{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,2,24]],"date-time":"2026-02-24T07:30:12Z","timestamp":1771918212575,"version":"3.50.1"},"reference-count":36,"publisher":"Springer Science and Business Media LLC","issue":"16","license":[{"start":{"date-parts":[[2021,2,17]],"date-time":"2021-02-17T00:00:00Z","timestamp":1613520000000},"content-version":"tdm","delay-in-days":0,"URL":"https:\/\/www.springer.com\/tdm"},{"start":{"date-parts":[[2021,2,17]],"date-time":"2021-02-17T00:00:00Z","timestamp":1613520000000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/www.springer.com\/tdm"}],"content-domain":{"domain":["link.springer.com"],"crossmark-restriction":false},"short-container-title":["Neural Comput & Applic"],"published-print":{"date-parts":[[2021,8]]},"DOI":"10.1007\/s00521-021-05782-5","type":"journal-article","created":{"date-parts":[[2021,2,19]],"date-time":"2021-02-19T02:43:05Z","timestamp":1613702585000},"page":"10199-10209","update-policy":"https:\/\/doi.org\/10.1007\/springer_crossmark_policy","source":"Crossref","is-referenced-by-count":10,"title":["Multilayered convolutional neural network-based auto-CODEC for audio signal denoising using mel-frequency cepstral coefficients"],"prefix":"10.1007","volume":"33","author":[{"given":"Shivangi","family":"Raj","sequence":"first","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-2471-6375","authenticated-orcid":false,"given":"P.","family":"Prakasam","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Shubham","family":"Gupta","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"297","published-online":{"date-parts":[[2021,2,17]]},"reference":[{"key":"5782_CR1","first-page":"1","volume":"53","author":"MA Ali","year":"2015","unstructured":"Ali MA, Shemi PM (2015) An improved method of audio denoising based on wavelet transform. Proceedings of the IEEE International Conference on Power, Instrumentation, Control and Computing. 53:1\u20136","journal-title":"Proceedings of the IEEE International Conference on Power, Instrumentation, Control and Computing."},{"key":"5782_CR2","doi-asserted-by":"publisher","DOI":"10.1016\/j.measurement.2019.107117","author":"H Haneche","year":"2020","unstructured":"Haneche H, Boudraa B, Ouahabi A (2020) A new way to enhance speech signal based on compressed sensing. Measurement. https:\/\/doi.org\/10.1016\/j.measurement.2019.107117","journal-title":"Measurement"},{"key":"5782_CR3","doi-asserted-by":"crossref","unstructured":"Welk M., Bergmeister A., Weickert J (2015) Denoising of Audio Data by Nonlinear Diffusion, In: Scale Space and PDE Methods in Computer Vision. Lecture Notes in Computer Science. 3459; 598\u2013609.","DOI":"10.1007\/11408031_51"},{"key":"5782_CR4","doi-asserted-by":"crossref","unstructured":"Yu, G. Bacry, E. Mallat, S (2007) Audio Signal Denoising with Complex Wavelets and Adaptive Block Attenuation. In:Proceedings of the IEEE International Conference on Acoustics, Speech and Signal Processing, 863\u2013869.","DOI":"10.1109\/ICASSP.2007.366818"},{"issue":"2","key":"5782_CR5","doi-asserted-by":"publisher","first-page":"629","DOI":"10.1016\/j.jestch.2018.10.008","volume":"22","author":"A Ali","year":"2019","unstructured":"Ali A (2019) Impulse noise reduction in audio signal through multi-stage technique. Engineering Science and Technology, an International Journal 22(2):629\u2013636","journal-title":"Engineering Science and Technology, an International Journal"},{"key":"5782_CR6","doi-asserted-by":"crossref","unstructured":"Pohjalainen, J. Ringeval, F. Zhang, Z. Schuller, B. (2016). Spectral and Cepstral Audio Noise Reduction Techniques in Speech Emotion Recognition, In: Proceedings of the 24th ACM International Conference on Multimedia. 670 - 674.","DOI":"10.1145\/2964284.2967306"},{"issue":"4","key":"5782_CR7","doi-asserted-by":"publisher","first-page":"2159","DOI":"10.3233\/JIFS-162329","volume":"33","author":"MJ Davoudabadi","year":"2017","unstructured":"Davoudabadi MJ, Mina A (2017) A fuzzy-wavelet denoising technique with applications to noise reduction in audio signals. Journal of Intelligent & Fuzzy Systems 33(4):2159\u20132169","journal-title":"Journal of Intelligent & Fuzzy Systems"},{"key":"5782_CR8","doi-asserted-by":"publisher","DOI":"10.1007\/s10772-020-09674-2","author":"N Das","year":"2020","unstructured":"Das N, Chakraborty S, Chaki J, Padhy N, Dey N (2020) Fundamentals, present and future perspectives of speech enhancement. Int J Speech Technol. https:\/\/doi.org\/10.1007\/s10772-020-09674-2","journal-title":"Int J Speech Technol"},{"key":"5782_CR9","volume-title":"2019","author":"M Michelashvili","year":"2019","unstructured":"Michelashvili M, Wolf L (2019) 2019. Audio Denoising with Deep Network Priors, CoRR"},{"key":"5782_CR10","doi-asserted-by":"publisher","first-page":"78421","DOI":"10.1109\/ACCESS.2019.2922370","volume":"7","author":"GS Bhat","year":"2019","unstructured":"Bhat GS, Shankar N, Reddy CKA, Panahi IMS (2019) A Real-Time Convolutional Neural Network Based Speech Enhancement for Hearing Impaired Listeners Using Smartphone. IEEE Access 7:78421\u201378433","journal-title":"IEEE Access"},{"key":"5782_CR11","doi-asserted-by":"crossref","unstructured":"Candes, E,J. Li, X. Ma, Y. Wright, J (2011) Robust principal component analysis?. Journal of the ACM. 58(3); 11:01\u201311:37.","DOI":"10.1145\/1970392.1970395"},{"key":"5782_CR12","doi-asserted-by":"publisher","first-page":"1979","DOI":"10.1109\/TIFS.2017.2678458","volume":"12","author":"YH Chin","year":"2017","unstructured":"Chin YH, Wang JC, Huang CL, Wang KY, Wu CH (2017) Speaker identification using discriminative features and sparse representation. IEEE Trans Inf Forensics Secur 12:1979\u20131987","journal-title":"IEEE Trans Inf Forensics Secur"},{"key":"5782_CR13","doi-asserted-by":"crossref","unstructured":"Wilson, K.W. Raj, B. Smaragdis, P. Divakaran, A. (2009). Speech denoising using nonnegative matrix factorization with priors, In: Proceedings of the IEEE International Conference on Acoustics, Speech and Signal Processing. 32; 4029\u20134032.","DOI":"10.1109\/ICASSP.2008.4518538"},{"issue":"11","key":"5782_CR14","doi-asserted-by":"publisher","first-page":"2122","DOI":"10.1109\/TASLP.2016.2598306","volume":"24","author":"JC Wang","year":"2016","unstructured":"Wang JC, Lee YS, Lin CH, Wang SF, Shih CH, Wu CH (2016) Compressive sensing-based speech enhancement. IEEE\/ACM Transactions on Audio, Speech and Language Processing 24(11):2122\u20132131","journal-title":"IEEE\/ACM Transactions on Audio, Speech and Language Processing"},{"key":"5782_CR15","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 (2019) Learning complex spectral mapping with gated convolutional recurrent networks for monaural speech enhancement. IEEE\/ACM Transactions on Audio, Speech and Language Processing 28:380\u2013390","journal-title":"IEEE\/ACM Transactions on Audio, Speech and Language Processing"},{"key":"5782_CR16","doi-asserted-by":"publisher","DOI":"10.1016\/j.apacoust.2020.107631","author":"N Alamdari","year":"2020","unstructured":"Alamdari N, Azarang A, Kehtarnavaz N (2020) Improving deep speech denoising by Noisy2Noisy signal mapping. Appl Acoust. https:\/\/doi.org\/10.1016\/j.apacoust.2020.107631","journal-title":"Appl Acoust"},{"key":"5782_CR17","doi-asserted-by":"crossref","unstructured":"Chen, Z. Watanabe, S. Erdogan, H. Hershey, J.R. (2015). Speech enhancement and recognition using multi-task learning of long short term memory recurrent neural networks, In: Proceedings of the 16th Annual Conference of the International Speech Communication Association, 3274\u20133278.","DOI":"10.21437\/Interspeech.2015-659"},{"key":"5782_CR18","doi-asserted-by":"crossref","unstructured":"Sun, L. Du, J. Dai, L. Lee, C. (2017). Multiple-target deep learning for LSTM-RNN based speech enhancement, In: Proceedings of the Hands-free Speech Communications and Microphone Arrays Conference, 136\u2013140.","DOI":"10.1109\/HSCMA.2017.7895577"},{"issue":"1","key":"5782_CR19","doi-asserted-by":"publisher","first-page":"65","DOI":"10.1109\/LSP.2013.2291240","volume":"21","author":"Y Xu","year":"2014","unstructured":"Xu Y, Du J, Dai LR, Lee CH (2014) An experimental study on speech enhancement based on deep neural networks. IEEE Signal Process Lett 21(1):65\u201368","journal-title":"IEEE Signal Process Lett"},{"issue":"7","key":"5782_CR20","doi-asserted-by":"publisher","first-page":"1179","DOI":"10.1109\/TASLP.2019.2913512","volume":"27","author":"A Pandey","year":"2019","unstructured":"Pandey A, Wang D (2019) A new framework for CNN-based speech enhancement in the time domain. IEEE\/ACM Transactions on Audio, Speech and Language Processing 27(7):1179\u20131188","journal-title":"IEEE\/ACM Transactions on Audio, Speech and Language Processing"},{"issue":"9","key":"5782_CR21","doi-asserted-by":"publisher","first-page":"1570","DOI":"10.1109\/TASLP.2018.2821903","volume":"26","author":"SW Fu","year":"2018","unstructured":"Fu SW, Wang TW, Tsao Y, Lu X, Kawai H (2018) End-to-end waveform utterance enhancement for direct evaluation metrics optimization by fully convolutional neural networks. IEEE\/ACM Transactions on Audio, Speech and Language Processing 26(9):1570\u20131584","journal-title":"IEEE\/ACM Transactions on Audio, Speech and Language Processing"},{"key":"5782_CR22","first-page":"3371","volume":"11","author":"P Vincent","year":"2010","unstructured":"Vincent P, Larochelle H, Lajoie I, Bengio Y, Manzagol PA (2010) Stacked denoising autoencoders: Learning useful representations in a deep network with a local denoising criterion. Journal of Machine Learning Research 11:3371\u20133408","journal-title":"Journal of Machine Learning Research"},{"key":"5782_CR23","doi-asserted-by":"crossref","unstructured":"Shivakumar P.G. Georgiou, P.G (2016) Perception optimized deep denoising autoencoders for speech enhancement. In: Proc. INTERSPEECH. 3743\u20133747.","DOI":"10.21437\/Interspeech.2016-1284"},{"key":"5782_CR24","doi-asserted-by":"publisher","first-page":"535","DOI":"10.1007\/978-3-319-12637-1_67","volume":"8834","author":"B Chandra","year":"2014","unstructured":"Chandra B, Sharma RK (2014) Adaptive Noise Schedule for Denoising Autoencoder. In Neural Information Processing. ICONIP 2014. Lect Notes Comput Sci 8834:535\u2013542","journal-title":"Lect Notes Comput Sci"},{"key":"5782_CR25","doi-asserted-by":"crossref","unstructured":"Hao, X. Shan, C. Xu, Y. Sun, S. Xie, L. (2019) An Attention-based Neural Network Approach for Single Channel Speech Enhancement, In: Proceedings of IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP). 6895\u20136899.","DOI":"10.1109\/ICASSP.2019.8683169"},{"key":"5782_CR26","doi-asserted-by":"publisher","first-page":"48464","DOI":"10.1109\/ACCESS.2020.2979554","volume":"8","author":"R Liang","year":"2020","unstructured":"Liang R, Kong F, Xie Y, Tang G, Cheng J (2020) Real-Time Speech Enhancement Algorithm Based on Attention LSTM. IEEE Access 8:48464\u201348476","journal-title":"IEEE Access"},{"key":"5782_CR27","doi-asserted-by":"crossref","unstructured":"Vincent, P. Larochelle, H. Bengio, Y. Manzagol, P.A. (2008). Extracting and Composing Robust Features with Denoising Autoencoders, In: Proceedings of the International Conference on Machine Learning, 1096\u20131103","DOI":"10.1145\/1390156.1390294"},{"key":"5782_CR28","doi-asserted-by":"publisher","first-page":"198","DOI":"10.1016\/j.cogsys.2018.07.004","volume":"53","author":"O Yildirim","year":"2018","unstructured":"Yildirim O, Tan RS, Acharya UR (2018) An efficient compression of ECG signals using deep convolutional autoencoders. Cognitive Systems Research 53:198\u2013211","journal-title":"Cognitive Systems Research"},{"issue":"4","key":"5782_CR29","doi-asserted-by":"publisher","first-page":"663","DOI":"10.1109\/TASLP.2018.2887337","volume":"27","author":"Z Zhao","year":"2019","unstructured":"Zhao Z, Liu H, Fingscheidt T (2019) Convolutional Neural Networks to Enhance Coded Speech. IEEE\/ACM Transactions on Audio, Speech and Language Processing 27(4):663\u2013678","journal-title":"IEEE\/ACM Transactions on Audio, Speech and Language Processing"},{"issue":"1","key":"5782_CR30","first-page":"19","volume":"1","author":"V Tiwari","year":"2010","unstructured":"Tiwari V (2010) MFCC and its applications in speaker recognition. International Journal on Emerging Technologies 1(1):19\u201322","journal-title":"International Journal on Emerging Technologies"},{"issue":"10","key":"5782_CR31","first-page":"2449","volume":"13","author":"Thiruvengadam","year":"2017","unstructured":"Thiruvengadam, (2017) Speech\/Music Classification using MFCC and KNN. International Journal of Computational Intelligence Research 13(10):2449\u20132452","journal-title":"International Journal of Computational Intelligence Research"},{"key":"5782_CR32","doi-asserted-by":"publisher","DOI":"10.1007\/s41745-019-0102-z","author":"U Vidyadhar","year":"2019","unstructured":"Vidyadhar U, Sastry PA (2019) An Overview of Restricted Boltzmann Machines. J Indian Inst Sci. https:\/\/doi.org\/10.1007\/s41745-019-0102-z","journal-title":"J Indian Inst Sci"},{"issue":"7","key":"5782_CR33","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 Algorithm for Intelligibility Prediction of Time-Frequency Weighted Noisy Speech. IEEE Trans Audio Speech Lang Process 19(7):2125\u20132136","journal-title":"IEEE Trans Audio Speech Lang Process"},{"key":"5782_CR34","first-page":"749","volume":"2","author":"AW Rix","year":"2001","unstructured":"Rix AW, Beerends JG, Hollier MP, Hekstra AP (2001) Perceptual evaluation of speech quality (PESQ)-a new method for speech quality assessment of telephone networks and codecs. Proceedings of the IEEE International Conference on Acoustics, Speech and Signal Processing 2:749\u2013752","journal-title":"Proceedings of the IEEE International Conference on Acoustics, Speech and Signal Processing"},{"issue":"10","key":"5782_CR35","doi-asserted-by":"publisher","first-page":"1702","DOI":"10.1109\/TASLP.2018.2842159","volume":"26","author":"D Wang","year":"2018","unstructured":"Wang D, Chen J (2018) Supervised Speech Separation Based on Deep Learning: An Overview. IEEE\/ACM Transactions on Audio, Speech and Language Processing 26(10):1702\u20131726","journal-title":"IEEE\/ACM Transactions on Audio, Speech and Language Processing"},{"key":"5782_CR36","doi-asserted-by":"crossref","unstructured":"Pascual, S. Bonafonte, A. Serra, J. (2017). SEGAN: Speech Enhancement Generative Adversarial Network, In: Proceedings of INTERSPEECH. 3642\u20133646.","DOI":"10.21437\/Interspeech.2017-1428"}],"container-title":["Neural Computing and Applications"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/link.springer.com\/content\/pdf\/10.1007\/s00521-021-05782-5.pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/link.springer.com\/article\/10.1007\/s00521-021-05782-5\/fulltext.html","content-type":"text\/html","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/link.springer.com\/content\/pdf\/10.1007\/s00521-021-05782-5.pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2022,12,18]],"date-time":"2022-12-18T04:02:20Z","timestamp":1671336140000},"score":1,"resource":{"primary":{"URL":"https:\/\/link.springer.com\/10.1007\/s00521-021-05782-5"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2021,2,17]]},"references-count":36,"journal-issue":{"issue":"16","published-print":{"date-parts":[[2021,8]]}},"alternative-id":["5782"],"URL":"https:\/\/doi.org\/10.1007\/s00521-021-05782-5","relation":{},"ISSN":["0941-0643","1433-3058"],"issn-type":[{"value":"0941-0643","type":"print"},{"value":"1433-3058","type":"electronic"}],"subject":[],"published":{"date-parts":[[2021,2,17]]},"assertion":[{"value":"4 October 2020","order":1,"name":"received","label":"Received","group":{"name":"ArticleHistory","label":"Article History"}},{"value":"28 January 2021","order":2,"name":"accepted","label":"Accepted","group":{"name":"ArticleHistory","label":"Article History"}},{"value":"17 February 2021","order":3,"name":"first_online","label":"First Online","group":{"name":"ArticleHistory","label":"Article History"}},{"order":1,"name":"Ethics","group":{"name":"EthicsHeading","label":"Compliance with Ethical Standards"}},{"value":"We hereby declare that there is no conflict of interest in this research work\/paper.","order":2,"name":"Ethics","group":{"name":"EthicsHeading","label":"Conflicts of interest"}}]}}