{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,7,4]],"date-time":"2026-07-04T23:15:52Z","timestamp":1783206952420,"version":"3.54.6"},"reference-count":56,"publisher":"Elsevier BV","license":[{"start":{"date-parts":[[2026,7,1]],"date-time":"2026-07-01T00:00:00Z","timestamp":1782864000000},"content-version":"tdm","delay-in-days":0,"URL":"https:\/\/www.elsevier.com\/tdm\/userlicense\/1.0\/"},{"start":{"date-parts":[[2026,7,1]],"date-time":"2026-07-01T00:00:00Z","timestamp":1782864000000},"content-version":"tdm","delay-in-days":0,"URL":"https:\/\/www.elsevier.com\/legal\/tdmrep-license"},{"start":{"date-parts":[[2026,7,1]],"date-time":"2026-07-01T00:00:00Z","timestamp":1782864000000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-017"},{"start":{"date-parts":[[2026,7,1]],"date-time":"2026-07-01T00:00:00Z","timestamp":1782864000000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-037"},{"start":{"date-parts":[[2026,7,1]],"date-time":"2026-07-01T00:00:00Z","timestamp":1782864000000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-012"},{"start":{"date-parts":[[2026,7,1]],"date-time":"2026-07-01T00:00:00Z","timestamp":1782864000000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2026,7,1]],"date-time":"2026-07-01T00:00:00Z","timestamp":1782864000000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-004"}],"funder":[{"DOI":"10.13039\/501100001809","name":"National Natural Science Foundation of China","doi-asserted-by":"publisher","award":["61901227"],"award-info":[{"award-number":["61901227"]}],"id":[{"id":"10.13039\/501100001809","id-type":"DOI","asserted-by":"publisher"}]}],"content-domain":{"domain":["elsevier.com","sciencedirect.com"],"crossmark-restriction":true},"short-container-title":["Speech Communication"],"published-print":{"date-parts":[[2026,7]]},"DOI":"10.1016\/j.specom.2026.103425","type":"journal-article","created":{"date-parts":[[2026,6,2]],"date-time":"2026-06-02T06:39:38Z","timestamp":1780382378000},"page":"103425","update-policy":"https:\/\/doi.org\/10.1016\/elsevier_cm_policy","source":"Crossref","is-referenced-by-count":0,"special_numbering":"C","title":["KCAM-SENet: Speech enhancement network with KAN-based channel attention module"],"prefix":"10.1016","volume":"182","author":[{"ORCID":"https:\/\/orcid.org\/0000-0001-9442-9964","authenticated-orcid":false,"given":"Linhui","family":"Sun","sequence":"first","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Zhaowei","family":"Ding","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Yuhang","family":"Qin","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Tingting","family":"Wang","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Shengchen","family":"Li","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Xi","family":"Shao","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Eng Siong","family":"Chng","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"78","reference":[{"key":"10.1016\/j.specom.2026.103425_b1","series-title":"Layer normalization","author":"Ba","year":"2016"},{"key":"10.1016\/j.specom.2026.103425_b2","doi-asserted-by":"crossref","first-page":"40","DOI":"10.1016\/j.heares.2017.12.016","article-title":"A phenomenological model of the synapse between the inner hair cell and auditory nerve: Implications of limited neurotransmitter release sites","volume":"360","author":"Bruce","year":"2018","journal-title":"Hear. Res."},{"key":"10.1016\/j.specom.2026.103425_b3","series-title":"CMGAN: Conformer-based metric GAN for speech enhancement","author":"Cao","year":"2022"},{"key":"10.1016\/j.specom.2026.103425_b4","series-title":"2024 IEEE Spoken Language Technology Workshop","first-page":"302","article-title":"An investigation of incorporating mamba for speech enhancement","author":"Chao","year":"2024"},{"key":"10.1016\/j.specom.2026.103425_b5","doi-asserted-by":"crossref","unstructured":"Dang, F., Chen, H., Zhang, P., 2021. DPT-FSNet: Dual-Path Transformer Based Full-Band and Sub-Band Fusion Network for Speech Enhancement. In: ICASSP 2022 - 2022 IEEE International Conference on Acoustics, Speech and Signal Processing. ICASSP, pp. 6857\u20136861.","DOI":"10.1109\/ICASSP43922.2022.9746171"},{"key":"10.1016\/j.specom.2026.103425_b6","series-title":"Real time speech enhancement in the waveform domain","author":"D\u00e9fossez","year":"2020"},{"key":"10.1016\/j.specom.2026.103425_b7","unstructured":"Fu, S.-W., Liao, C.-F., Tsao, Y., Lin, S.-D., 2019. MetricGAN: Generative Adversarial Networks based Black-box Metric Scores Optimization for Speech Enhancement. In: International Conference on Machine Learning."},{"key":"10.1016\/j.specom.2026.103425_b8","series-title":"Interspeech","article-title":"MetricGAN+: An improved version of metricgan for speech enhancement","author":"Fu","year":"2021"},{"key":"10.1016\/j.specom.2026.103425_b9","series-title":"KAN4TSF: Are KAN and KAN-based models effective for time series forecasting?","author":"Han","year":"2024"},{"key":"10.1016\/j.specom.2026.103425_b10","doi-asserted-by":"crossref","unstructured":"Hao, X., Su, X., Horaud, R., Li, X., 2021. Fullsubnet: A Full-Band and Sub-Band Fusion Model for Real-Time Single-Channel Speech Enhancement. In: ICASSP 2021 - 2021 IEEE International Conference on Acoustics, Speech and Signal Processing. ICASSP, pp. 6633\u20136637.","DOI":"10.1109\/ICASSP39728.2021.9414177"},{"key":"10.1016\/j.specom.2026.103425_b11","series-title":"2015 IEEE International Conference on Computer Vision","first-page":"1026","article-title":"Delving deep into rectifiers: Surpassing human-level performance on ImageNet classification","author":"He","year":"2015"},{"issue":"1","key":"10.1016\/j.specom.2026.103425_b12","doi-asserted-by":"crossref","first-page":"229","DOI":"10.1109\/TASL.2007.911054","article-title":"Evaluation of objective quality measures for speech enhancement","volume":"16","author":"Hu","year":"2008","journal-title":"IEEE Trans. Audio, Speech, Lang. Process."},{"key":"10.1016\/j.specom.2026.103425_b13","series-title":"Interspeech","article-title":"SE-conformer: Time-domain speech enhancement using conformer","author":"Kim","year":"2021"},{"issue":"2","key":"10.1016\/j.specom.2026.103425_b14","first-page":"953","article-title":"On the representation of continuous functions of many variables by superposition of continuous functions of one variable and addition","volume":"2","author":"Kolmogorov","year":"1957","journal-title":"Dokl.Akad.Nauk Sssr"},{"key":"10.1016\/j.specom.2026.103425_b15","series-title":"xLSTM-SENet: xLSTM for single-channel speech enhancement","author":"K\u00fchne","year":"2025"},{"key":"10.1016\/j.specom.2026.103425_b16","series-title":"Kolmogorov-arnold networks are radial basis function networks","author":"Li","year":"2024"},{"key":"10.1016\/j.specom.2026.103425_b17","series-title":"U-KAN makes strong backbone for medical image segmentation and generation","author":"Li","year":"2024"},{"key":"10.1016\/j.specom.2026.103425_b18","doi-asserted-by":"crossref","unstructured":"Li, A., You, S., Yu, G., Zheng, C., Li, X., 2022. Taylor, Can You Hear Me Now? A Taylor-Unfolding Framework for Monaural Speech Enhancement. In: International Joint Conference on Artificial Intelligence.","DOI":"10.24963\/ijcai.2022\/582"},{"key":"10.1016\/j.specom.2026.103425_b19","series-title":"Two heads are better than one: A two-stage approach for monaural noise reduction in the complex domain","author":"Li","year":"2020"},{"key":"10.1016\/j.specom.2026.103425_b20","series-title":"MUSE: Flexible voiceprint receptive fields and multi-path fusion enhanced taylor transformer for U-net-based speech enhancement","author":"Lin","year":"2024"},{"key":"10.1016\/j.specom.2026.103425_b21","series-title":"A mask free neural network for monaural speech enhancement","author":"Liu","year":"2023"},{"key":"10.1016\/j.specom.2026.103425_b22","series-title":"KAN: Kolmogorov-arnold networks","author":"Liu","year":"2024"},{"key":"10.1016\/j.specom.2026.103425_b23","series-title":"2022 3rd International Conference on Electronic Communication and Artificial Intelligence","first-page":"384","article-title":"EfficientNetv2 model for breast cancer histopathological image classification","author":"Liu","year":"2022"},{"key":"10.1016\/j.specom.2026.103425_b24","unstructured":"Loshchilov, I., Hutter, F., 2017. Decoupled Weight Decay Regularization. In: International Conference on Learning Representations."},{"key":"10.1016\/j.specom.2026.103425_b25","series-title":"Explicit estimation of magnitude and phase spectra in parallel for high-quality speech enhancement","author":"Lu","year":"2023"},{"key":"10.1016\/j.specom.2026.103425_b26","doi-asserted-by":"crossref","unstructured":"Mai, Y., Goetze, S., 2025. MetricGAN+KAN: Kolmogorov-Arnold Networks in Metric-Driven Speech Enhancement Systems. In: ICASSP 2025 - 2025 IEEE International Conference on Acoustics, Speech and Signal Processing. ICASSP, pp. 1\u20135.","DOI":"10.1109\/ICASSP49660.2025.10890542"},{"key":"10.1016\/j.specom.2026.103425_b27","doi-asserted-by":"crossref","first-page":"80","DOI":"10.1016\/j.specom.2020.10.004","article-title":"Masked multi-head self-attention for causal speech enhancement","volume":"125","author":"Nicolson","year":"2020","journal-title":"Speech Commun."},{"key":"10.1016\/j.specom.2026.103425_b28","doi-asserted-by":"crossref","unstructured":"Pandey, A., Wang, D., 2020. Densely Connected Neural Network with Dilated Convolutions for Real-Time Speech Enhancement in The Time Domain. In: ICASSP 2020 - 2020 IEEE International Conference on Acoustics, Speech and Signal Processing. ICASSP, pp. 6629\u20136633.","DOI":"10.1109\/ICASSP40776.2020.9054536"},{"key":"10.1016\/j.specom.2026.103425_b29","series-title":"SEGAN: Speech enhancement generative adversarial network","author":"Pascual","year":"2017"},{"key":"10.1016\/j.specom.2026.103425_b30","series-title":"Interspeech","article-title":"The interspeech 2020 deep noise suppression challenge: Datasets, subjective testing framework, and challenge results","author":"Reddy","year":"2020"},{"key":"10.1016\/j.specom.2026.103425_b31","series-title":"2001 IEEE International Conference on Acoustics, Speech, and Signal Processing. Proceedings (Cat. No.01CH37221)","first-page":"749","article-title":"Perceptual evaluation of speech quality (PESQ)-a new method for speech quality assessment of telephone networks and codecs","volume":"vol. 2","author":"Rix","year":"2001"},{"key":"10.1016\/j.specom.2026.103425_b32","doi-asserted-by":"crossref","unstructured":"Roux, J.L., Wisdom, S., Erdogan, H., Hershey, J.R., 2019. SDR \u2013 Half-baked or Well Done?. In: ICASSP 2019 - 2019 IEEE International Conference on Acoustics, Speech and Signal Processing. ICASSP, pp. 626\u2013630.","DOI":"10.1109\/ICASSP.2019.8683855"},{"key":"10.1016\/j.specom.2026.103425_b33","doi-asserted-by":"crossref","DOI":"10.1016\/j.knosys.2025.113452","article-title":"CTSE-Net: Resource-efficient convolutional and TF-transformer network for speech enhancement","volume":"317","author":"Saleem","year":"2025","journal-title":"Knowl.-Based Syst."},{"key":"10.1016\/j.specom.2026.103425_b34","doi-asserted-by":"crossref","unstructured":"Shi, W., Caballero, J., Husz\u00e1r, F., Totz, J., Aitken, A.P., Bishop, R., Rueckert, D., Wang, Z., 2016. Real-Time Single Image and Video Super-Resolution Using an Efficient Sub-Pixel Convolutional Neural Network. In: 2016 IEEE Conference on Computer Vision and Pattern Recognition. CVPR, pp. 1874\u20131883.","DOI":"10.1109\/CVPR.2016.207"},{"key":"10.1016\/j.specom.2026.103425_b35","series-title":"Interspeech","article-title":"Self-attentional acoustic models","author":"Sperber","year":"2018"},{"key":"10.1016\/j.specom.2026.103425_b36","doi-asserted-by":"crossref","first-page":"1457","DOI":"10.1109\/TASLP.2024.3362691","article-title":"Dual-branch modeling based on state-space model for speech enhancement","volume":"32","author":"Sun","year":"2024","journal-title":"IEEE\/ACM Trans. Audio, Speech, Lang. Process."},{"issue":"7","key":"10.1016\/j.specom.2026.103425_b37","doi-asserted-by":"crossref","first-page":"2125","DOI":"10.1109\/TASL.2011.2114881","article-title":"An algorithm for intelligibility prediction of time\u2013frequency weighted noisy speech","volume":"19","author":"Taal","year":"2011","journal-title":"IEEE Trans. Audio Speech Lang. Process."},{"key":"10.1016\/j.specom.2026.103425_b38","doi-asserted-by":"crossref","DOI":"10.1121\/1.4806631","article-title":"The diverse environments multi-channel acoustic noise database (DEMAND): A database of multichannel environmental noise recordings","volume":"133","author":"Thiemann","year":"2013","journal-title":"J. Acoust. Soc. Am."},{"key":"10.1016\/j.specom.2026.103425_b39","series-title":"Instance normalization: The missing ingredient for fast stylization","author":"Ulyanov","year":"2016"},{"key":"10.1016\/j.specom.2026.103425_b40","doi-asserted-by":"crossref","unstructured":"Valentini-Botinhao, C., Wang, X., Takaki, S., Yamagishi, J., 2016. Investigating RNN-based speech enhancement methods for noise-robust Text-to-Speech. In: Proceedings of 9th ISCA Speech Synthesis Workshop. pp. 159\u2013165.","DOI":"10.21437\/SSW.2016-24"},{"key":"10.1016\/j.specom.2026.103425_b41","series-title":"Neural Information Processing Systems","article-title":"Attention is all you need","author":"Vaswani","year":"2017"},{"key":"10.1016\/j.specom.2026.103425_b42","series-title":"Neural Information Processing Systems","article-title":"Attention is all you need","author":"Vaswani","year":"2017"},{"key":"10.1016\/j.specom.2026.103425_b43","doi-asserted-by":"crossref","unstructured":"Veaux, C., Yamagishi, J., King, S., 2013. The voice bank corpus: Design, collection and data analysis of a large regional accent speech database. In: 2013 International Conference Oriental COCOSDA held jointly with 2013 Conference on Asian Spoken Language Research and Evaluation (O-COCOSDA\/CASLRE). pp. 1\u20134.","DOI":"10.1109\/ICSDA.2013.6709856"},{"issue":"4","key":"10.1016\/j.specom.2026.103425_b44","doi-asserted-by":"crossref","first-page":"12086","DOI":"10.1109\/TCE.2025.3598007","article-title":"Lightweight adaptive deep learning for efficient real-time speech enhancement on edge devices","volume":"71","author":"Wahab","year":"2025","journal-title":"IEEE Trans. Consum. Electron."},{"key":"10.1016\/j.specom.2026.103425_b45","doi-asserted-by":"crossref","DOI":"10.1016\/j.neucom.2024.129150","article-title":"MA-Net: Resource-efficient multi-attentional network for end-to-end speech enhancement","volume":"619","author":"Wahab","year":"2025","journal-title":"Neurocomputing"},{"key":"10.1016\/j.specom.2026.103425_b46","doi-asserted-by":"crossref","unstructured":"Wang, K., He, B., Zhu, W., 2021. 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.","DOI":"10.1109\/ICASSP39728.2021.9413740"},{"key":"10.1016\/j.specom.2026.103425_b47","series-title":"Computer Vision \u2013 ECCV","first-page":"3","article-title":"CBAM: Convolutional block attention module","author":"Woo","year":"2018"},{"key":"10.1016\/j.specom.2026.103425_b48","doi-asserted-by":"crossref","DOI":"10.1016\/j.specom.2024.103154","article-title":"Two-stage UNet with channel and temporal-frequency attention for multi-channel speech enhancement","volume":"166","author":"Xu","year":"2025","journal-title":"Speech Commun."},{"key":"10.1016\/j.specom.2026.103425_b49","series-title":"Kolmogorov-arnold networks for time series: Bridging predictive power and interpretability","author":"Xu","year":"2024"},{"key":"10.1016\/j.specom.2026.103425_b50","doi-asserted-by":"crossref","DOI":"10.1016\/j.specom.2025.103248","article-title":"Dual-path and interactive UNET for speech enhancement with multi-order fractional features","volume":"172","author":"Xu","year":"2025","journal-title":"Speech Commun."},{"key":"10.1016\/j.specom.2026.103425_b51","series-title":"Interspeech","article-title":"Tridentse: Guiding speech enhancement with 32 global tokens","author":"Yin","year":"2022"},{"key":"10.1016\/j.specom.2026.103425_b52","series-title":"Interspeech","article-title":"SCP-GAN: Self-correcting discriminator optimization for training consistency preserving metric GAN on speech enhancement tasks","author":"Zadorozhnyy","year":"2022"},{"key":"10.1016\/j.specom.2026.103425_b53","doi-asserted-by":"crossref","first-page":"462","DOI":"10.1109\/TASLP.2022.3225649","article-title":"A time-frequency attention module for neural speech enhancement","volume":"31","author":"Zhang","year":"2023","journal-title":"IEEE\/ACM Trans. Audio, Speech, Lang. Process."},{"key":"10.1016\/j.specom.2026.103425_b54","doi-asserted-by":"crossref","first-page":"1933","DOI":"10.1109\/TASLPRO.2025.3566210","article-title":"Mamba in speech: Towards an alternative to self-attention","volume":"33","author":"Zhang","year":"2025","journal-title":"IEEE Trans. Audio, Speech Lang. Process."},{"key":"10.1016\/j.specom.2026.103425_b55","doi-asserted-by":"crossref","unstructured":"Zhao, S., Ma, B., Watcharasupat, K.N., Gan, W.-S., 2022. FRCRN: Boosting Feature Representation Using Frequency Recurrence for Monaural Speech Enhancement. In: ICASSP 2022 - 2022 IEEE International Conference on Acoustics, Speech and Signal Processing. ICASSP, pp. 9281\u20139285.","DOI":"10.1109\/ICASSP43922.2022.9747578"},{"key":"10.1016\/j.specom.2026.103425_b56","doi-asserted-by":"crossref","first-page":"1705","DOI":"10.12733\/jics20101658","article-title":"A speech enhancement method employing sparse representation of power spectral density","volume":"10","author":"Zhao","year":"2013","journal-title":"J. Inf. Comput. Sci."}],"container-title":["Speech Communication"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/api.elsevier.com\/content\/article\/PII:S0167639326000737?httpAccept=text\/xml","content-type":"text\/xml","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/api.elsevier.com\/content\/article\/PII:S0167639326000737?httpAccept=text\/plain","content-type":"text\/plain","content-version":"vor","intended-application":"text-mining"}],"deposited":{"date-parts":[[2026,7,4]],"date-time":"2026-07-04T22:23:51Z","timestamp":1783203831000},"score":1,"resource":{"primary":{"URL":"https:\/\/linkinghub.elsevier.com\/retrieve\/pii\/S0167639326000737"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2026,7]]},"references-count":56,"alternative-id":["S0167639326000737"],"URL":"https:\/\/doi.org\/10.1016\/j.specom.2026.103425","relation":{},"ISSN":["0167-6393"],"issn-type":[{"value":"0167-6393","type":"print"}],"subject":[],"published":{"date-parts":[[2026,7]]},"assertion":[{"value":"Elsevier","name":"publisher","label":"This article is maintained by"},{"value":"KCAM-SENet: Speech enhancement network with KAN-based channel attention module","name":"articletitle","label":"Article Title"},{"value":"Speech Communication","name":"journaltitle","label":"Journal Title"},{"value":"https:\/\/doi.org\/10.1016\/j.specom.2026.103425","name":"articlelink","label":"CrossRef DOI link to publisher maintained version"},{"value":"article","name":"content_type","label":"Content Type"},{"value":"\u00a9 2026 Elsevier B.V. All rights are reserved, including those for text and data mining, AI training, and similar technologies.","name":"copyright","label":"Copyright"}],"article-number":"103425"}}