{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2025,9,9]],"date-time":"2025-09-09T21:43:16Z","timestamp":1757454196475,"version":"3.37.3"},"reference-count":63,"publisher":"Springer Science and Business Media LLC","issue":"22","license":[{"start":{"date-parts":[[2019,7,25]],"date-time":"2019-07-25T00:00:00Z","timestamp":1564012800000},"content-version":"tdm","delay-in-days":0,"URL":"http:\/\/www.springer.com\/tdm"},{"start":{"date-parts":[[2019,7,25]],"date-time":"2019-07-25T00:00:00Z","timestamp":1564012800000},"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":["Multimed Tools Appl"],"published-print":{"date-parts":[[2019,11]]},"DOI":"10.1007\/s11042-019-08032-y","type":"journal-article","created":{"date-parts":[[2019,7,25]],"date-time":"2019-07-25T22:02:11Z","timestamp":1564092131000},"page":"31867-31891","update-policy":"https:\/\/doi.org\/10.1007\/springer_crossmark_policy","source":"Crossref","is-referenced-by-count":6,"title":["Variance based time-frequency mask estimation for unsupervised speech enhancement"],"prefix":"10.1007","volume":"78","author":[{"ORCID":"https:\/\/orcid.org\/0000-0003-0010-0629","authenticated-orcid":false,"given":"Nasir","family":"Saleem","sequence":"first","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Muhammad Irfan","family":"Khattak","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Gunawan","family":"Witjaksono","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Gulzar","family":"Ahmad","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"297","published-online":{"date-parts":[[2019,7,25]]},"reference":[{"doi-asserted-by":"crossref","unstructured":"Abel A, Hussain A (2015). Cognitively inspired audiovisual speech filtering: towards an intelligent, fuzzy based, multimodal, two-stage speech enhancement system(Vol. 5). Springer","key":"8032_CR1","DOI":"10.1007\/978-3-319-13509-0"},{"issue":"22","key":"8032_CR2","doi-asserted-by":"publisher","first-page":"23661","DOI":"10.1007\/s11042-016-4145-0","volume":"76","author":"AB Aicha","year":"2017","unstructured":"Aicha AB (2017) Noise estimation for speech enhancement algorithms with post-smoothness processor incorporating global posterior SNR. Multimed Tools Appl 76(22):23661\u201323678","journal-title":"Multimed Tools Appl"},{"doi-asserted-by":"crossref","unstructured":"Bao F, Abdulla WH (2018) Noise masking method based on an effective ratio mask estimation in Gammatone channels. APSIPA Transactions on Signal and Information Processing, 7","key":"8032_CR3","DOI":"10.1017\/ATSIP.2018.7"},{"issue":"2","key":"8032_CR4","doi-asserted-by":"publisher","first-page":"113","DOI":"10.1109\/TASSP.1979.1163209","volume":"27","author":"S Boll","year":"1979","unstructured":"Boll S (1979) Suppression of acoustic noise in speech using spectral subtraction. IEEE Trans Acoust Speech Signal Process 27(2):113\u2013120","journal-title":"IEEE Trans Acoust Speech Signal Process"},{"doi-asserted-by":"crossref","unstructured":"Braun S, Kowalczyk K, Habets EA (2015) In Residual noise control using a parametric multichannel Wiener filter, Acoustics, Speech and Signal Processing (ICASSP), 2015 IEEE International Conference on, IEEE; pp 360\u2013364","key":"8032_CR5","DOI":"10.1109\/ICASSP.2015.7177991"},{"issue":"4","key":"8032_CR6","doi-asserted-by":"publisher","first-page":"1158","DOI":"10.1109\/TASL.2011.2172428","volume":"20","author":"N Chatlani","year":"2012","unstructured":"Chatlani N, Soraghan JJ (2012) EMD-based filtering (EMDF) of low-frequency noise for speech enhancement. IEEE Trans Audio Speech Lang Process 20(4):1158\u20131166","journal-title":"IEEE Trans Audio Speech Lang Process"},{"issue":"10","key":"8032_CR7","doi-asserted-by":"publisher","first-page":"1491","DOI":"10.1002\/acs.2781","volume":"31","author":"S Chehrehsa","year":"2017","unstructured":"Chehrehsa S, Moir TJ (2017) Speech and noise power estimation using gamma modeling. International Journal of Adaptive Control and Signal Processing 31(10):1491\u20131502","journal-title":"International Journal of Adaptive Control and Signal Processing"},{"issue":"1","key":"8032_CR8","doi-asserted-by":"publisher","first-page":"12","DOI":"10.1109\/97.988717","volume":"9","author":"I Cohen","year":"2002","unstructured":"Cohen I, Berdugo B (2002) Noise estimation by minima controlled recursive averaging for robust speech enhancement. IEEE Signal processing letters 9(1):12\u201315","journal-title":"IEEE Signal processing letters"},{"issue":"6","key":"8032_CR9","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 (1984) Speech enhancement using a minimum-mean square error short-time spectral amplitude estimator. IEEE Trans Acoust Speech Signal Process 32(6):1109\u20131121","journal-title":"IEEE Trans Acoust Speech Signal Process"},{"issue":"2","key":"8032_CR10","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 Trans Acoust Speech Signal Process 33(2):443\u2013445","journal-title":"IEEE Trans Acoust Speech Signal Process"},{"key":"8032_CR11","doi-asserted-by":"publisher","first-page":"e39880","DOI":"10.4025\/actasciagron.v41i1.39880","volume":"41","author":"LB Ferreira","year":"2019","unstructured":"Ferreira LB, Duarte AB, da Cunha FF, Fernandes Filho EI (2019) Multivariate adaptive regression splines (MARS) applied to daily reference evapotranspiration modeling with limited weather data. Acta Scientiarum Agronomy 41:e39880","journal-title":"Acta Scientiarum Agronomy"},{"key":"8032_CR12","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 JJ, van Dijk B, Zarowski A, Bleeck S (2017) Speech enhancement based on neural networks improves speech intelligibility in noise for cochlear implant users. Hear Res 344:183\u2013194","journal-title":"Hear Res"},{"doi-asserted-by":"crossref","unstructured":"Gogate M, Adeel A, Marxer R, Barker J, Hussain A (2018) Dnn driven speaker independent audio-visual mask estimation for speech separation. arXiv preprint arXiv:1808.00060","key":"8032_CR13","DOI":"10.21437\/Interspeech.2018-2516"},{"unstructured":"Guang-Yan W, Xiao-qun Z, Xia W (2009) Musical noise reduction based on spectral subtraction combined with Wiener filtering for speech communication","key":"8032_CR14"},{"issue":"8","key":"8032_CR15","doi-asserted-by":"publisher","first-page":"799","DOI":"10.1109\/89.966083","volume":"9","author":"H Gustafsson","year":"2001","unstructured":"Gustafsson H, Nordholm SE, Claesson I (2001) Spectral subtraction using reduced delay convolution and adaptive averaging. IEEE transactions on speech and audio processing 9(8):799\u2013807","journal-title":"IEEE transactions on speech and audio processing"},{"key":"8032_CR16","doi-asserted-by":"publisher","first-page":"347","DOI":"10.1016\/j.neucom.2015.06.048","volume":"171","author":"T Han","year":"2016","unstructured":"Han T, Yao H, Sun X, Zhao S, Zhang Y (2016) Unsupervised discovery of crowd activities by saliency-based clustering. Neurocomputing 171:347\u2013361","journal-title":"Neurocomputing"},{"issue":"1","key":"8032_CR17","doi-asserted-by":"publisher","first-page":"045821","DOI":"10.1155\/2007\/45821","volume":"2007","author":"K Hermus","year":"2006","unstructured":"Hermus K, Wambacq P (2006) A review of signal subspace speech enhancement and its application to noise robust speech recognition. EURASIP journal on advances in signal processing 2007(1):045821","journal-title":"EURASIP journal on advances in signal processing"},{"doi-asserted-by":"crossref","unstructured":"Hirsch H-G, Pearce D (2000) In The Aurora experimental framework for the performance evaluation of speech recognition systems under noisy conditions, ASR2000-Automatic Speech Recognition: Challenges for the new Millenium ISCA Tutorial and Research Workshop (ITRW)","key":"8032_CR18","DOI":"10.21437\/ICSLP.2000-743"},{"issue":"4","key":"8032_CR19","doi-asserted-by":"publisher","first-page":"334","DOI":"10.1109\/TSA.2003.814458","volume":"11","author":"Y Hu","year":"2003","unstructured":"Hu Y, Loizou PC (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"},{"issue":"1","key":"8032_CR20","doi-asserted-by":"publisher","first-page":"229","DOI":"10.1109\/TASL.2007.911054","volume":"16","author":"Y Hu","year":"2008","unstructured":"Hu Y, Loizou PC (2008) Evaluation of objective quality measures for speech enhancement. IEEE Trans Audio Speech Lang Process 16(1):229\u2013238","journal-title":"IEEE Trans Audio Speech Lang Process"},{"doi-asserted-by":"crossref","unstructured":"Huang NE, Shen Z, Long SR, Wu MC, Shih HH, Zheng Q, Yen N-C, Tung CC, Liu HH (1998) In The empirical mode decomposition and the Hilbert spectrum for nonlinear and non-stationary time series analysis, Proceedings of the Royal Society of London A: mathematical, physical and engineering sciences, The Royal Society; pp 903\u2013995","key":"8032_CR21","DOI":"10.1098\/rspa.1998.0193"},{"doi-asserted-by":"crossref","unstructured":"Kamath S, Loizou, P. (2002) In A multi-band spectral subtraction method for enhancing speech corrupted by colored noise, ICASSP, pp 44164\u201344164","key":"8032_CR22","DOI":"10.1109\/ICASSP.2002.5745591"},{"issue":"07","key":"8032_CR23","doi-asserted-by":"publisher","first-page":"1858002","DOI":"10.1142\/S0218001418580028","volume":"32","author":"H Li","year":"2018","unstructured":"Li H, Wang Y, Zhao R, Zhang X (2018) An unsupervised two-talker speech separation system based on CASA. Int J Pattern Recognit Artif Intell 32(07):1858002","journal-title":"Int J Pattern Recognit Artif Intell"},{"issue":"3","key":"8032_CR24","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 (1978) All-pole modeling of degraded speech. IEEE Trans Acoust Speech Signal Process 26(3):197\u2013210","journal-title":"IEEE Trans Acoust Speech Signal Process"},{"unstructured":"Liu Z, Wang T. (2016) An Adaptive Image Denoising Algorithm Based on Wavelet Transform and Independent Component Analysis, Sixth International Conference on Intelligent Systems Design and Engineering Applications. IEEE:104\u2013107","key":"8032_CR25"},{"key":"8032_CR26","doi-asserted-by":"publisher","first-page":"588","DOI":"10.1016\/j.specom.2007.05.002","volume":"49","author":"P Loizou","year":"2007","unstructured":"Loizou P (2007) Subjective evaluation and comparison of speech enhancement methods. Speech Commun 49:588\u2013601","journal-title":"Speech Commun"},{"issue":"11","key":"8032_CR27","doi-asserted-by":"publisher","first-page":"1300","DOI":"10.1016\/j.patrec.2007.03.001","volume":"28","author":"C-T Lu","year":"2007","unstructured":"Lu C-T (2007) Reduction of musical residual noise for speech enhancement using masking properties and optimal smoothing. Pattern Recogn Lett 28(11):1300\u20131306","journal-title":"Pattern Recogn Lett"},{"key":"8032_CR28","doi-asserted-by":"publisher","first-page":"249","DOI":"10.1016\/j.apacoust.2013.08.015","volume":"76","author":"C-T Lu","year":"2014","unstructured":"Lu C-T (2014) Noise reduction using three-step gain factor and iterative-directional-median filter. Appl Acoust 76:249\u2013261","journal-title":"Appl Acoust"},{"issue":"5","key":"8032_CR29","doi-asserted-by":"publisher","first-page":"1123","DOI":"10.1109\/TASL.2010.2082531","volume":"19","author":"Y Lu","year":"2011","unstructured":"Lu Y, Loizou PC (2011) Estimators of the magnitude-squared spectrum and methods for incorporating SNR uncertainty. IEEE Trans Audio Speech Lang Process 19(5):1123","journal-title":"IEEE Trans Audio Speech Lang Process"},{"unstructured":"Luo Y, Mesgarani N (2018) TasNet: Surpassing ideal time-frequency masking for speech separation. arXiv preprint arXiv:1809.07454","key":"8032_CR30"},{"issue":"5","key":"8032_CR31","doi-asserted-by":"publisher","first-page":"504","DOI":"10.1109\/89.928915","volume":"9","author":"R Martin","year":"2001","unstructured":"Martin R (2001) Noise power spectral density estimation based on optimal smoothing and minimum statistics. IEEE transactions on speech and audio processing 9(5):504\u2013512","journal-title":"IEEE transactions on speech and audio processing"},{"doi-asserted-by":"crossref","unstructured":"Marxer R, Barker J (2017) Binary Mask Estimation Strategies for Constrained Imputation-Based Speech Enhancement. In INTERSPEECH, pp. 1988\u20131992","key":"8032_CR32","DOI":"10.21437\/Interspeech.2017-1257"},{"doi-asserted-by":"crossref","unstructured":"Min G, Zhang X, Zou X, Sun M (2016) In Mask estimate through Itakura-Saito nonnegative RPCA for speech enhancement, Acoustic Signal Enhancement (IWAENC), 2016 IEEE International Workshop on, IEEE; pp 1\u20135","key":"8032_CR33","DOI":"10.1109\/IWAENC.2016.7602951"},{"issue":"6","key":"8032_CR34","doi-asserted-by":"publisher","first-page":"1081","DOI":"10.19026\/rjaset.6.4016","volume":"6","author":"S Nasir","year":"2013","unstructured":"Nasir S, Sher A, Usman K, Farman U (2013) Speech enhancement with geometric advent of spectral subtraction using connected time-frequency regions noise estimation. Res J Appl Sci Eng Technol 6(6):1081\u20131087","journal-title":"Res J Appl Sci Eng Technol"},{"issue":"1","key":"8032_CR35","doi-asserted-by":"publisher","first-page":"62","DOI":"10.1109\/TSMC.1979.4310076","volume":"9","author":"N Otsu","year":"1979","unstructured":"Otsu N (1979) A threshold selection method from gray-level histograms. IEEE transactions on systems, man, and cybernetics 9(1):62\u201366","journal-title":"IEEE transactions on systems, man, and cybernetics"},{"issue":"2","key":"8032_CR36","doi-asserted-by":"publisher","first-page":"341","DOI":"10.1007\/s10470-017-1042-z","volume":"93","author":"H Rahali","year":"2017","unstructured":"Rahali H, Hajaiej Z (2017) Enhancement of noise-suppressed speech by spectral processing implemented in a digital signal processor. Analog Integr Circ Sig Process 93(2):341\u2013350","journal-title":"Analog Integr Circ Sig Process"},{"issue":"2","key":"8032_CR37","doi-asserted-by":"publisher","first-page":"220","DOI":"10.1016\/j.specom.2005.08.005","volume":"48","author":"S Rangachari","year":"2006","unstructured":"Rangachari S, Loizou PC (2006) A noise-estimation method for highly non-stationary environments. Speech Comm 48(2):220\u2013231","journal-title":"Speech Comm"},{"doi-asserted-by":"crossref","unstructured":"Renson L, Sieber J, Barton DAW, Shaw AD, Neild SA (2019) Numerical Continuation in Nonlinear Experiments using Local Gaussian Process Regression. arXiv preprint arXiv:1901.06970","key":"8032_CR38","DOI":"10.1007\/s11071-019-05118-y"},{"unstructured":"Rix AW, Beerends JG, Hollier MP, Hekstra AP (2001) In Perceptual evaluation of speech quality (PESQ)-a new method for speech quality assessment of telephone networks and codecs, Acoustics, Speech, and Signal Processing, 2001. Proceedings.(ICASSP'01). 2001 IEEE International Conference on, IEEE: pp 749\u2013752","key":"8032_CR39"},{"key":"8032_CR40","doi-asserted-by":"publisher","first-page":"225","DOI":"10.1109\/TAU.1969.1162058","volume":"17","author":"E Rothauser","year":"1969","unstructured":"Rothauser E (1969) IEEE recommended practice for speech quality measurements. IEEE Trans on Audio and Electroacoustics 17:225\u2013246","journal-title":"IEEE Trans on Audio and Electroacoustics"},{"issue":"1","key":"8032_CR41","doi-asserted-by":"publisher","first-page":"89","DOI":"10.1007\/s10772-016-9391-z","volume":"20","author":"N Saleem","year":"2017","unstructured":"Saleem N (2017) Single channel noise reduction system in low SNR. International Journal of Speech Technology 20(1):89\u201398","journal-title":"International Journal of Speech Technology"},{"issue":"2","key":"8032_CR42","doi-asserted-by":"publisher","first-page":"217","DOI":"10.1007\/s10772-018-9500-2","volume":"21","author":"N Saleem","year":"2018","unstructured":"Saleem N, Ijaz G (2018) Low rank sparse decomposition model based speech enhancement using gammatone filterbank and Kullback\u2013Leibler divergence. International Journal of Speech Technology 21(2):217\u2013231","journal-title":"International Journal of Speech Technology"},{"issue":"6","key":"8032_CR43","doi-asserted-by":"publisher","first-page":"2591","DOI":"10.1007\/s00034-017-0684-5","volume":"37","author":"N Saleem","year":"2018","unstructured":"Saleem N, Irfan M (2018) Noise reduction based on soft masks by incorporating SNR uncertainty in frequency domain. Circuits, Systems, and Signal Processing 37(6):2591\u20132612","journal-title":"Circuits, Systems, and Signal Processing"},{"issue":"4","key":"8032_CR44","first-page":"36","volume":"20","author":"N Saleem","year":"2015","unstructured":"Saleem N, Shafi M, Mustafa E, Nawaz A (2015) 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):36","journal-title":"Technical Journal"},{"key":"8032_CR45","doi-asserted-by":"publisher","first-page":"333","DOI":"10.1016\/j.apacoust.2018.07.027","volume":"141","author":"N Saleem","year":"2018","unstructured":"Saleem N, Khattak MI, Shafi M (2018) Unsupervised speech enhancement in low SNR environments via sparseness and temporal gradient regularization. Appl Acoust 141:333\u2013347","journal-title":"Appl Acoust"},{"unstructured":"Scalart P (1996) In Speech enhancement based on a priori signal to noise estimation, Acoustics, Speech, and Signal Processing, 1996. ICASSP-96. Conference Proceedings, 1996 IEEE International Conference on, IEEE; pp 629-63e2","key":"8032_CR46"},{"issue":"4","key":"8032_CR47","doi-asserted-by":"publisher","first-page":"609","DOI":"10.1007\/s10772-015-9305-5","volume":"18","author":"S Singh","year":"2015","unstructured":"Singh S, Tripathy M, Anand R (2015) Binary mask based method for enhancement of mixed noise speech of low SNR input. International Journal of Speech Technology 18(4):609\u2013617","journal-title":"International Journal of Speech Technology"},{"key":"8032_CR48","first-page":"2954","volume":"2005","author":"KV Sorensen","year":"2005","unstructured":"Sorensen KV, Andersen SV (2005) Speech enhancement with natural sounding residual noise based on connected time-frequency speech presence regions. EURASIP Journal on Applied Signal Processing 2005:2954\u20132964","journal-title":"EURASIP Journal on Applied Signal Processing"},{"issue":"11","key":"8032_CR49","doi-asserted-by":"publisher","first-page":"1486","DOI":"10.1016\/j.specom.2006.09.003","volume":"48","author":"S Srinivasan","year":"2006","unstructured":"Srinivasan S, Roman N, Wang D (2006) Binary and ratio time-frequency masks for robust speech recognition. Speech Comm 48(11):1486\u20131501","journal-title":"Speech Comm"},{"issue":"7","key":"8032_CR50","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, Jensen J (2011) An method for intelligibility prediction of time\u2013frequency weighted noisy speech. IEEE Trans Audio Speech Lang Process 19(7):2125\u20132136","journal-title":"IEEE Trans Audio Speech Lang Process"},{"issue":"1","key":"8032_CR51","doi-asserted-by":"publisher","first-page":"6","DOI":"10.1109\/LSP.2015.2495102","volume":"23","author":"R Tavares","year":"2016","unstructured":"Tavares R, Coelho R (2016) Speech enhancement with nonstationary acoustic noise detection in time domain. IEEE Signal Processing Letters 23(1):6\u201310","journal-title":"IEEE Signal Processing Letters"},{"doi-asserted-by":"crossref","unstructured":"Wang D (2005) On ideal binary mask as the computational goal of auditory scene analysis. In Speech separation by humans and machines, Springer: pp 181\u2013197","key":"8032_CR52","DOI":"10.1007\/0-387-22794-6_12"},{"issue":"4","key":"8032_CR53","doi-asserted-by":"publisher","first-page":"332","DOI":"10.1177\/1084713808326455","volume":"12","author":"D Wang","year":"2008","unstructured":"Wang D (2008) Time-frequency masking for speech separation and its potential for hearing aid design. Trends in Amplification 12(4):332\u2013353","journal-title":"Trends in Amplification"},{"doi-asserted-by":"crossref","unstructured":"Wang D, Brown GJ (2006) Computational auditory scene analysis: Principles, methods, and applications. Wiley-IEEE press","key":"8032_CR54","DOI":"10.1109\/9780470043387"},{"issue":"12","key":"8032_CR55","doi-asserted-by":"publisher","first-page":"3389","DOI":"10.1109\/TMM.2018.2838320","volume":"20","author":"C Yan","year":"2018","unstructured":"Yan C, Xie H, Chen J, Zha Z, Hao X, Zhang Y, Dai Q (2018) A fast uyghur text detector for complex background images. IEEE Transactions on Multimedia 20(12):3389\u20133398","journal-title":"IEEE Transactions on Multimedia"},{"doi-asserted-by":"crossref","unstructured":"Yan C, Li L, Zhang C, Liu B, Zhang Y, Dai Q (2019) Cross-modality bridging and knowledge transferring for image understanding. IEEE Transactions on Multimedia","key":"8032_CR56","DOI":"10.1109\/TMM.2019.2903448"},{"doi-asserted-by":"crossref","unstructured":"Yan C, Li Z, Zhang Y, Qin P, Ji X and Dai Q. (2019) Depth image denoising using nuclear norm and learning graph model. IEEE Transactions on Multimedia","key":"8032_CR57","DOI":"10.1145\/3404374"},{"doi-asserted-by":"crossref","unstructured":"Yan C, Tu Y, Wang X, Zhang Y, Hao X, Zhang Y and Dai Q (2019) STAT: Spatial-Temporal Attention Mechanism for Video Captioning. IEEE Transactions on Multimedia","key":"8032_CR58","DOI":"10.1109\/TMM.2020.2966830"},{"issue":"12","key":"8032_CR59","doi-asserted-by":"publisher","first-page":"3271","DOI":"10.1109\/TIP.2010.2055570","volume":"19","author":"X You","year":"2010","unstructured":"You X, Du L, Cheung Y-m, Chen Q (2010) A blind watermarking scheme using new nontensor product wavelet filter banks. IEEE Trans Image Process 19(12):3271\u20133284","journal-title":"IEEE Trans Image Process"},{"issue":"5","key":"8032_CR60","doi-asserted-by":"publisher","first-page":"899","DOI":"10.1109\/TASLP.2014.2312541","volume":"22","author":"L Zao","year":"2014","unstructured":"Zao L, Coelho R, Flandrin P (2014) Speech enhancement with emd and Hurst-based mode selection. IEEE\/ACM Transactions on Audio, Speech and Language Processing (TASLP) 22(5):899\u2013911","journal-title":"IEEE\/ACM Transactions on Audio, Speech and Language Processing (TASLP)"},{"doi-asserted-by":"crossref","unstructured":"Zhao S, Yao H, Wang F, Jiang X, Zhang W (2014) Emotion based image musicalization. IEEE International conference on multimedia and expo workshops (ICMEW) pp. 1\u20136","key":"8032_CR61","DOI":"10.1109\/ICMEW.2014.6890565"},{"issue":"5","key":"8032_CR62","doi-asserted-by":"publisher","first-page":"1812","DOI":"10.1109\/TSP.2007.910555","volume":"56","author":"X Zou","year":"2008","unstructured":"Zou X, Jancovic P, Liu J, Kokuer M (2008) Speech signal enhancement based on MAP method in the ICA space. IEEE Trans Signal Process 56(5):1812\u20131820","journal-title":"IEEE Trans Signal Process"},{"issue":"9","key":"8032_CR63","doi-asserted-by":"publisher","first-page":"1436","DOI":"10.3390\/app8091436","volume":"8","author":"Y Zou","year":"2018","unstructured":"Zou Y, Liu Z, Ritz C (2018) Enhancing target speech based on nonlinear soft masking using a single acoustic vector sensor. Appl Sci 8(9):1436","journal-title":"Appl Sci"}],"container-title":["Multimedia Tools and Applications"],"original-title":[],"language":"en","link":[{"URL":"http:\/\/link.springer.com\/content\/pdf\/10.1007\/s11042-019-08032-y.pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"text-mining"},{"URL":"http:\/\/link.springer.com\/article\/10.1007\/s11042-019-08032-y\/fulltext.html","content-type":"text\/html","content-version":"vor","intended-application":"text-mining"},{"URL":"http:\/\/link.springer.com\/content\/pdf\/10.1007\/s11042-019-08032-y.pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2023,9,18]],"date-time":"2023-09-18T15:16:09Z","timestamp":1695050169000},"score":1,"resource":{"primary":{"URL":"http:\/\/link.springer.com\/10.1007\/s11042-019-08032-y"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2019,7,25]]},"references-count":63,"journal-issue":{"issue":"22","published-print":{"date-parts":[[2019,11]]}},"alternative-id":["8032"],"URL":"https:\/\/doi.org\/10.1007\/s11042-019-08032-y","relation":{},"ISSN":["1380-7501","1573-7721"],"issn-type":[{"type":"print","value":"1380-7501"},{"type":"electronic","value":"1573-7721"}],"subject":[],"published":{"date-parts":[[2019,7,25]]},"assertion":[{"value":"14 October 2018","order":1,"name":"received","label":"Received","group":{"name":"ArticleHistory","label":"Article History"}},{"value":"7 June 2019","order":2,"name":"revised","label":"Revised","group":{"name":"ArticleHistory","label":"Article History"}},{"value":"19 July 2019","order":3,"name":"accepted","label":"Accepted","group":{"name":"ArticleHistory","label":"Article History"}},{"value":"25 July 2019","order":4,"name":"first_online","label":"First Online","group":{"name":"ArticleHistory","label":"Article History"}}]}}