{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,7,3]],"date-time":"2026-07-03T05:22:57Z","timestamp":1783056177736,"version":"3.54.6"},"reference-count":74,"publisher":"Springer Science and Business Media LLC","issue":"6","license":[{"start":{"date-parts":[[2025,1,31]],"date-time":"2025-01-31T00:00:00Z","timestamp":1738281600000},"content-version":"tdm","delay-in-days":0,"URL":"https:\/\/www.springernature.com\/gp\/researchers\/text-and-data-mining"},{"start":{"date-parts":[[2025,1,31]],"date-time":"2025-01-31T00:00:00Z","timestamp":1738281600000},"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":["Circuits Syst Signal Process"],"published-print":{"date-parts":[[2025,6]]},"DOI":"10.1007\/s00034-025-03010-2","type":"journal-article","created":{"date-parts":[[2025,1,31]],"date-time":"2025-01-31T19:15:29Z","timestamp":1738350929000},"page":"4224-4257","update-policy":"https:\/\/doi.org\/10.1007\/springer_crossmark_policy","source":"Crossref","is-referenced-by-count":13,"title":["Single Channel Speech Enhancement using a Complex Dual-Path Multi Axial Transformer with Frequency Prompt"],"prefix":"10.1007","volume":"44","author":[{"given":"Chaitanya","family":"Jannu","sequence":"first","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Manaswini","family":"Burra","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Sunny Dayal","family":"Vanambathina","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Veeraswamy","family":"Parisae","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Chinta Venkata Murali","family":"Krishna","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"G. L.","family":"Madhumati","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"297","published-online":{"date-parts":[[2025,1,31]]},"reference":[{"key":"3010_CR1","unstructured":"Y. Bengio, C. Pal, Deep complex networks, in International Conference on Learning Representations (ICLR) (2018)"},{"key":"3010_CR2","doi-asserted-by":"crossref","unstructured":"R. Cao, S. Abdulatif, B. Yang, CMGAN: Conformer-based metric GAN for speech enhancement (2022). arXiv preprint arXiv:2203.15149","DOI":"10.36227\/techrxiv.21187846.v2"},{"issue":"10","key":"3010_CR3","doi-asserted-by":"publisher","first-page":"2825","DOI":"10.1016\/j.cnsns.2013.02.011","volume":"18","author":"CJ Cheng","year":"2013","unstructured":"C.J. Cheng, C.B. Cheng, An asymmetric image cryptosystem based on the adaptive synchronization of an uncertain unified chaotic system and a cellular neural network. Commun. Nonlinear Sci. Numer. Simul. 18(10), 2825\u20132837 (2013)","journal-title":"Commun. Nonlinear Sci. Numer. Simul."},{"key":"3010_CR4","doi-asserted-by":"crossref","unstructured":"R. Cheng, C. Bao, Y. Xiang, Speech enhancement with phase correction based on modified DNN architecture, in 2018 Asia-Pacific Signal and Information Processing Association Annual Summit and Conference (APSIPA ASC), pp. 1222\u20131227. (IEEE, 2018)","DOI":"10.23919\/APSIPA.2018.8659625"},{"key":"3010_CR5","doi-asserted-by":"crossref","unstructured":"F. Dang, H. Chen, P. Zhang, Dpt-fsnet: Dual-path transformer based full-band and sub-band fusion network for speech enhancement, in ICASSP 2022\u20132022 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP). (IEEE, 2022), pp. 6857\u20136861","DOI":"10.1109\/ICASSP43922.2022.9746171"},{"key":"3010_CR6","doi-asserted-by":"crossref","unstructured":"A. Defossez, G. Synnaeve, Y. Adi, Real time speech enhancement in the waveform domain. arXiv preprint arXiv:2006.12847 (2020)","DOI":"10.21437\/Interspeech.2020-2409"},{"key":"3010_CR7","doi-asserted-by":"crossref","unstructured":"Y. Fu, Y. Liu, J. Li et al., Uformer: A unet based dilated complex & real dual-path conformer network for simultaneous speech enhancement and dereverberation, in ICASSP 2022\u20132022 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP). (IEEE, 2022), pp. 7417\u20137421","DOI":"10.1109\/ICASSP43922.2022.9746020"},{"key":"3010_CR8","doi-asserted-by":"crossref","unstructured":"E.M. Grais, D. Ward, M.D. Plumbley, Raw multi-channel audio source separation using multi-resolution convolutional auto-encoders, in 2018 26th European Signal Processing Conference (EUSIPCO), pp. 1577\u20131581 (IEEE, 2018)","DOI":"10.23919\/EUSIPCO.2018.8553571"},{"key":"3010_CR9","doi-asserted-by":"crossref","unstructured":"A. Gulati, J. Qin, C.C. Chiu, et\u00a0al., Conformer: Convolution-augmented transformer for speech recognition. arXiv preprint arXiv:2005.08100 (2020)","DOI":"10.21437\/Interspeech.2020-3015"},{"key":"3010_CR10","doi-asserted-by":"publisher","first-page":"146","DOI":"10.1109\/OJITS.2022.3147816","volume":"3","author":"X Han","year":"2022","unstructured":"X. Han, M. Pan, Z. Li et al., Vhf speech enhancement based on transformer. IEEE Open J. Intell. Transp. Syst. 3, 146\u2013152 (2022)","journal-title":"IEEE Open J. Intell. Transp. Syst."},{"key":"3010_CR11","doi-asserted-by":"publisher","first-page":"588","DOI":"10.1016\/j.specom.2006.12.006","volume":"49","author":"Y Hu","year":"2007","unstructured":"Y. Hu, Subjective evaluation and comparison of speech enhancement algorithms. Speech Commun. 49, 588\u2013601 (2007)","journal-title":"Speech Commun."},{"issue":"1","key":"3010_CR12","doi-asserted-by":"publisher","first-page":"229","DOI":"10.1109\/TASL.2007.911054","volume":"16","author":"Y Hu","year":"2007","unstructured":"Y. Hu, P.C. Loizou, Evaluation of objective quality measures for speech enhancement. IEEE Trans. Audio Speech Lang. Process. 16(1), 229\u2013238 (2007)","journal-title":"IEEE Trans. Audio Speech Lang. Process."},{"key":"3010_CR13","doi-asserted-by":"crossref","unstructured":"Y. Hu, Y. Liu, S. Lv, et\u00a0al. DCCRN: Deep complex convolution recurrent network for phase-aware speech enhancement. arXiv preprint arXiv:2008.00264 (2020)","DOI":"10.21437\/Interspeech.2020-2537"},{"key":"3010_CR14","doi-asserted-by":"crossref","unstructured":"P.S. Huang, M. Kim, M. Hasegawa-Johnson et al., Deep learning for monaural speech separation, in 2014 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP), pp. 1562\u20131566. (IEEE, 2014)","DOI":"10.1109\/ICASSP.2014.6853860"},{"key":"3010_CR15","doi-asserted-by":"crossref","unstructured":"U. Isik, R. Giri, N. Phansalkar, et\u00a0al. Poconet: Better speech enhancement with frequency-positional embeddings, semi-supervised conversational data, and biased loss. arXiv preprint arXiv:2008.04470 (2020)","DOI":"10.21437\/Interspeech.2020-3027"},{"key":"3010_CR16","doi-asserted-by":"crossref","unstructured":"C. Jannu, S.D. Vanambathina, Convolutional transformer based local and global feature learning for speech enhancement. Int. J. Adv. Comput. Sci. Appl. 14(1) (2023)","DOI":"10.14569\/IJACSA.2023.0140181"},{"issue":"12","key":"3010_CR17","doi-asserted-by":"publisher","first-page":"7467","DOI":"10.1007\/s00034-023-02455-7","volume":"42","author":"C Jannu","year":"2023","unstructured":"C. Jannu, S.D. Vanambathina, Multi-stage progressive learning-based speech enhancement using time-frequency attentive squeezed temporal convolutional networks. Circuits Syst. Signal Process. 42(12), 7467\u20137493 (2023)","journal-title":"Circuits Syst. Signal Process."},{"issue":"1","key":"3010_CR18","doi-asserted-by":"publisher","first-page":"197","DOI":"10.1007\/s10772-023-10020-5","volume":"26","author":"C Jannu","year":"2023","unstructured":"C. Jannu, S.D. Vanambathina, Weibull and Nakagami speech priors based regularized NMF with adaptive wiener filter for speech enhancement. Int. J. Speech Technol. 26(1), 197\u2013209 (2023)","journal-title":"Int. J. Speech Technol."},{"key":"3010_CR19","doi-asserted-by":"crossref","unstructured":"E. Kim, H. Seo, Se-conformer: Time-domain speech enhancement using conformer, in Interspeech, pp. 2736\u20132740 (2021)","DOI":"10.21437\/Interspeech.2021-2207"},{"issue":"12","key":"3010_CR20","doi-asserted-by":"publisher","first-page":"1931","DOI":"10.1109\/TASLP.2014.2354236","volume":"22","author":"M Krawczyk","year":"2014","unstructured":"M. Krawczyk, T. Gerkmann, STFT phase reconstruction in voiced speech for an improved single-channel speech enhancement. IEEE\/ACM Trans. Audio Speech Lang. Process. 22(12), 1931\u20131940 (2014)","journal-title":"IEEE\/ACM Trans. Audio Speech Lang. Process."},{"issue":"5","key":"3010_CR21","doi-asserted-by":"publisher","first-page":"598","DOI":"10.1109\/LSP.2014.2365040","volume":"22","author":"J Kulmer","year":"2014","unstructured":"J. Kulmer, P. Mowlaee, Phase estimation in single channel speech enhancement using phase decomposition. IEEE Signal Process. Lett. 22(5), 598\u2013602 (2014)","journal-title":"IEEE Signal Process. Lett."},{"key":"3010_CR22","doi-asserted-by":"publisher","DOI":"10.1016\/j.apacoust.2021.108499","volume":"187","author":"A Li","year":"2022","unstructured":"A. Li, C. Zheng, L. Zhang et al., Glance and gaze: a collaborative learning framework for single-channel speech enhancement. Appl. Acoust. 187, 108499 (2022)","journal-title":"Appl. Acoust."},{"key":"3010_CR23","doi-asserted-by":"publisher","first-page":"1511","DOI":"10.1109\/TASLP.2023.3265839","volume":"31","author":"Y Li","year":"2023","unstructured":"Y. Li, Y. Sun, W. Wang et al., U-shaped transformer with frequency-band aware attention for speech enhancement. IEEE\/ACM Trans. Audio Speech Lang. Process. 31, 1511\u20131521 (2023)","journal-title":"IEEE\/ACM Trans. Audio Speech Lang. Process."},{"key":"3010_CR24","doi-asserted-by":"crossref","unstructured":"B. Lim, S. Son, H. Kim, et\u00a0al., Enhanced deep residual networks for single image super-resolution, in Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition Workshops, pp. 136\u2013144 (2017)","DOI":"10.1109\/CVPRW.2017.151"},{"key":"3010_CR25","doi-asserted-by":"crossref","unstructured":"N. Mamun, J.H. Hansen, Speech enhancement for cochlear implant recipients using deep complex convolution transformer with frequency transformation. IEEE\/ACM Trans. Audio Speech Lang Process. (2024)","DOI":"10.1109\/TASLP.2024.3366760"},{"key":"3010_CR26","unstructured":"Mozilla. Commonvoice. https:\/\/commonvoice.mozilla.org\/en (2017)"},{"key":"3010_CR27","doi-asserted-by":"publisher","first-page":"80","DOI":"10.1016\/j.specom.2020.10.004","volume":"125","author":"A Nicolson","year":"2020","unstructured":"A. Nicolson, K.K. Paliwal, Masked multi-head self-attention for causal speech enhancement. Speech Commun. 125, 80\u201396 (2020)","journal-title":"Speech Commun."},{"key":"3010_CR28","doi-asserted-by":"crossref","unstructured":"K. Paliwal, K. W\u00f3jcicki, B. Shannon, The importance of phase in speech enhancement. Speech Commun. 53(4), 465\u2013494 (2011)","DOI":"10.1016\/j.specom.2010.12.003"},{"key":"3010_CR29","doi-asserted-by":"crossref","unstructured":"V. Panayotov, G. Chen, D. Povey, et\u00a0al. Librispeech: an ASR corpus based on public domain audio books, in 2015 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP), pp 5206\u20135210 (IEEE, 2015)","DOI":"10.1109\/ICASSP.2015.7178964"},{"key":"3010_CR30","doi-asserted-by":"crossref","unstructured":"A. Pandey, D. Wang, TCNN: temporal convolutional neural network for real-time speech enhancement in the time domain, in ICASSP 2019\u20132019 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP). (IEEE, 2019), pp. 6875\u20136879","DOI":"10.1109\/ICASSP.2019.8683634"},{"key":"3010_CR31","doi-asserted-by":"crossref","unstructured":"V. Parisae, S.N. Bhavanam, Adaptive attention mechanism for single channel speech enhancement. Multimedia Tools Appl. 1\u201326 (2024)","DOI":"10.1007\/s11042-024-19076-0"},{"key":"3010_CR32","doi-asserted-by":"crossref","unstructured":"V. Parisae, S.N. Bhavanam, Multi scale encoder-decoder network with time frequency attention and s-TCN for single channel speech enhancement. J. Intell. Fuzzy Syst. (Preprint), 1\u201316 (2024)","DOI":"10.3233\/JIFS-233312"},{"key":"3010_CR33","doi-asserted-by":"crossref","unstructured":"V. Parisae, S.N. Bhavanam, Single channel speech enhancement using CNN with frequency dimension adaptive attention based squeeze-TCN, in 2024 2nd International Conference on Intelligent Data Communication Technologies and Internet of Things (IDCIoT), IEEE, pp. 674\u2013679 (2024)","DOI":"10.1109\/IDCIoT59759.2024.10467854"},{"key":"3010_CR34","doi-asserted-by":"crossref","unstructured":"V. Parisae, S. Nagakishore\u00a0Bhavanam, Stacked u-net with time\u2013frequency attention and deep connection net for single channel speech enhancement. Int. J. Image Graph. 2550067 (2024)","DOI":"10.1142\/S0219467825500676"},{"key":"3010_CR35","doi-asserted-by":"crossref","unstructured":"S. Pascual, A. Bonafonte, J. Serra, Segan: Speech enhancement generative adversarial network. arXiv preprint arXiv:1703.09452 (2017)","DOI":"10.21437\/Interspeech.2017-1428"},{"key":"3010_CR36","doi-asserted-by":"crossref","unstructured":"C.K. Reddy, H. Dubey, V. Gopal, et al., ICASSP 2021 deep noise suppression challenge, in ICASSP 2021\u20132021 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP). (IEEE, 2021), pp. 6623\u20136627","DOI":"10.1109\/ICASSP39728.2021.9415105"},{"key":"3010_CR37","doi-asserted-by":"crossref","unstructured":"D. Rethage, J. Pons, X. Serra, A wavenet for speech denoising, in 2018 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP). (IEEE, 2018), pp. 5069\u20135073","DOI":"10.1109\/ICASSP.2018.8462417"},{"key":"3010_CR38","doi-asserted-by":"crossref","unstructured":"A.W. Rix, J.G. Beerends, M.P. Hollier, et\u00a0al. Perceptual evaluation of speech quality (PESQ)-a new method for speech quality assessment of telephone networks and codecs, in 2001 IEEE international conference on acoustics, speech, and signal processing. Proceedings (Cat. No. 01CH37221), pp. 749\u2013752 (IEEE, 2001)","DOI":"10.1109\/ICASSP.2001.941023"},{"key":"3010_CR39","doi-asserted-by":"crossref","unstructured":"H. Shi, M. Mimura, L. Wang et al., Time-domain speech enhancement assisted by multi-resolution frequency encoder and decoder, in ICASSP 2023\u20132023 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP). (IEEE, 2023), pp. 1\u20135","DOI":"10.1109\/ICASSP49357.2023.10094718"},{"key":"3010_CR40","doi-asserted-by":"publisher","DOI":"10.1016\/j.neucom.2023.126498","volume":"550","author":"X Song","year":"2023","unstructured":"X. Song, N. Wu, S. Song et al., Bipartite synchronization for cooperative-competitive neural networks with reaction\u2013diffusion terms via dual event-triggered mechanism. Neurocomputing 550, 126498 (2023)","journal-title":"Neurocomputing"},{"key":"3010_CR41","doi-asserted-by":"publisher","DOI":"10.1016\/j.cnsns.2024.107945","volume":"132","author":"X Song","year":"2024","unstructured":"X. Song, Z. Peng, S. Song et al., Anti-disturbance state estimation for PDT-switched RDNNs utilizing time-sampling and space-splitting measurements. Commun. Nonlinear Sci. Numer. Simul. 132, 107945 (2024)","journal-title":"Commun. Nonlinear Sci. Numer. Simul."},{"key":"3010_CR42","doi-asserted-by":"crossref","unstructured":"M. Sperber, J. Niehues, G. Neubig, et\u00a0al., Self-attentional acoustic models. arXiv preprint arXiv:1803.09519 (2018)","DOI":"10.21437\/Interspeech.2018-1910"},{"issue":"1","key":"3010_CR43","doi-asserted-by":"publisher","first-page":"1434","DOI":"10.1038\/s41598-020-80713-3","volume":"11","author":"C Sun","year":"2021","unstructured":"C. Sun, M. Zhang, R. Wu et al., A convolutional recurrent neural network with attention framework for speech separation in monaural recordings. Sci. Rep. 11(1), 1434 (2021)","journal-title":"Sci. Rep."},{"key":"3010_CR44","doi-asserted-by":"crossref","unstructured":"L. Sun, J. Du, L.R. Dai, et\u00a0al., Multiple-target deep learning for LSTM-RNN based speech enhancement, in 2017 Hands-free Speech Communications and Microphone Arrays (HSCMA), pp. 136\u2013140 (IEEE, 2017)","DOI":"10.1109\/HSCMA.2017.7895577"},{"issue":"7","key":"3010_CR45","doi-asserted-by":"publisher","first-page":"2125","DOI":"10.1109\/TASL.2011.2114881","volume":"19","author":"CH Taal","year":"2011","unstructured":"C.H. Taal, R.C. Hendriks, R. Heusdens et al., An algorithm for intelligibility prediction of time-frequency weighted noisy speech. IEEE Trans. Audio Speech Lang. Process. 19(7), 2125\u20132136 (2011)","journal-title":"IEEE Trans. Audio Speech Lang. Process."},{"key":"3010_CR46","doi-asserted-by":"crossref","unstructured":"K. Tan, D. Wang, A convolutional recurrent neural network for real-time speech enhancement, in Interspeech, pp. 3229\u20133233 (2018)","DOI":"10.21437\/Interspeech.2018-1405"},{"key":"3010_CR47","doi-asserted-by":"publisher","first-page":"380","DOI":"10.1109\/TASLP.2019.2955276","volume":"28","author":"K Tan","year":"2019","unstructured":"K. Tan, D. Wang, Learning complex spectral mapping with gated convolutional recurrent networks for monaural speech enhancement. IEEE\/ACM Trans. Audio Speech Lang. Process. 28, 380\u2013390 (2019)","journal-title":"IEEE\/ACM Trans. Audio Speech Lang. Process."},{"issue":"10","key":"3010_CR48","doi-asserted-by":"publisher","first-page":"1943","DOI":"10.1177\/01423312231225782","volume":"46","author":"Y Tao","year":"2024","unstructured":"Y. Tao, H. Tao, Z. Zhuang et al., Quantized iterative learning control of communication-constrained systems with encoding and decoding mechanism. Trans. Inst. Meas. Control. 46(10), 1943\u20131954 (2024)","journal-title":"Trans. Inst. Meas. Control."},{"issue":"5\u2013Supplement","key":"3010_CR49","doi-asserted-by":"publisher","first-page":"3591","DOI":"10.1121\/1.4806631","volume":"133","author":"J Thiemann","year":"2013","unstructured":"J. Thiemann, N. Ito, E. Vincent, The diverse environments multi-channel acoustic noise database: a database of multichannel environmental noise recordings. J. Acoust. Soc. Am. 133(5\u2013Supplement), 3591\u20133591 (2013)","journal-title":"J. Acoust. Soc. Am."},{"key":"3010_CR50","doi-asserted-by":"crossref","unstructured":"M. Tu, X. Zhang, Speech enhancement based on deep neural networks with skip connections, in 2017 IEEE international conference on acoustics, speech and signal processing (ICASSP), pp. 5565\u20135569 (IEEE, 2017)","DOI":"10.1109\/ICASSP.2017.7953221"},{"key":"3010_CR51","doi-asserted-by":"crossref","unstructured":"C. Valentini-Botinhao, X. Wang, S. Takaki, et\u00a0al. Investigating RNN-based speech enhancement methods for noise-robust text-to-speech, in SSW, pp. 146\u2013152 (2016)","DOI":"10.21437\/SSW.2016-24"},{"key":"3010_CR52","unstructured":"A. Vaswani, N. Shazeer, N. Parmar, et\u00a0al. Attention is all you need, in Advances in Neural Information Processing Systems 30 (2017)"},{"key":"3010_CR53","doi-asserted-by":"crossref","unstructured":"K. Wang, B. He, W.P. Zhu, TSTNN: two-stage transformer based neural network for speech enhancement in the time domain, in ICASSP 2021-2021 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP), pp. 7098\u20137102 (IEEE, 2021)","DOI":"10.1109\/ICASSP39728.2021.9413740"},{"issue":"12","key":"3010_CR54","doi-asserted-by":"publisher","first-page":"1849","DOI":"10.1109\/TASLP.2014.2352935","volume":"22","author":"Y Wang","year":"2014","unstructured":"Y. Wang, A. Narayanan, D. Wang, On training targets for supervised speech separation. IEEE\/ACM Trans. Audio Speech Lang. Process. 22(12), 1849\u20131858 (2014)","journal-title":"IEEE\/ACM Trans. Audio Speech Lang. Process."},{"issue":"3","key":"3010_CR55","doi-asserted-by":"publisher","first-page":"483","DOI":"10.1109\/TASLP.2015.2512042","volume":"24","author":"DS Williamson","year":"2015","unstructured":"D.S. Williamson, Y. Wang, D. Wang, Complex ratio masking for monaural speech separation. IEEE\/ACM Trans. Audio Speech Lang. Process. 24(3), 483\u2013492 (2015)","journal-title":"IEEE\/ACM Trans. Audio Speech Lang. Process."},{"key":"3010_CR56","doi-asserted-by":"publisher","first-page":"128","DOI":"10.1109\/OJCAS.2024.3387849","volume":"5","author":"CH Wu","year":"2024","unstructured":"C.H. Wu, T.S. Chang, A low-power streaming speech enhancement accelerator for edge devices. IEEE Open J. Circuits Syst. 5, 128\u2013140 (2024)","journal-title":"IEEE Open J. Circuits Syst."},{"issue":"1","key":"3010_CR57","doi-asserted-by":"publisher","first-page":"143","DOI":"10.1109\/JSTSP.2020.3045846","volume":"15","author":"Y Xian","year":"2020","unstructured":"Y. Xian, Y. Sun, W. Wang et al., A multi-scale feature recalibration network for end-to-end single channel speech enhancement. IEEE J. Sel. Top. Signal Process. 15(1), 143\u2013155 (2020)","journal-title":"IEEE J. Sel. Top. Signal Process."},{"key":"3010_CR58","doi-asserted-by":"publisher","first-page":"1455","DOI":"10.1109\/LSP.2021.3093859","volume":"28","author":"X Xiang","year":"2021","unstructured":"X. Xiang, X. Zhang, H. Chen, A convolutional network with multi-scale and attention mechanisms for end-to-end single-channel speech enhancement. IEEE Signal Process. Lett. 28, 1455\u20131459 (2021)","journal-title":"IEEE Signal Process. Lett."},{"key":"3010_CR59","doi-asserted-by":"publisher","first-page":"105","DOI":"10.1109\/LSP.2021.3128374","volume":"29","author":"X Xiang","year":"2021","unstructured":"X. Xiang, X. Zhang, H. Chen, A nested u-net with self-attention and dense connectivity for monaural speech enhancement. IEEE Signal Process. Lett. 29, 105\u2013109 (2021)","journal-title":"IEEE Signal Process. Lett."},{"key":"3010_CR60","unstructured":"Z. Xie, I. Sato, M. Sugiyama, Stable weight decay regularization. arXiv (2020)"},{"key":"3010_CR61","doi-asserted-by":"publisher","DOI":"10.1016\/j.cnsns.2023.107535","volume":"127","author":"C Xu","year":"2023","unstructured":"C. Xu, M. Jiang, J. Hu, Mean-square finite-time synchronization of stochastic competitive neural networks with infinite time-varying delays and reaction-diffusion terms. Commun. Nonlinear Sci. Numer. Simul. 127, 107535 (2023)","journal-title":"Commun. Nonlinear Sci. Numer. Simul."},{"issue":"1","key":"3010_CR62","doi-asserted-by":"publisher","first-page":"65","DOI":"10.1109\/LSP.2013.2291240","volume":"21","author":"Y Xu","year":"2013","unstructured":"Y. Xu, J. Du, L.R. Dai et al., An experimental study on speech enhancement based on deep neural networks. IEEE Signal Process. Lett. 21(1), 65\u201368 (2013)","journal-title":"IEEE Signal Process. Lett."},{"issue":"1","key":"3010_CR63","doi-asserted-by":"publisher","first-page":"7","DOI":"10.1109\/TASLP.2014.2364452","volume":"23","author":"Y Xu","year":"2014","unstructured":"Y. Xu, J. Du, L.R. Dai et al., A regression approach to speech enhancement based on deep neural networks. IEEE\/ACM Trans. Audio Speech Lang. Process. 23(1), 7\u201319 (2014)","journal-title":"IEEE\/ACM Trans. Audio Speech Lang. Process."},{"key":"3010_CR64","doi-asserted-by":"crossref","unstructured":"D. Yin, C. Luo, Z. Xiong, et\u00a0al. PHASEN: a phase-and-harmonics-aware speech enhancement network, in Proceedings of the AAAI Conference on Artificial Intelligence, pp. 9458\u20139465 (2020)","DOI":"10.1609\/aaai.v34i05.6489"},{"key":"3010_CR65","doi-asserted-by":"publisher","first-page":"2629","DOI":"10.1109\/TASLP.2022.3195112","volume":"30","author":"G Yu","year":"2022","unstructured":"G. Yu, A. Li, H. Wang et al., DBT-Net: Dual-branch federative magnitude and phase estimation with attention-in-attention transformer for monaural speech enhancement. IEEE\/ACM Trans. Audio Speech Lang. Process. 30, 2629\u20132644 (2022)","journal-title":"IEEE\/ACM Trans. Audio Speech Lang. Process."},{"key":"3010_CR66","doi-asserted-by":"crossref","unstructured":"G. Yu, A. Li, C. Zheng et al., Dual-branch attention-in-attention transformer for single-channel speech enhancement, in ICASSP 2022\u20132022 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP), pp. 7847\u20137851. (IEEE, 2022)","DOI":"10.1109\/ICASSP43922.2022.9746273"},{"key":"3010_CR67","unstructured":"W. Yu, J. Zhou, H. Wang et al., Setransformer: Speech enhancement transformer. Cognit. Comput. 1\u20137 (2022)"},{"key":"3010_CR68","doi-asserted-by":"publisher","first-page":"1","DOI":"10.1155\/2020\/2196893","volume":"2020","author":"CM Yuan","year":"2020","unstructured":"C.M. Yuan, X.M. Sun, H. Zhao, Speech separation using convolutional neural network and attention mechanism. Discrete Dyn. Nat. Soc. 2020, 1\u201310 (2020)","journal-title":"Discrete Dyn. Nat. Soc."},{"key":"3010_CR69","doi-asserted-by":"crossref","unstructured":"Y. Zhang, K. Li, K. Li, et\u00a0al. Image super-resolution using very deep residual channel attention networks, in Proceedings of the European Conference on Computer Vision (ECCV), pp. 286\u2013301 (2018)","DOI":"10.1007\/978-3-030-01234-2_18"},{"key":"3010_CR70","doi-asserted-by":"publisher","first-page":"366","DOI":"10.1016\/j.neunet.2023.07.024","volume":"166","author":"FL Zhao","year":"2023","unstructured":"F.L. Zhao, Z.P. Wang, J. Qiao et al., Adaptive event-triggered extended dissipative synchronization of delayed reaction\u2013diffusion neural networks under deception attacks. Neural Netw. 166, 366\u2013378 (2023)","journal-title":"Neural Netw."},{"key":"3010_CR71","doi-asserted-by":"crossref","unstructured":"H. Zhao, S. Zarar, I. Tashev et al., Convolutional-recurrent neural networks for speech enhancement, in 2018 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP), pp. 2401\u20132405. (IEEE, 2018)","DOI":"10.1109\/ICASSP.2018.8462155"},{"key":"3010_CR72","doi-asserted-by":"crossref","unstructured":"S. Zhao, B. Ma, D2former: A fully complex dual-path dual-decoder conformer network using joint complex masking and complex spectral mapping for monaural speech enhancement, in ICASSP 2023\u20132023 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP). (IEEE, 2023), pp. 1\u20135","DOI":"10.1109\/ICASSP49357.2023.10096259"},{"key":"3010_CR73","doi-asserted-by":"crossref","unstructured":"S. Zhao, T.H. Nguyen, B. Ma, Monaural speech enhancement with complex convolutional block attention module and joint time frequency losses, in ICASSP 2021\u20132021 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP). (IEEE, 2021), pp. 6648\u20136652","DOI":"10.1109\/ICASSP39728.2021.9414569"},{"key":"3010_CR74","doi-asserted-by":"crossref","unstructured":"S. Zhao, B. Ma, K.N. Watcharasupat et al., FRCRN: Boosting feature representation using frequency recurrence for monaural speech enhancement, in ICASSP 2022\u20132022 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP). (IEEE, 2022), pp. 9281\u20139285","DOI":"10.1109\/ICASSP43922.2022.9747578"}],"container-title":["Circuits, Systems, and Signal Processing"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/link.springer.com\/content\/pdf\/10.1007\/s00034-025-03010-2.pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/link.springer.com\/article\/10.1007\/s00034-025-03010-2\/fulltext.html","content-type":"text\/html","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/link.springer.com\/content\/pdf\/10.1007\/s00034-025-03010-2.pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,5,14]],"date-time":"2025-05-14T20:09:51Z","timestamp":1747253391000},"score":1,"resource":{"primary":{"URL":"https:\/\/link.springer.com\/10.1007\/s00034-025-03010-2"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2025,1,31]]},"references-count":74,"journal-issue":{"issue":"6","published-print":{"date-parts":[[2025,6]]}},"alternative-id":["3010"],"URL":"https:\/\/doi.org\/10.1007\/s00034-025-03010-2","relation":{},"ISSN":["0278-081X","1531-5878"],"issn-type":[{"value":"0278-081X","type":"print"},{"value":"1531-5878","type":"electronic"}],"subject":[],"published":{"date-parts":[[2025,1,31]]},"assertion":[{"value":"30 April 2024","order":1,"name":"received","label":"Received","group":{"name":"ArticleHistory","label":"Article History"}},{"value":"3 January 2025","order":2,"name":"revised","label":"Revised","group":{"name":"ArticleHistory","label":"Article History"}},{"value":"5 January 2025","order":3,"name":"accepted","label":"Accepted","group":{"name":"ArticleHistory","label":"Article History"}},{"value":"31 January 2025","order":4,"name":"first_online","label":"First Online","group":{"name":"ArticleHistory","label":"Article History"}},{"order":1,"name":"Ethics","group":{"name":"EthicsHeading","label":"Declarations"}},{"value":"No conflict of interest.","order":2,"name":"Ethics","group":{"name":"EthicsHeading","label":"Conflict of interest"}}]}}