{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,7,9]],"date-time":"2026-07-09T15:45:37Z","timestamp":1783611937817,"version":"3.55.0"},"reference-count":57,"publisher":"Springer Science and Business Media LLC","issue":"3","license":[{"start":{"date-parts":[[2024,4,30]],"date-time":"2024-04-30T00:00:00Z","timestamp":1714435200000},"content-version":"tdm","delay-in-days":0,"URL":"https:\/\/www.springernature.com\/gp\/researchers\/text-and-data-mining"},{"start":{"date-parts":[[2024,4,30]],"date-time":"2024-04-30T00:00:00Z","timestamp":1714435200000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/www.springernature.com\/gp\/researchers\/text-and-data-mining"}],"content-domain":{"domain":["link.springer.com"],"crossmark-restriction":false},"short-container-title":["Cogn Comput"],"published-print":{"date-parts":[[2024,5]]},"DOI":"10.1007\/s12559-024-10288-y","type":"journal-article","created":{"date-parts":[[2024,4,30]],"date-time":"2024-04-30T09:01:42Z","timestamp":1714467702000},"page":"1221-1236","update-policy":"https:\/\/doi.org\/10.1007\/springer_crossmark_policy","source":"Crossref","is-referenced-by-count":21,"title":["Towards Efficient Recurrent Architectures: A Deep LSTM Neural Network Applied to Speech Enhancement and Recognition"],"prefix":"10.1007","volume":"16","author":[{"given":"Jing","family":"Wang","sequence":"first","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-0010-0629","authenticated-orcid":false,"given":"Nasir","family":"Saleem","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Teddy Surya","family":"Gunawan","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"297","published-online":{"date-parts":[[2024,4,30]]},"reference":[{"issue":"2","key":"10288_CR1","doi-asserted-by":"publisher","first-page":"113","DOI":"10.1109\/TASSP.1979.1163209","volume":"27","author":"S Boll","year":"1979","unstructured":"Boll S. Suppression of acoustic noise in speech using spectral subtraction. IEEE Trans Acoust Speech Signal Process. 1979;27(2):113\u201320.","journal-title":"IEEE Trans Acoust Speech Signal Process"},{"issue":"6","key":"10288_CR2","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. Speech enhancement with geometric advent of spectral subtraction using connected time-frequency regions noise estimation. Res J Appl Sci Eng Technol. 2013;6(6):1081\u20137.","journal-title":"Res J Appl Sci Eng Technol"},{"issue":"3","key":"10288_CR3","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. All-pole modeling of degraded speech. IEEE Trans Acoust Speech Signal Process. 1978;26(3):197\u2013210.","journal-title":"IEEE Trans Acoust Speech Signal Process"},{"issue":"6","key":"10288_CR4","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. Speech enhancement using a minimum-mean square error short-time spectral amplitude estimator. IEEE Trans Acoust Speech Signal Process. 1984;32(6):1109\u201321.","journal-title":"IEEE Trans Acoust Speech Signal Process"},{"issue":"10","key":"10288_CR5","doi-asserted-by":"publisher","first-page":"2140","DOI":"10.1109\/TASL.2013.2270369","volume":"21","author":"N Mohammadiha","year":"2013","unstructured":"Mohammadiha N, Smaragdis P, Leijon A. Supervised and unsupervised speech enhancement using nonnegative matrix factorization. IEEE Trans Audio Speech Lang Process. 2013;21(10):2140\u201351.","journal-title":"IEEE Trans Audio Speech Lang Process"},{"issue":"1","key":"10288_CR6","doi-asserted-by":"publisher","first-page":"65","DOI":"10.1109\/LSP.2013.2291240","volume":"21","author":"Y Xu","year":"2013","unstructured":"Xu Y, Du J, Dai L-R, Lee C-H. An experimental study on speech enhancement based on deep neural networks. IEEE Signal Process Lett. 2013;21(1):65\u20138.","journal-title":"IEEE Signal Process Lett"},{"issue":"1","key":"10288_CR7","doi-asserted-by":"publisher","first-page":"7","DOI":"10.1109\/TASLP.2014.2364452","volume":"23","author":"Y Xu","year":"2014","unstructured":"Xu Y, Du J, Dai L-R, Lee C-H. A regression approach to speech enhancement based on deep neural networks. IEEE\/ACM Trans Audio Speech Lang Process. 2014;23(1):7\u201319.","journal-title":"IEEE\/ACM Trans Audio Speech Lang Process"},{"issue":"12","key":"10288_CR8","doi-asserted-by":"publisher","first-page":"1849","DOI":"10.1109\/TASLP.2014.2352935","volume":"22","author":"Y Wang","year":"2014","unstructured":"Wang Y, Narayanan A, Wang D. On training targets for supervised speech separation. IEEE\/ACM Trans Audio Speech Lang Process. 2014;22(12):1849\u201358.","journal-title":"IEEE\/ACM Trans Audio Speech Lang Process"},{"issue":"1","key":"10288_CR9","first-page":"84","volume":"6","author":"N Saleem","year":"2020","unstructured":"Saleem N, Khattak MI. Deep neural networks for speech enhancement in complex-noisy environments. Int J Interactive Multimed Artif Intell. 2020;6(1):84.","journal-title":"Int J Interactive Multimed Artif Intell"},{"key":"10288_CR10","doi-asserted-by":"publisher","DOI":"10.1016\/j.asoc.2020.106666","volume":"95","author":"N Saleem","year":"2020","unstructured":"Saleem N, Khattak MI. Multi-scale decomposition based supervised single channel deep speech enhancement. Appl Soft Comput. 2020;95: 106666.","journal-title":"Appl Soft Comput"},{"key":"10288_CR11","doi-asserted-by":"publisher","first-page":"5039","DOI":"10.1109\/ICASSP.2018.8462068","volume-title":"2018 IEEE international conference on acoustics, speech and signal processing (ICASSP)","author":"MH Soni","year":"2018","unstructured":"Soni MH, Shah N, Patil HA. Time-frequency masking-based speech enhancement using generative adversarial network. In: 2018 IEEE international conference on acoustics, speech and signal processing (ICASSP). IEEE; 2018. p. 5039\u201343."},{"key":"10288_CR12","doi-asserted-by":"publisher","first-page":"1152","DOI":"10.1007\/s12559-020-09817-2","volume":"14","author":"W Yu","year":"2022","unstructured":"Yu W, Zhou J, Wang H, et al. SETransformer: speech enhancement transformer. Cogn Comput. 2022;14:1152\u20138. https:\/\/doi.org\/10.1007\/s12559-020-09817-2.","journal-title":"Cogn Comput"},{"key":"10288_CR13","unstructured":"Sutskever I, Vinyals O, Le QV. Sequence to sequence learning with neural networks. Adv Neural Inf Process Syst. 2014;27."},{"key":"10288_CR14","volume-title":"Building end-to-end dialogue systems using generative hierarchical neural network models","author":"I Serban","year":"2016","unstructured":"Serban I, Sordoni A, Bengio Y, Courville A, Pineau J. Building end-to-end dialogue systems using generative hierarchical neural network models, vol. 30, no. 1. Proceedings of the AAAI conference on artificial intelligence; 2016."},{"key":"10288_CR15","doi-asserted-by":"publisher","first-page":"1927","DOI":"10.1109\/TASLP.2023.3275033","volume":"31","author":"QS Zhu","year":"2023","unstructured":"Zhu QS, Zhang J, Zhang ZQ, Dai LR. A joint speech enhancement and self-supervised representation learning framework for noise-robust speech recognition. IEEE\/ACM Trans Audio Speech Lang Process. 2023;31:1927\u201339.","journal-title":"IEEE\/ACM Trans Audio Speech Lang Process"},{"issue":"1","key":"10288_CR16","doi-asserted-by":"publisher","first-page":"153","DOI":"10.1109\/TASLP.2016.2628641","volume":"25","author":"M Kolb\u00e6k","year":"2016","unstructured":"Kolb\u00e6k M, Tan Z-H, Jensen J. Speech intelligibility potential of general and specialized deep neural network based speech enhancement systems. IEEE\/ACM transactions on audio, speech, and language processing. 2016;25(1):153\u201367.","journal-title":"IEEE\/ACM transactions on audio, speech, and language processing"},{"issue":"6","key":"10288_CR17","doi-asserted-by":"publisher","first-page":"4705","DOI":"10.1121\/1.4986931","volume":"141","author":"J Chen","year":"2017","unstructured":"Chen J, Wang D. Long short-term memory for speaker generalization in supervised speech separation. The Journal of the Acoustical Society of America. 2017;141(6):4705\u201314.","journal-title":"The Journal of the Acoustical Society of America"},{"issue":"3","key":"10288_CR18","doi-asserted-by":"publisher","first-page":"517","DOI":"10.1109\/TASLP.2015.2400218","volume":"23","author":"M Sundermeyer","year":"2015","unstructured":"Sundermeyer M, Ney H, Schl\u00a8uter R. From feedforward to recurrent lstm neural networks for language modeling. IEEE\/ACM transactions on audio, speech, and language processing. 2015;23(3):517\u201329.","journal-title":"IEEE\/ACM transactions on audio, speech, and language processing"},{"issue":"8","key":"10288_CR19","doi-asserted-by":"publisher","first-page":"1735","DOI":"10.1162\/neco.1997.9.8.1735","volume":"9","author":"S Hochreiter","year":"1997","unstructured":"Hochreiter S, Schmidhuber J. Long short-term memory. Neural Comput. 1997;9(8):1735\u201380.","journal-title":"Neural Comput"},{"key":"10288_CR20","doi-asserted-by":"publisher","first-page":"103976","DOI":"10.1016\/j.engappai.2020.103976","volume":"96","author":"M Fern\u00b4andez-D\u00b4\u0131az","year":"2020","unstructured":"Fern\u00b4andez-D\u00b4\u0131az M, Gallardo-Antol\u00b4\u0131n A. An attention long short-term memory based system for automatic classification of speech intelligibility. Eng Appl Artif Intell. 2020;96:103976.","journal-title":"Eng Appl Artif Intell"},{"key":"10288_CR21","doi-asserted-by":"publisher","DOI":"10.1016\/j.knosys.2021.107914","volume":"238","author":"N Saleem","year":"2022","unstructured":"Saleem N, Gao J, Khattak MI, Rauf HT, Kadry S, Shafi M. Deepresgru: residual gated recurrent neural network-augmented kalman filtering for speech enhancement and recognition. Knowl-Based Syst. 2022;238: 107914.","journal-title":"Knowl-Based Syst"},{"key":"10288_CR22","doi-asserted-by":"publisher","first-page":"24013","DOI":"10.1007\/s11042-019-08293-7","volume":"79","author":"SA El-Moneim","year":"2020","unstructured":"El-Moneim SA, Nassar M, Dessouky MI, Ismail NA, El-Fishawy AS, Abd El-Samie FE. Text-independent speaker recognition using lstm-rnn and speech enhancement. Multimedia tools and applications. 2020;79:24013\u201328.","journal-title":"Multimedia tools and applications"},{"key":"10288_CR23","unstructured":"Chang B, Meng L, Haber E, Tung F, Begert D. Multi-level residual networks from dynamical systems view. arXiv preprint; 2017.\u00a0arXiv:171010348."},{"key":"10288_CR24","doi-asserted-by":"publisher","first-page":"1","DOI":"10.1186\/s13634-020-00707-1","volume":"2020","author":"M Strake","year":"2020","unstructured":"Strake M, Defraene B, Fluyt K, Tirry W, Fingscheidt T. Speech enhancement by lstm-based noise suppression followed by cnn-based speech restoration. EURASIP Journal on Advances in Signal Processing. 2020;2020:1\u201326.","journal-title":"EURASIP Journal on Advances in Signal Processing"},{"key":"10288_CR25","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. Lstm-convolutional-blstm encoder-decoder network for minimum mean-square error approach to speech enhancement. Appl Acoust. 2021;172: 107647.","journal-title":"Appl Acoust"},{"key":"10288_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. Real-time speech enhancement algorithm based on attention lstm. IEEE Access. 2020;8:48464\u201376.","journal-title":"IEEE Access"},{"key":"10288_CR27","doi-asserted-by":"crossref","unstructured":"Li X, Horaud R. Online monaural speech enhancement using delayed subband LSTM. Interspeech; 2020. p. 2462\u20136. arXiv:2005.05037.","DOI":"10.21437\/Interspeech.2020-2091"},{"key":"10288_CR28","doi-asserted-by":"crossref","unstructured":"Zhang S, Kong Y, Lv S, Hu Y, Xie L. FT-LSTM based complex network for joint acoustic echo cancellation and speech enhancement. arXiv preprint; 2021.\u00a0arXiv:2106.07577.","DOI":"10.21437\/Interspeech.2021-1359"},{"key":"10288_CR29","doi-asserted-by":"crossref","unstructured":"Fedorov I, Stamenovic M, Jensen C, Yang LC, Mandell A, Gan Y, Mattina M, Whatmough PN. TinyLSTMs: efficient neural speech enhancement for hearing aids. arXiv preprint; 2020.\u00a0arXiv:2005.11138.","DOI":"10.21437\/Interspeech.2020-1864"},{"key":"10288_CR30","first-page":"2702","volume-title":"Bidirectional LSTM network with ordered neurons for speech enhancement","author":"X Li","year":"2020","unstructured":"Li X, Li Y, Dong Y, Xu S, Zhang Z, Wang D, Xiong S. Bidirectional LSTM network with ordered neurons for speech enhancement. Inter Speech; 2020. p. 2702\u20136."},{"issue":"10","key":"10288_CR31","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. Multi-objective long-short term memory recurrent neural networks for speech enhancement. J Ambient Intell Humaniz Comput. 2021;12(10):9037\u201352.","journal-title":"J Ambient Intell Humaniz Comput"},{"key":"10288_CR32","unstructured":"Goswami RG, Andhavarapu S, Murty K. Phase aware speech enhancement using realisation of complex-valued LSTM. arXiv preprint; 2020.\u00a0arXiv:2010.14122."},{"key":"10288_CR33","doi-asserted-by":"crossref","unstructured":"Westhausen NL, Meyer BT. Dual-signal transformation LSTM network for real-time noise suppression. Proc. Interspeech; 2020. p. 2477\u201381. arXiv:2005.07551.","DOI":"10.21437\/Interspeech.2020-2631"},{"issue":"3","key":"10288_CR34","doi-asserted-by":"publisher","first-page":"3647","DOI":"10.1007\/s11042-022-13302-3","volume":"82","author":"A Garg","year":"2023","unstructured":"Garg A. Speech enhancement using long short term memory with trained speech features and adaptive wiener filter. Multimedia tools and applications. 2023;82(3):3647\u201375.","journal-title":"Multimedia tools and applications"},{"key":"10288_CR35","first-page":"1","volume-title":"ICASSP 2023-2023 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)","author":"J Yu","year":"2023","unstructured":"Yu J, Luo Y. Efficient monaural speech enhancement with universal sample rate band-split rnn. In: ICASSP 2023-2023 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP). IEEE; 2023. p. 1\u20135."},{"key":"10288_CR36","doi-asserted-by":"publisher","DOI":"10.1016\/j.bspc.2022.104408","volume":"80","author":"Y Korkmaz","year":"2023","unstructured":"Korkmaz Y, Boyac\u0131 A. Hybrid voice activity detection system based on lstm and auditory speech features. Biomed Signal Process Control. 2023;80: 104408.","journal-title":"Biomed Signal Process Control"},{"key":"10288_CR37","doi-asserted-by":"publisher","first-page":"27403","DOI":"10.6028\/NIST.IR.4930","volume-title":"DARPA TIMIT acoustic-phonetic continous speech corpus CD-ROM. NIST speech disc 1-1.1","author":"JS Garofolo","year":"1993","unstructured":"Garofolo JS, Lamel LF, Fisher WM, Fiscus JG, Pallett DS. DARPA TIMIT acoustic-phonetic continous speech corpus CD-ROM. NIST speech disc 1-1.1, vol. 93. NASA STI\/Recon technical report n; 1993. p. 27403."},{"key":"10288_CR38","first-page":"5206","volume-title":"Librispeech: an asr corpus based on public domain audio books","author":"V Panayotov","year":"2015","unstructured":"Panayotov V, Chen G, Povey D, Khudanpur S. Librispeech: an asr corpus based on public domain audio books. 2015\u00a0IEEE international conference on acoustics speech and signal processing\u00a0(ICASSP); 2015. p. 5206\u201310."},{"key":"10288_CR39","volume-title":"Aurora working group: DSR front end LVCSR evaluation AU\/384\/02","author":"D Pearce","year":"2002","unstructured":"Pearce D, Picone J. Aurora working group: DSR front end LVCSR evaluation AU\/384\/02. Inst. for Signal & Inform. Process., Mississippi State Univ., Tech. Rep.; 2002."},{"issue":"3","key":"10288_CR40","doi-asserted-by":"publisher","first-page":"247","DOI":"10.1016\/0167-6393(93)90095-3","volume":"12","author":"A Varga","year":"1993","unstructured":"Varga A, Steeneken H, et al. Noisex-92: A database and an experiment to study the effect of additive noise on speech recognition systems. Speech Commun. 1993;12(3):247\u201353.","journal-title":"Speech Commun"},{"issue":"10","key":"10288_CR41","first-page":"755","volume":"50","author":"AW Rix","year":"2002","unstructured":"Rix AW, Hollier MP, Hekstra AP, Beerends JG. Perceptual evaluation of speech quality (pesq) the new itu standard for end-to-end speech quality assessment part i\u2013time-delay compensation. Journal of the Audio Engineering Society. 2002;50(10):755\u201364.","journal-title":"Journal of the Audio Engineering Society"},{"key":"10288_CR42","doi-asserted-by":"publisher","first-page":"4214","DOI":"10.1109\/ICASSP.2010.5495701","volume-title":"2010 IEEE international conference on acoustics, speech and signal processing","author":"CH Taal","year":"2010","unstructured":"Taal CH, Hendriks RC, Heusdens R, Jensen J. A short-time objective intelligibility measure for time-frequency weighted noisy speech. In: 2010 IEEE international conference on acoustics, speech and signal processing. IEEE; 2010. p. 4214\u20137."},{"key":"10288_CR43","first-page":"1447","volume-title":"Evaluation of objective measures for speech enhancement","author":"H Yi","year":"2006","unstructured":"Yi H. Evaluation of objective measures for speech enhancement. Pittsburgh, Pennsylvania: Interspeech; 2006. p. 1447\u201350."},{"key":"10288_CR44","first-page":"1","volume-title":"2017 IEEE International Workshop of Electronics, Control, Measurement, Signals and their Application to Mechatronics (ECMSM)","author":"T Kounovsky","year":"2017","unstructured":"Kounovsky T, Malek J. Single channel speech enhancement using convolutional neural network. In: 2017 IEEE International Workshop of Electronics, Control, Measurement, Signals and their Application to Mechatronics (ECMSM). IEEE; 2017. p. 1\u20135."},{"issue":"12","key":"10288_CR45","doi-asserted-by":"publisher","first-page":"1862","DOI":"10.1109\/LSP.2016.2627029","volume":"23","author":"P Sun","year":"2016","unstructured":"Sun P, Qin J. Low-rank and sparsity analysis applied to speech enhancement via online estimated dictionary. IEEE Signal Process Lett. 2016;23(12):1862\u20136.","journal-title":"IEEE Signal Process Lett"},{"key":"10288_CR46","doi-asserted-by":"publisher","first-page":"179","DOI":"10.1109\/ICIS.2017.7959990","volume-title":"2017 IEEE\/ACIS 16th International Conference on Computer and Information Science (ICIS)","author":"W Shi","year":"2017","unstructured":"Shi W, Zhang X, Zou X, Han W, Min G. Auditory mask estimation by RPCA for monaural speech enhancement. In: 2017 IEEE\/ACIS 16th International Conference on Computer and Information Science (ICIS). IEEE; 2017. p. 179\u201384."},{"key":"10288_CR47","first-page":"3229","volume":"2018","author":"K Tan","year":"2018","unstructured":"Tan K, Wang D. A convolutional recurrent neural network for real-time speech enhancement. In: Interspeech. 2018;2018:3229\u201333.","journal-title":"In: Interspeech"},{"key":"10288_CR48","unstructured":"Zhou L, Gao Y, Wang Z, Li J, Zhang W. Complex spectral mapping with attention based convolution recurrent neural network for speech enhancement. arXiv preprint; 2021.\u00a0arXiv:2104.05267."},{"key":"10288_CR49","volume-title":"IEEE 2011 workshop on automatic speech recognition and understanding","author":"D Povey","year":"2011","unstructured":"Povey D, Ghoshal A, Boulianne G, Burget L, Glembek O, Goel N, Hannemann M, Motlicek P, Qian Y, Schwarz P, Silovsky J. The Kaldi speech recognition toolkit. In: IEEE 2011 workshop on automatic speech recognition and understanding. IEEE Signal Processing Society; 2011."},{"key":"10288_CR50","volume-title":"SEGAN: speech enhancement generative adversarial network","author":"S Pascual","year":"2017","unstructured":"Pascual S, Bonafonte A, Serr\u00e0 J. SEGAN: speech enhancement generative adversarial network. Interspeech; 2017."},{"key":"10288_CR51","doi-asserted-by":"publisher","first-page":"106","DOI":"10.1109\/ICASSP.2019.8683799","volume-title":"ICASSP 2019-2019 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)","author":"D Baby","year":"2019","unstructured":"Baby D, Verhulst S. Sergan: Speech enhancement using relativistic generative adversarial networks with gradient penalty. In: ICASSP 2019-2019 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP). IEEE; 2019. p. 106\u201310."},{"key":"10288_CR52","volume-title":"DCCRN: deep complex convolution recurrent network for phase-aware speech enhancement","author":"Y Hu","year":"2020","unstructured":"Hu Y, Liu Y, Lv S, Xing M, Zhang S, Fu Y, Wu J, Zhang B, Xie L. DCCRN: deep complex convolution recurrent network for phase-aware speech enhancement. Interspeech; 2020."},{"key":"10288_CR53","doi-asserted-by":"publisher","first-page":"7767","DOI":"10.1109\/ICASSP43922.2022.9747029","volume-title":"ICASSP 2022-2022 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)","author":"S Lv","year":"2022","unstructured":"Lv S, Fu Y, Xing M, Sun J, Xie L, Huang J, Wang Y, Yu T. S-dccrn: Super wide band dccrn with learnable complex feature for speech enhancement. In: ICASSP 2022-2022 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP). IEEE; 2022. p. 7767\u201371."},{"key":"10288_CR54","doi-asserted-by":"crossref","unstructured":"Defossez A, Synnaeve G, Adi Y. Real time speech enhancement in the waveform domain. arXiv preprint\u00a0arXiv:2006.12847. 2020.","DOI":"10.21437\/Interspeech.2020-2409"},{"key":"10288_CR55","doi-asserted-by":"publisher","first-page":"7857","DOI":"10.1109\/ICASSP43922.2022.9747888","volume-title":"ICASSP 2022-2022 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)","author":"J Chen","year":"2022","unstructured":"Chen J, Wang Z, Tuo D, Wu Z, Kang S, Meng H. Fullsubnet+: channel attention fullsubnet with complex spectrograms for speech enhancement. In: ICASSP 2022-2022 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP). IEEE; 2022. p. 7857\u201361."},{"key":"10288_CR56","doi-asserted-by":"publisher","first-page":"196","DOI":"10.1016\/j.neucom.2022.11.081","volume":"527","author":"LA Passos","year":"2023","unstructured":"Passos LA, Papa JP, Hussain A, Adeel A. Canonical cortical graph neural networks and its application for speech enhancement in audio-visual hearing aids. Neurocomputing. 2023;527:196\u2013203.","journal-title":"Neurocomputing"},{"issue":"5","key":"10288_CR57","doi-asserted-by":"publisher","first-page":"833","DOI":"10.1109\/TAI.2022.3169995","volume":"3","author":"T Hussain","year":"2022","unstructured":"Hussain T, Wang W-C, Gogate M, Dashtipour K, Tsao Y, Lu X, Ahsan A, Hussain A. A novel temporal attentive-pooling based convolutional recurrent architecture for acoustic signal enhancement. IEEE transactions on artificial intelligence. 2022;3(5):833\u201342.","journal-title":"IEEE transactions on artificial intelligence"}],"container-title":["Cognitive Computation"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/link.springer.com\/content\/pdf\/10.1007\/s12559-024-10288-y.pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/link.springer.com\/article\/10.1007\/s12559-024-10288-y\/fulltext.html","content-type":"text\/html","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/link.springer.com\/content\/pdf\/10.1007\/s12559-024-10288-y.pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2024,6,1]],"date-time":"2024-06-01T09:01:49Z","timestamp":1717232509000},"score":1,"resource":{"primary":{"URL":"https:\/\/link.springer.com\/10.1007\/s12559-024-10288-y"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2024,4,30]]},"references-count":57,"journal-issue":{"issue":"3","published-print":{"date-parts":[[2024,5]]}},"alternative-id":["10288"],"URL":"https:\/\/doi.org\/10.1007\/s12559-024-10288-y","relation":{},"ISSN":["1866-9956","1866-9964"],"issn-type":[{"value":"1866-9956","type":"print"},{"value":"1866-9964","type":"electronic"}],"subject":[],"published":{"date-parts":[[2024,4,30]]},"assertion":[{"value":"12 June 2023","order":1,"name":"received","label":"Received","group":{"name":"ArticleHistory","label":"Article History"}},{"value":"10 April 2024","order":2,"name":"accepted","label":"Accepted","group":{"name":"ArticleHistory","label":"Article History"}},{"value":"30 April 2024","order":3,"name":"first_online","label":"First Online","group":{"name":"ArticleHistory","label":"Article History"}},{"order":1,"name":"Ethics","group":{"name":"EthicsHeading","label":"Declarations"}},{"value":"This article does not contain any studies on human participants or animals performed by any of the authors.","order":2,"name":"Ethics","group":{"name":"EthicsHeading","label":"Ethics Approval and Consent to Participate"}},{"value":"The authors declare no competing interests.","order":3,"name":"Ethics","group":{"name":"EthicsHeading","label":"Competing Interest"}}]}}