{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2025,9,11]],"date-time":"2025-09-11T22:14:03Z","timestamp":1757628843638,"version":"3.44.0"},"reference-count":35,"publisher":"Springer Science and Business Media LLC","issue":"29","license":[{"start":{"date-parts":[[2023,11,21]],"date-time":"2023-11-21T00:00:00Z","timestamp":1700524800000},"content-version":"tdm","delay-in-days":0,"URL":"https:\/\/www.springernature.com\/gp\/researchers\/text-and-data-mining"},{"start":{"date-parts":[[2023,11,21]],"date-time":"2023-11-21T00:00:00Z","timestamp":1700524800000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/www.springernature.com\/gp\/researchers\/text-and-data-mining"}],"funder":[{"DOI":"10.13039\/100020595","name":"National Science and Technology Council","doi-asserted-by":"publisher","award":["NSTC 111-2410-H-035-059-MY3","NSTC110-2410-H-239-019"],"award-info":[{"award-number":["NSTC 111-2410-H-035-059-MY3","NSTC110-2410-H-239-019"]}],"id":[{"id":"10.13039\/100020595","id-type":"DOI","asserted-by":"publisher"}]}],"content-domain":{"domain":["link.springer.com"],"crossmark-restriction":false},"short-container-title":["Multimed Tools Appl"],"DOI":"10.1007\/s11042-023-17655-1","type":"journal-article","created":{"date-parts":[[2023,11,21]],"date-time":"2023-11-21T01:04:34Z","timestamp":1700528674000},"page":"34795-34817","update-policy":"https:\/\/doi.org\/10.1007\/springer_crossmark_policy","source":"Crossref","is-referenced-by-count":0,"title":["A speech denoising demonstration system using multi-model deep-learning neural networks"],"prefix":"10.1007","volume":"84","author":[{"given":"Ching-Ta","family":"Lu","sequence":"first","affiliation":[]},{"ORCID":"https:\/\/orcid.org\/0000-0002-6220-096X","authenticated-orcid":false,"given":"Jun-Hong","family":"Shen","sequence":"additional","affiliation":[]},{"given":"Aniello","family":"Castiglione","sequence":"additional","affiliation":[]},{"given":"Cheng-Han","family":"Chung","sequence":"additional","affiliation":[]},{"given":"Yen-Yu","family":"Lu","sequence":"additional","affiliation":[]}],"member":"297","published-online":{"date-parts":[[2023,11,21]]},"reference":[{"key":"17655_CR1","doi-asserted-by":"publisher","unstructured":"Emani RPK, Telagathoti P, Prasad N (2020) Telephony speech enhancement for elderly people. Proc Int Conf Comput Commun Signal Process (ICCCSP), Chennai, India; 1\u20134. https:\/\/doi.org\/10.1109\/ICCCSP49186.2020.9315269","DOI":"10.1109\/ICCCSP49186.2020.9315269"},{"key":"17655_CR2","doi-asserted-by":"publisher","unstructured":"Prasad N, Praveen Kumar E, Sitaramanjaneyulu P, Srinivasa Raju GRLVN (2020) Telephony speech enhancement for hearing-impaired people. Proc Int Conf Comput Commun Security (ICCCS), Patna, India, 2020;1-4https:\/\/doi.org\/10.1109\/ICCCS49678.2020.9277386","DOI":"10.1109\/ICCCS49678.2020.9277386"},{"key":"17655_CR3","doi-asserted-by":"publisher","first-page":"687","DOI":"10.1109\/TNSRE.2018.2794557","volume":"26","author":"R Koning","year":"2018","unstructured":"Koning R, Bruce IC, Denys S, Wouters J (2018) Perceptual and model-based evaluation of ideal time-frequency noise reduction in hearing-impaired listeners. IEEE Trans Neural Syst Rehabilitation Eng 26:687\u2013697. https:\/\/doi.org\/10.1109\/TNSRE.2018.2794557","journal-title":"IEEE Trans Neural Syst Rehabilitation Eng"},{"key":"17655_CR4","doi-asserted-by":"publisher","first-page":"99","DOI":"10.1109\/TASLP.2018.2872128","volume":"27","author":"MS Kavalekalam","year":"2019","unstructured":"Kavalekalam MS, Nielsen JK, Boldt JB, Christensen MG (2019) Model-based speech enhancement for intelligibility improvement in binaural hearing aids. IEEE\/ACM Trans Audio Speech Language Process 27:99\u2013113. https:\/\/doi.org\/10.1109\/TASLP.2018.2872128","journal-title":"IEEE\/ACM Trans Audio Speech Language Process"},{"key":"17655_CR5","doi-asserted-by":"publisher","first-page":"445","DOI":"10.1007\/s11265-019-01480-7","volume":"92","author":"MSA Islam","year":"2020","unstructured":"Islam MSA, Mahmud THA, Khan WU, Ye Z (2020) Supervised single channel speech enhancement based on stationary wavelet transforms and non-negative matrix factorization with concatenated framing process and subband smooth ratio mask. J Signal Process Syst 92:445\u2013458. https:\/\/doi.org\/10.1007\/s11265-019-01480-7","journal-title":"J Signal Process Syst"},{"key":"17655_CR6","doi-asserted-by":"publisher","first-page":"2150","DOI":"10.1109\/TASLP.2019.2937174","volume":"27","author":"SUN Wood","year":"2019","unstructured":"Wood SUN, Stahl JKW, Mowlaee P (2019) Binaural codebook-based speech enhancement with atomic speech presence probability. IEEE\/ACM Trans Audio Speech Language Process 27:2150\u20132161. https:\/\/doi.org\/10.1109\/TASLP.2019.2937174","journal-title":"IEEE\/ACM Trans Audio Speech Language Process"},{"key":"17655_CR7","doi-asserted-by":"publisher","first-page":"1315","DOI":"10.1109\/TASLP.2020.2986877","volume":"28","author":"T Lavanya","year":"2020","unstructured":"Lavanya T, Nagarajan T, Vijayalakshmi P (2020) Multi-level single-channel speech enhancement using a unified framework for estimating magnitude and phase spectra. IEEE\/ACM Trans Audio Speech Language Process 28:1315\u20131327. https:\/\/doi.org\/10.1109\/TASLP.2020.2986877","journal-title":"IEEE\/ACM Trans Audio Speech Language Process"},{"key":"17655_CR8","doi-asserted-by":"publisher","first-page":"1","DOI":"10.1016\/j.specom.2019.05.001","volume":"111","author":"J Stahl","year":"2019","unstructured":"Stahl J, Mowlaee P (2019) Exploiting temporal correlation in pitch-adaptive speech enhancement. Speech Commun 111:1\u201313. https:\/\/doi.org\/10.1016\/j.specom.2019.05.001","journal-title":"Speech Commun"},{"key":"17655_CR9","doi-asserted-by":"publisher","first-page":"249","DOI":"10.1016\/j.apacoust.2013.08.015","volume":"76","author":"CT Lu","year":"2014","unstructured":"Lu CT (2014) Noise reduction using three-step gain factor and iterative-directional-median filter. Appl Acoust 76:249\u2013261. https:\/\/doi.org\/10.1016\/j.apacoust.2013.08.015","journal-title":"Appl Acoust"},{"key":"17655_CR10","doi-asserted-by":"publisher","first-page":"126","DOI":"10.1109\/89.748118","volume":"7","author":"N Virag","year":"1999","unstructured":"Virag N (1999) Single channel speech enhancement based on masking properties of the human auditory system. IEEE Trans Speech Audio Process 7:126\u2013137. https:\/\/doi.org\/10.1109\/89.748118","journal-title":"IEEE Trans Speech Audio Process"},{"key":"17655_CR11","doi-asserted-by":"publisher","first-page":"2098","DOI":"10.1109\/TASL.2006.872621","volume":"14","author":"C Plapous","year":"2006","unstructured":"Plapous C, Marro C, Scalart P (2006) Improved signal-to-noise ratio estimation for speech enhancement. IEEE Trans Audio Speech Language Process 14:2098\u20132108. https:\/\/doi.org\/10.1109\/TASL.2006.872621","journal-title":"IEEE Trans Audio Speech Language Process"},{"key":"17655_CR12","doi-asserted-by":"publisher","first-page":"509","DOI":"10.3397\/1\/376565","volume":"65","author":"CT Lu","year":"2017","unstructured":"Lu CT, Lei CL, Shen JH, Wang LL (2017) Noise reduction using subtraction-based approach with over-subtraction and reservation factors adapted by harmonic properties. Noise Control Eng J 65:509\u2013521","journal-title":"Noise Control Eng J"},{"key":"17655_CR13","doi-asserted-by":"publisher","first-page":"450","DOI":"10.1109\/LSP.2004.824017","volume":"11","author":"MK Hasan","year":"2004","unstructured":"Hasan MK, Salahuddin S, Khan MR (2004) A modified a priori SNR for speech enhancement using spectral subtraction rules. IEEE Signal Process Lett 11:450\u2013453. https:\/\/doi.org\/10.1109\/LSP.2004.824017","journal-title":"IEEE Signal Process Lett"},{"key":"17655_CR14","doi-asserted-by":"publisher","first-page":"179","DOI":"10.1007\/s10044-018-00768-x","volume":"23","author":"A Garg","year":"2020","unstructured":"Garg A, Sahu OP (2020) Enhancement of speech signal using diminished empirical mean curve decomposition-based adaptive Wiener filtering. Pattern Anal Applic 23:179\u2013198. https:\/\/doi.org\/10.1007\/s10044-018-00768-x","journal-title":"Pattern Anal Applic"},{"key":"17655_CR15","doi-asserted-by":"publisher","first-page":"745","DOI":"10.1007\/s10772-022-09987-4","volume":"25","author":"RK Jaiswal","year":"2022","unstructured":"Jaiswal RK, Yeduri SR, Cenkeramaddi LR (2022) Single-channel speech enhancement using implicit Wiener filter for high-quality speech communication. Int J Speech Technol 25:745\u2013758. https:\/\/doi.org\/10.1007\/s10772-022-09987-4","journal-title":"Int J Speech Technol"},{"key":"17655_CR16","doi-asserted-by":"publisher","first-page":"35","DOI":"10.1016\/j.specom.2013.11.002","volume":"58","author":"CT Lu","year":"2014","unstructured":"Lu CT (2014) Reduction of musical residual noise using block-and-directional-median filter adapted by harmonic properties. Speech Commun 58:35\u201348. https:\/\/doi.org\/10.1016\/j.specom.2013.11.002","journal-title":"Speech Commun"},{"key":"17655_CR17","doi-asserted-by":"publisher","first-page":"632","DOI":"10.1016\/j.csl.2009.09.001","volume":"24","author":"CT Lu","year":"2010","unstructured":"Lu CT, Tseng KF (2010) A gain factor adapted by masking property and SNR variation for speech enhancement in colored-noise corruptions. Comput Speech Language 24:632\u2013647. https:\/\/doi.org\/10.1016\/j.csl.2009.09.001","journal-title":"Comput Speech Language"},{"key":"17655_CR18","doi-asserted-by":"publisher","first-page":"495","DOI":"10.1016\/j.specom.2010.11.008","volume":"53","author":"CT Lu","year":"2011","unstructured":"Lu CT (2011) Enhancement of single channel speech using perceptual-decision-directed approach. Speech Commun 53:495\u2013507. https:\/\/doi.org\/10.1016\/j.specom.2010.11.008","journal-title":"Speech Commun"},{"key":"17655_CR19","doi-asserted-by":"publisher","first-page":"24101","DOI":"10.1007\/s11042-022-14180-5","volume":"82","author":"A Jadda","year":"2022","unstructured":"Jadda A, Prabha IS (2022) Adaptive Weiner filtering with AR-GWO based optimized fuzzy wavelet neural network for enhanced speech enhancement. Multimed Tools Appl 82:24101\u201324125. https:\/\/doi.org\/10.1007\/s11042-022-14180-5","journal-title":"Multimed Tools Appl"},{"key":"17655_CR20","doi-asserted-by":"publisher","DOI":"10.1016\/j.eswa.2023.120746","volume":"232","author":"R Nisa","year":"2023","unstructured":"Nisa R, Showkat H, Baba A (2023) The speech signal enhancement approach with multiple sub-frames analysis for complex magnitude and phase spectrum recompense. Expert Syst Applications 232:120746. https:\/\/doi.org\/10.1016\/j.eswa.2023.120746","journal-title":"Expert Syst Applications"},{"key":"17655_CR21","doi-asserted-by":"publisher","first-page":"875","DOI":"10.1007\/s11265-020-01518-1","volume":"92","author":"N Zheng","year":"2020","unstructured":"Zheng N, Shi Y, Rong W, Kang Y (2020) Effects of skip connections in CNN-based architectures for speech enhancement. J Signal Process Syst 92:875\u2013884. https:\/\/doi.org\/10.1007\/s11265-020-01518-1","journal-title":"J Signal Process Syst"},{"key":"17655_CR22","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\u2013synthesis framework with improved parameter domain enhancement. J Signal Process Syst 82:141\u2013150. https:\/\/doi.org\/10.1007\/s11265-015-1025-1","journal-title":"J Signal Process Syst"},{"key":"17655_CR23","doi-asserted-by":"publisher","unstructured":"Chai L, Du J, Liu QF, Lee CH (2021) Cross-entropy-guided measure (CEGM) for assessing speech recognition performance and optimizing DNN-based speech enhancement. IEEE\/ACM Trans Audio Speech Language Process 106\u2013117. https:\/\/doi.org\/10.1109\/TASLP.2020.3036783","DOI":"10.1109\/TASLP.2020.3036783"},{"key":"17655_CR24","doi-asserted-by":"publisher","first-page":"235","DOI":"10.1109\/CC.2018.8456465","volume":"15","author":"H Bai","year":"2018","unstructured":"Bai H, Ge F, Yan Y (2018) DNN-based speech enhancement using soft audible noise masking for wind noise reduction. China Commun 15:235\u2013243. https:\/\/doi.org\/10.1109\/CC.2018.8456465","journal-title":"China Commun"},{"key":"17655_CR25","doi-asserted-by":"publisher","first-page":"80","DOI":"10.1016\/j.specom.2020.10.004","volume":"125","author":"A Nicolson","year":"2020","unstructured":"Nicolson A, Paliwal KK (2020) Masked multi-head self-attention for causal speech enhancement. Speech Commun 125:80\u201396. https:\/\/doi.org\/10.1016\/j.specom.2020.10.004","journal-title":"Speech Commun"},{"key":"17655_CR26","doi-asserted-by":"publisher","first-page":"75","DOI":"10.1016\/j.specom.2020.09.002","volume":"124","author":"W Yuan","year":"2020","unstructured":"Yuan W (2020) A time\u2013frequency smoothing neural network for speech enhancement. Speech Commun 124:75\u201384. https:\/\/doi.org\/10.1016\/j.specom.2020.09.002","journal-title":"Speech Commun"},{"key":"17655_CR27","doi-asserted-by":"publisher","DOI":"10.1016\/j.apacoust.2020.107647","volume":"172","author":"Z Wang","year":"2021","unstructured":"Wang Z, Zhang T, Shao Y, Ding B (2021) LSTM-convolutional-BLSTM encoder-decoder network for minimum mean-square error approach to speech enhancement. Applied Acoust 172:107647. https:\/\/doi.org\/10.1016\/j.apacoust.2020.107647","journal-title":"Applied Acoust"},{"key":"17655_CR28","doi-asserted-by":"publisher","DOI":"10.1016\/j.apacoust.2020.107511","volume":"170","author":"Y Zhu","year":"2020","unstructured":"Zhu Y, Xu X, Ye Z (2020) FLGCNN: A novel fully convolutional neural network for end-to-end monaural speech enhancement with utterance-based objective functions. Applied Acoust 170:107511. https:\/\/doi.org\/10.1016\/j.apacoust.2020.107511","journal-title":"Applied Acoust"},{"key":"17655_CR29","doi-asserted-by":"publisher","first-page":"1","DOI":"10.1016\/j.specom.2020.02.001","volume":"118","author":"F Yang","year":"2020","unstructured":"Yang F, Wang Z, Li J, Xia R, Yan Y (2020) Improving generative adversarial networks for speech enhancement through regularization of latent representations. Speech Commun 118:1\u20139. https:\/\/doi.org\/10.1016\/j.specom.2020.02.001","journal-title":"Speech Commun"},{"key":"17655_CR30","doi-asserted-by":"publisher","DOI":"10.1016\/j.compeleceng.2022.107887","volume":"100","author":"MI Khattak","year":"2022","unstructured":"Khattak MI, Saleem N, Gao J, Verdu E, Fuente JP (2022) Regularized sparse features for noisy speech enhancement using deep neural networks. Comput Electr Eng 100:107887. https:\/\/doi.org\/10.1016\/j.compeleceng.2022.107887","journal-title":"Comput Electr Eng"},{"key":"17655_CR31","doi-asserted-by":"publisher","first-page":"1525","DOI":"10.1007\/s12652-021-03022-1","volume":"13","author":"Y Wei","year":"2022","unstructured":"Wei Y, Gong Z, Yang S, Ye K, Wen Y (2022) EdgeCRNN: an edge-computing oriented model of acoustic feature enhancement for keyword spotting. J Ambient Intell Human Comput 13:1525\u20131535. https:\/\/doi.org\/10.1007\/s12652-021-03022-1","journal-title":"J Ambient Intell Human Comput"},{"key":"17655_CR32","doi-asserted-by":"publisher","first-page":"9037","DOI":"10.1007\/s12652-020-02598-4","volume":"12","author":"N Saleem","year":"2021","unstructured":"Saleem N, Khattak MI, Al-Hasan M, Jan A (2021) Multi-objective long-short term memory recurrent neural networks for speech enhancement. J Ambient Intell Human Comput 12:9037\u20139052. https:\/\/doi.org\/10.1007\/s12652-020-02598-4","journal-title":"J Ambient Intell Human Comput"},{"key":"17655_CR33","doi-asserted-by":"publisher","first-page":"895","DOI":"10.1007\/s12652-016-0395-y","volume":"8","author":"TH Yang","year":"2017","unstructured":"Yang TH, Wu CH, Huang KY, Su MH (2017) Coupled HMM-based multimodal fusion for mood disorder detection through elicited audio\u2013visual signals. J Ambient Intell Human Comput 8:895\u2013906. https:\/\/doi.org\/10.1007\/s12652-016-0395-y","journal-title":"J Ambient Intell Human Comput"},{"key":"17655_CR34","doi-asserted-by":"publisher","DOI":"10.1016\/j.jocs.2023.101970","volume":"67","author":"R Khanduzi","year":"2023","unstructured":"Khanduzi R, Sangaiah AK (2023) An efficient recurrent neural network for defensive Stackelberg game. J Comput Sci 67:101970. https:\/\/doi.org\/10.1016\/j.jocs.2023.101970","journal-title":"J Comput Sci"},{"key":"17655_CR35","doi-asserted-by":"publisher","DOI":"10.1016\/j.asoc.2022.108485","volume":"118","author":"J Zhang","year":"2022","unstructured":"Zhang J, Feng W, Yuan T, Wang J, Sangaiah AK (2022) SCSTCF: Spatial-channel selection and temporal regularized correlation filters for visual tracking. Applied Soft Comput 118:108485. https:\/\/doi.org\/10.1016\/j.asoc.2022.108485","journal-title":"Applied Soft Comput"}],"container-title":["Multimedia Tools and Applications"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/link.springer.com\/content\/pdf\/10.1007\/s11042-023-17655-1.pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/link.springer.com\/article\/10.1007\/s11042-023-17655-1\/fulltext.html","content-type":"text\/html","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/link.springer.com\/content\/pdf\/10.1007\/s11042-023-17655-1.pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,9,10]],"date-time":"2025-09-10T11:28:01Z","timestamp":1757503681000},"score":1,"resource":{"primary":{"URL":"https:\/\/link.springer.com\/10.1007\/s11042-023-17655-1"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2023,11,21]]},"references-count":35,"journal-issue":{"issue":"29","published-online":{"date-parts":[[2025,9]]}},"alternative-id":["17655"],"URL":"https:\/\/doi.org\/10.1007\/s11042-023-17655-1","relation":{},"ISSN":["1573-7721"],"issn-type":[{"type":"electronic","value":"1573-7721"}],"subject":[],"published":{"date-parts":[[2023,11,21]]},"assertion":[{"value":"27 April 2023","order":1,"name":"received","label":"Received","group":{"name":"ArticleHistory","label":"Article History"}},{"value":"22 August 2023","order":2,"name":"revised","label":"Revised","group":{"name":"ArticleHistory","label":"Article History"}},{"value":"2 November 2023","order":3,"name":"accepted","label":"Accepted","group":{"name":"ArticleHistory","label":"Article History"}},{"value":"21 November 2023","order":4,"name":"first_online","label":"First Online","group":{"name":"ArticleHistory","label":"Article History"}},{"order":1,"name":"Ethics","group":{"name":"EthicsHeading","label":"Declarations"}},{"value":"The authors declare no conflict of interest. The funders had no role in the study's design; in the collection, analyses, or interpretation of data; in the writing of the manuscript, or in the decision to publish the results. The authors have no other competing interests to declare relevant to this article's content.","order":2,"name":"Ethics","group":{"name":"EthicsHeading","label":"Conflicts of Interest"}}]}}