":"1988","unstructured":"TamuraS.i. and WaibelA., Noise reduction using connectionist models, International Conference on the Acoustics, Speech, and Signal Processing, ICASSP-88. 1988.","journal-title":"ICASSP-88"},{"key":"e_1_3_1_20_2","doi-asserted-by":"crossref","DOI":"10.1109\/ICASSP.1994.389720","article-title":"Compernolle, A family of MLP based nonlinear spectral estimators for noise reduction, IEEE International Conference on Acoustics, Speech, and Signal Processing","author":"Xie F.","year":"1994","unstructured":"XieF. and VanD., Compernolle, A family of MLP based nonlinear spectral estimators for noise reduction, IEEE International Conference on Acoustics, Speech, and Signal Processing, ICASSP-94., 1994.","journal-title":"ICASSP-94."},{"key":"e_1_3_1_21_2","doi-asserted-by":"publisher","DOI":"10.1121\/1.1610463"},{"key":"e_1_3_1_22_2","doi-asserted-by":"publisher","DOI":"10.1016\/j.specom.2004.03.006"},{"key":"e_1_3_1_23_2","doi-asserted-by":"publisher","DOI":"10.1109\/TASL.2008.2010633"},{"key":"e_1_3_1_24_2","doi-asserted-by":"publisher","DOI":"10.1121\/1.3184603"},{"key":"e_1_3_1_25_2","doi-asserted-by":"crossref","unstructured":"ChenJ. and WangD. DNN based mask estimation for supervised speech separation Audio source separation (2018) 207\u2013235.","DOI":"10.1007\/978-3-319-73031-8_9"},{"key":"e_1_3_1_26_2","doi-asserted-by":"publisher","DOI":"10.1121\/1.2363929"},{"key":"e_1_3_1_27_2","doi-asserted-by":"publisher","DOI":"10.1121\/1.2832617"},{"key":"e_1_3_1_28_2","doi-asserted-by":"publisher","DOI":"10.1121\/1.3083233"},{"issue":"4","key":"e_1_3_1_29_2","first-page":"36","article-title":"A novel binary mask estimation based on spectral subtraction gain-induced distortions for improved speech intelligibility and quality. University of Engineering and Technology Taxila","volume":"20","author":"Saleem N.","year":"2015","unstructured":"SaleemN., ShafiM., MustafaE. and NawazA., A novel binary mask estimation based on spectral subtraction gain-induced distortions for improved speech intelligibility and quality. University of Engineering and Technology Taxila, Technical Journal 20(4) (2015), 36.","journal-title":"Technical Journal"},{"key":"e_1_3_1_30_2","doi-asserted-by":"publisher","DOI":"10.1121\/1.3179673"},{"key":"e_1_3_1_31_2","doi-asserted-by":"crossref","unstructured":"HummersoneC. StokesT. and BrookesT. On the ideal ratio mask as the goal of computational auditory scene analysis Blind source separation (2014) 349\u2013368.","DOI":"10.1007\/978-3-642-55016-4_12"},{"key":"e_1_3_1_32_2","article-title":"Ideal ratio mask estimation using deep neural networks for robust speech recognition","author":"Narayanan A.","year":"2013","unstructured":"NarayananA. and WangD., Ideal ratio mask estimation using deep neural networks for robust speech recognition, IEEE International Conference on the Acoustics, Speech and Signal Processing (ICASSP), 2013.","journal-title":"IEEE International Conference on the Acoustics, Speech and Signal Processing (ICASSP)"},{"key":"e_1_3_1_33_2","doi-asserted-by":"publisher","DOI":"10.1016\/j.specom.2006.09.003"},{"key":"e_1_3_1_34_2","doi-asserted-by":"publisher","DOI":"10.1109\/TASLP.2014.2352935"},{"key":"e_1_3_1_35_2","doi-asserted-by":"publisher","DOI":"10.1016\/j.csl.2017.10.004"},{"key":"e_1_3_1_36_2","doi-asserted-by":"publisher","DOI":"10.1109\/ACCESS.2017.2766675"},{"key":"e_1_3_1_37_2","doi-asserted-by":"publisher","DOI":"10.1109\/TASL.2013.2250961"},{"key":"e_1_3_1_38_2","doi-asserted-by":"publisher","DOI":"10.1121\/1.399423"},{"key":"e_1_3_1_39_2","doi-asserted-by":"publisher","DOI":"10.1109\/89.326616"},{"key":"e_1_3_1_40_2","article-title":"Robust speaker identification using auditory features and computational auditory scene analysis, IEEE International Conference on the Acoustics, Speech and Signal Processing","author":"Shao Y.","year":"2008","unstructured":"ShaoY. and WangD., Robust speaker identification using auditory features and computational auditory scene analysis, IEEE International Conference on the Acoustics, Speech and Signal Processing, ICASSP 2008.","journal-title":"ICASSP"},{"key":"e_1_3_1_41_2","doi-asserted-by":"publisher","DOI":"10.1109\/TASL.2012.2186803"},{"key":"e_1_3_1_42_2","doi-asserted-by":"publisher","DOI":"10.1109\/TASL.2006.876717"},{"key":"e_1_3_1_43_2","doi-asserted-by":"publisher","DOI":"10.1109\/TASLP.2014.2359159"},{"key":"e_1_3_1_44_2","doi-asserted-by":"publisher","DOI":"10.1109\/TSA.2005.845805"},{"key":"e_1_3_1_45_2","article-title":"Spectral conversion based on maximum likelihood estimation considering global variance of converted parameter","author":"Toda T.","year":"2005","unstructured":"TodaT., BlackA.W. and TokudaK., Spectral conversion based on maximum likelihood estimation considering global variance of converted parameter, IEEE International Conference on Acoustics, Speech, and Signal Processing, Proceedings. (ICASSP\u201905). 2005.","journal-title":"IEEE International Conference on Acoustics, Speech, and Signal Processing, Proceedings. (ICASSP\u201905)"},{"key":"e_1_3_1_46_2","doi-asserted-by":"publisher","DOI":"10.1109\/TAU.1969.1162058"},{"key":"e_1_3_1_47_2","unstructured":"HirschH.-G. and PearceD. The Aurora experimental framework for the performance evaluation of speech recognition systems under noisy conditions. ASR-Automatic Speech Recognition: Challenges for the new Millenium ISCA Tutorial and Research Workshop (2000)."},{"key":"e_1_3_1_48_2","doi-asserted-by":"publisher","DOI":"10.1109\/TASLP.2014.2364452"},{"key":"e_1_3_1_49_2","first-page":"1","article-title":"Enhancement of speech using deep neural network with discrete cosine transform","author":"Rashmirekha R.","unstructured":"RashmirekhaR. and MohnatyM.N., Enhancement of speech using deep neural network with discrete cosine transform, Journal of Intelligent & Fuzzy Systems Preprint: 1\u20138.","journal-title":"Journal of Intelligent & Fuzzy Systems Preprint"},{"key":"e_1_3_1_50_2","doi-asserted-by":"publisher","DOI":"10.1109\/TASL.2011.2114881"},{"key":"e_1_3_1_51_2","unstructured":"RixA.W. BeerendsJ.G. HollierM.P. and HekstraA.P. Perceptual evaluation of speech quality (PESQ)-a new method for speech quality assessment of telephone networks and codecs IEEE International Conference on the Acoustics Speech and Signal Processing 2001. Proceedings.(ICASSP\u201901). 2001."},{"key":"e_1_3_1_52_2","doi-asserted-by":"publisher","DOI":"10.1109\/IWAENC.2016.7602951"},{"key":"e_1_3_1_53_2","doi-asserted-by":"publisher","DOI":"10.1109\/TASL.2007.911054"},{"key":"e_1_3_1_54_2","doi-asserted-by":"publisher","DOI":"10.1109\/TASL.2010.2092767"},{"key":"e_1_3_1_55_2","doi-asserted-by":"publisher","DOI":"10.1109\/89.365379"},{"key":"e_1_3_1_56_2","doi-asserted-by":"publisher","DOI":"10.1109\/TASSP.1980.1163420"},{"key":"e_1_3_1_57_2","doi-asserted-by":"publisher","DOI":"10.1016\/0167-6393(95)00009-D"},{"key":"e_1_3_1_58_2","doi-asserted-by":"publisher","DOI":"10.1109\/TASL.2007.899278"}],"container-title":["Journal of Intelligent &amp; Fuzzy Systems"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/journals.sagepub.com\/doi\/pdf\/10.3233\/JIFS-190047","content-type":"application\/pdf","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/journals.sagepub.com\/doi\/full-xml\/10.3233\/JIFS-190047","content-type":"application\/xml","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/journals.sagepub.com\/doi\/pdf\/10.3233\/JIFS-190047","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2026,4,29]],"date-time":"2026-04-29T09:39:51Z","timestamp":1777455591000},"score":1,"resource":{"primary":{"URL":"https:\/\/journals.sagepub.com\/doi\/10.3233\/JIFS-190047"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2019,9,11]]},"references-count":57,"journal-issue":{"issue":"4","published-print":{"date-parts":[[2019,10,25]]}},"alternative-id":["10.3233\/JIFS-190047"],"URL":"https:\/\/doi.org\/10.3233\/jifs-190047","relation":{},"ISSN":["1064-1246","1875-8967"],"issn-type":[{"value":"1064-1246","type":"print"},{"value":"1875-8967","type":"electronic"}],"subject":[],"published":{"date-parts":[[2019,9,11]]}}}