{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,4,18]],"date-time":"2026-04-18T11:09:01Z","timestamp":1776510541984,"version":"3.51.2"},"reference-count":32,"publisher":"Springer Science and Business Media LLC","issue":"18","license":[{"start":{"date-parts":[[2022,3,26]],"date-time":"2022-03-26T00:00:00Z","timestamp":1648252800000},"content-version":"tdm","delay-in-days":0,"URL":"https:\/\/www.springer.com\/tdm"},{"start":{"date-parts":[[2022,3,26]],"date-time":"2022-03-26T00:00:00Z","timestamp":1648252800000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/www.springer.com\/tdm"}],"funder":[{"DOI":"10.13039\/501100011844","name":"Science and Technology Department, Heilongjiang Province","doi-asserted-by":"crossref","award":["No. LH2020F033"],"award-info":[{"award-number":["No. LH2020F033"]}],"id":[{"id":"10.13039\/501100011844","id-type":"DOI","asserted-by":"crossref"}]},{"DOI":"10.13039\/501100001809","name":"National Natural Science Youth Foundation of China","doi-asserted-by":"crossref","award":["No.11804068"],"award-info":[{"award-number":["No.11804068"]}],"id":[{"id":"10.13039\/501100001809","id-type":"DOI","asserted-by":"crossref"}]}],"content-domain":{"domain":["link.springer.com"],"crossmark-restriction":false},"short-container-title":["Multimed Tools Appl"],"published-print":{"date-parts":[[2022,7]]},"DOI":"10.1007\/s11042-022-12929-6","type":"journal-article","created":{"date-parts":[[2022,3,29]],"date-time":"2022-03-29T00:03:54Z","timestamp":1648512234000},"page":"26163-26184","update-policy":"https:\/\/doi.org\/10.1007\/springer_crossmark_policy","source":"Crossref","is-referenced-by-count":2,"title":["Research on improved DNN and MultiResU_Net network speech enhancement effect"],"prefix":"10.1007","volume":"81","author":[{"ORCID":"https:\/\/orcid.org\/0000-0003-4667-0635","authenticated-orcid":false,"given":"Chaofeng","family":"Lan","sequence":"first","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Lei","family":"Zhang","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"YuQiao","family":"Wang","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Chundong","family":"Liu","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"297","published-online":{"date-parts":[[2022,3,26]]},"reference":[{"key":"12929_CR1","unstructured":"Asma B, Sid AS, Abderrahmane A, Mohammed SY (2021) Improved empirical mode decomposition using optimal recursive averaging noise estimation for speech enhancement. Circuit Syst Signal Process :1\u201328. https:\/\/sci-hub.se\/downloads\/2021-08-16\/99\/bouchair2021.pdf"},{"key":"12929_CR2","doi-asserted-by":"publisher","DOI":"10.1007\/s00034-020-01604-6","author":"Y Attabi","year":"2021","unstructured":"Attabi Y, Champagne B, Zhu W-P (2021) DNN-based calibrated-filter models for speech enhancement. Circuits Syst Signal Process. https:\/\/doi.org\/10.1007\/s00034-020-01604-6","journal-title":"Circuits Syst Signal Process"},{"key":"12929_CR3","doi-asserted-by":"crossref","unstructured":"Bulut AE, Koishida K, Low-Latency Single Channel Speech Enhancement Using U-Net Convolutional Neural Networks (2020). 2020 IEEE International Conference on Acoustics, Speech and Signal Processing, Barcelona, Spain, 6214\u20136218. https:\/\/sci-hub.se\/downloads\/2020-05-19\/75\/bulut2020.pdf?rand=61a9f852d4d1d","DOI":"10.1109\/ICASSP40776.2020.9054563"},{"key":"12929_CR4","doi-asserted-by":"crossref","unstructured":"Chen J-T, Wang Y-X, Wang D-L (2014) A feature study for classification-based speech separation at very low signal-to-noise ratio. Paper presented at 2014 IEEE International Conference on Acoustics, Speech and Signal Processing, 14. https:\/\/ieeexplore.ieee.org\/document\/6854965\/","DOI":"10.1109\/ICASSP.2014.6854965"},{"key":"12929_CR5","doi-asserted-by":"crossref","unstructured":"Chen J-T, Wang Y-X, Wang D-L (2016) Noise perturbation for supervised speech separation. Speech Commun 78:1\u201310. https:\/\/www.sciencedirect.com\/science\/article\/abs\/pii\/S0167639315001405","DOI":"10.1016\/j.specom.2015.12.006"},{"key":"12929_CR6","doi-asserted-by":"crossref","unstructured":"Chen H, Du J, Hu Y, Dai L-R, Yin B-C, Lee C-H (2021) Correlating subword articulation with lip shapes for embedding aware audio-visual speech enhancement. Neural Netw 143:171\u2013182","DOI":"10.1016\/j.neunet.2021.06.003"},{"key":"12929_CR7","unstructured":"Choi HS, Kim JH, Huh J et al (2019) Phase-aware speech enhancement with deep complex U-Net. International Conference on Learning Representations, Montreal, Canada. https:\/\/openreview.net\/pdf?id=SkeRTsAcYm"},{"issue":"28","key":"12929_CR8","first-page":"888","volume":"4","author":"W Felix","year":"2014","unstructured":"Felix W, Juergen G, Martin W et al (2014) Feature enhancement by deep LSTM networks for ASR in reverberant multisource environments. Comput Speech Lang 4(28):888\u2013902","journal-title":"Comput Speech Lang"},{"key":"12929_CR9","unstructured":"Gao T, Du J, Dai L-R, Lee C-H (2018) Densely connected progressive learning for LSTM-based speech enhancement. 2018 IEEE International Conference on Acoustics, Speech and Signal Processing, Calgary, AB, Canada, 5054\u20135058. https:\/\/twin.sci-hub.se\/7118\/4d0fc104065ac4f94f302637571f9352\/gao2018.pdf"},{"key":"12929_CR10","doi-asserted-by":"publisher","first-page":"74","DOI":"10.1016\/j.neunet.2019.08.025","volume":"121","author":"N Ibtehaz","year":"2020","unstructured":"Ibtehaz N, Rahman MS (2020) MultiResUNet: rethinking the U-Net architecture for multimodal biomedical image segmentation neural networks [J]. Neural Netw 121:74\u201387","journal-title":"Neural Netw"},{"key":"12929_CR11","doi-asserted-by":"crossref","unstructured":"Islam MS, Zhu YY, Hossain MI, Ullah R, Ye ZF (2020) Supervised single channel dual domains speech enhancement using sparse non-negative matrix factorization. Digit Signal Proc 100(C):102697\u2013102697","DOI":"10.1016\/j.dsp.2020.102697"},{"key":"12929_CR12","doi-asserted-by":"crossref","unstructured":"Jia H-R, Wang W-M, Mei S-L (2021) Combining adaptive sparse NMF feature extraction and soft mask to optimize DNN for speech enhancement. Appl Acoust 171:107666. https:\/\/linkinghub.elsevier.com\/retrieve\/pii\/S0003682X20307702","DOI":"10.1016\/j.apacoust.2020.107666"},{"key":"12929_CR13","doi-asserted-by":"crossref","unstructured":"Jiang Y, Wang DL, Liu RS, Feng ZM (2014) Binaural classification for reverberant speech segregation using deep neural networks. IEEE\/ACM Trans Audio Speech Lang Process 22:2112\u20132121","DOI":"10.1109\/TASLP.2014.2361023"},{"key":"12929_CR14","doi-asserted-by":"crossref","unstructured":"Kang TG, Kwon K, Shin JW, Kim NS (2015) NMF-based target source separation using deep neural network. Published in IEEE Signal Processing Letters. https:\/\/ieeexplore.ieee.org\/document\/6892992","DOI":"10.1109\/LSP.2014.2354456"},{"issue":"13","key":"12929_CR15","doi-asserted-by":"publisher","first-page":"1586","DOI":"10.3390\/electronics10131586","volume":"10","author":"L-J Li","year":"2021","unstructured":"Li L-J, Kang Y-K, Shi Y-C, K\u00fcrzinger L, Watzel T, Rigoll G (2021) Light-weight self-attention augmented generative adversarial networks for speech enhancement. Electronics 10(13):1586","journal-title":"Electronics"},{"issue":"6","key":"12929_CR16","first-page":"819","volume":"42","author":"W-J Liu","year":"2016","unstructured":"Liu W-J, Nie S, Liang S, Zhang X-L (2016) Deep learning based speech separation technology and its developments. Acta Autom Sin 42(6):819\u2013833","journal-title":"Acta Autom Sin"},{"key":"12929_CR17","doi-asserted-by":"publisher","unstructured":"Olaf R, Fischer P, Brox T (2015) U-Net: Convolutional networks for biomedical image segmentatin[C]. International Conference on Medical Image Computing and Computer-Assisited Intervention Intervention, 234\u2013241. https:\/\/doi.org\/10.1007\/978-3-319-24574-4_28.pdf","DOI":"10.1007\/978-3-319-24574-4_28.pdf"},{"key":"12929_CR18","doi-asserted-by":"publisher","unstructured":"Park SR, Lee JW (2017) A fully convolutional neural network for speech enhancement. INTERSPEECH. https:\/\/doi.org\/10.21437\/Interspeech.2017-1465","DOI":"10.21437\/Interspeech.2017-1465"},{"key":"12929_CR19","unstructured":"Shi W-H, Zhang X-W, Zhang R-X, Han W (2016) Special lectures on deep learning theory and its applications (4) lecture 8 The Application of Deep Learning Methods in Speech Enhancement. Military Commun Technol 37(03):98\u2013104. https:\/\/kns.cnki.net\/kcms\/detail\/detail.aspx?dbcode=CJFD&dbname=CJFDLAST2016&filename=JSTY201603021&v=fegNytVa6QrSPGnMaPlHpz2qMtxEbwAw7zQMaviwn0uv0aRrm8owrnCdYqGPOpu0"},{"key":"12929_CR20","doi-asserted-by":"crossref","unstructured":"Smaragdis P (2007) Convolutive speech bases and their application to supervised speech separation. Published in: IEEE Transactions on Audio, Speech, and Language Processing. https:\/\/ieeexplore.ieee.org\/document\/4032795","DOI":"10.1109\/TASL.2006.876726"},{"key":"12929_CR21","doi-asserted-by":"crossref","unstructured":"Tim F, Marco C, Wilhelm W (2021) Speech signal enhancement in cocktail party scenarios by deep learning based virtual sensing of head-mounted microphones. Hear Res 408:108294","DOI":"10.1016\/j.heares.2021.108294"},{"key":"12929_CR22","doi-asserted-by":"crossref","unstructured":"Tseng H-W, Hong M-Y, Luo Z-Q (2015) Combining sparse NMF with deep neural network: A new classification-based approach for speech enhancement. Paper presented at 2015 IEEE International Conference on Acoustics, Speech and Signal Processing, 19\u201324. https:\/\/ieeexplore.ieee.org\/document\/7178350","DOI":"10.1109\/ICASSP.2015.7178350"},{"key":"12929_CR23","doi-asserted-by":"crossref","unstructured":"Tu M, Zhang X-X (2017) Speech enhancement based on Deep Neural Networks with skip connections. Paper presented at 2017 IEEE International Conference on Acoustics, Speech and Signal Processing, 5\u20139. https:\/\/ieeexplore.ieee.org\/document\/7953221","DOI":"10.1109\/ICASSP.2017.7953221"},{"key":"12929_CR24","unstructured":"Tu Y, Du J, Xu Y, Dai L-R, Lee C-H (2014) Deep neural network based speech separation for robust speech recognition. Published in 2014 12th International Conference on Signal Processing, 19-23. https:\/\/ieeexplore.ieee.org\/document\/7015061?tp=&arnumber=7015061&ranges%3D2013_2015_p_Publication_Year%26queryText%3Ddeep%20neural%20network%20in%20speech="},{"key":"12929_CR25","doi-asserted-by":"crossref","unstructured":"Vincent E, R\u00e9mi G, C\u00e9dric F (2006) Performance measurement in blind audio source separation. IEEE Trans Audio Speech Lang Process 14(4):1462\u20131469","DOI":"10.1109\/TSA.2005.858005"},{"key":"12929_CR26","doi-asserted-by":"crossref","unstructured":"Wang Y-X, Wang D-L (2014) A structure-preserving training target for supervised speech separation. Paper presented at 2014 IEEE International Conference on Acoustics, Speech and Signal Processing, 4\u20139. https:\/\/ieeexplore.ieee.org\/document\/6854777\/footnotes#footnotes","DOI":"10.1109\/ICASSP.2014.6854777"},{"key":"12929_CR27","unstructured":"Wang Y-X, Wang D-L (2013) Towards scaling up classification-based speech separation. Published in IEEE Transactions on Audio, Speech, and Language Processing. https:\/\/ieeexplore.ieee.org\/document\/6473841"},{"key":"12929_CR28","doi-asserted-by":"crossref","unstructured":"Williamson DS, Wang YX, Wang DL (2016) Complex ratio masking for monaural speech separation. IEEE\/ACM Trans Audio Speech Lang Process 24(3):483\u2013492","DOI":"10.1109\/TASLP.2015.2512042"},{"key":"12929_CR29","doi-asserted-by":"crossref","unstructured":"Xu Y, Du J, Dai L-R, Lee C-H (2014) An experimental study on speech enhancement based on deep neural networks. IEEE Signal Processing Lett 21(1):66\u201368","DOI":"10.1109\/LSP.2013.2291240"},{"key":"12929_CR30","doi-asserted-by":"crossref","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 Trans Audio Speech Lang Process 23(1):7\u201319","DOI":"10.1109\/TASLP.2014.2364452"},{"key":"12929_CR31","unstructured":"Yang Q, Li Y-K, Zhang M-Y et al (2020) Automatic segmentation of COVID-19 CT Images using improved MultiResU_Net[C]. 2020 Chinese Automation Congress (CAC), Shanghai, China, 1614\u20131618. https:\/\/sci-hub.se\/downloads\/2021-05-14\/\/54\/yang2020.pdf?rand=61a9f943ed918"},{"key":"12929_CR32","doi-asserted-by":"publisher","unstructured":"Zhang Q-Y, Zhang D-H, Xu F-J (2021) An encrypted speech authentication and tampering recovery method based on perceptual hashing. Multimed Tools Appl :1\u201314. https:\/\/doi.org\/10.1007\/s11042-021-10905-0.pdf","DOI":"10.1007\/s11042-021-10905-0.pdf"}],"container-title":["Multimedia Tools and Applications"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/link.springer.com\/content\/pdf\/10.1007\/s11042-022-12929-6.pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/link.springer.com\/article\/10.1007\/s11042-022-12929-6\/fulltext.html","content-type":"text\/html","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/link.springer.com\/content\/pdf\/10.1007\/s11042-022-12929-6.pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2022,7,1]],"date-time":"2022-07-01T07:30:49Z","timestamp":1656660649000},"score":1,"resource":{"primary":{"URL":"https:\/\/link.springer.com\/10.1007\/s11042-022-12929-6"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2022,3,26]]},"references-count":32,"journal-issue":{"issue":"18","published-print":{"date-parts":[[2022,7]]}},"alternative-id":["12929"],"URL":"https:\/\/doi.org\/10.1007\/s11042-022-12929-6","relation":{},"ISSN":["1380-7501","1573-7721"],"issn-type":[{"value":"1380-7501","type":"print"},{"value":"1573-7721","type":"electronic"}],"subject":[],"published":{"date-parts":[[2022,3,26]]},"assertion":[{"value":"5 May 2021","order":1,"name":"received","label":"Received","group":{"name":"ArticleHistory","label":"Article History"}},{"value":"7 December 2021","order":2,"name":"revised","label":"Revised","group":{"name":"ArticleHistory","label":"Article History"}},{"value":"9 March 2022","order":3,"name":"accepted","label":"Accepted","group":{"name":"ArticleHistory","label":"Article History"}},{"value":"26 March 2022","order":4,"name":"first_online","label":"First Online","group":{"name":"ArticleHistory","label":"Article History"}},{"value":"This manuscript has been presented as Preprint according to the following link:\u00a0.","order":1,"name":"Ethics","group":{"name":"EthicsHeading","label":"Declarations"}},{"value":"The authors declare that there is no conflict of interest regarding the publication of this article.","order":2,"name":"Ethics","group":{"name":"EthicsHeading","label":"Conflict of interest"}}]}}