{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,10,1]],"date-time":"2026-10-01T18:02:40Z","timestamp":1790877760443,"version":"4.1.0"},"reference-count":36,"publisher":"Public Library of Science (PLoS)","issue":"10","license":[{"start":{"date-parts":[[2026,10,1]],"date-time":"2026-10-01T00:00:00Z","timestamp":1790812800000},"content-version":"vor","delay-in-days":0,"URL":"http:\/\/creativecommons.org\/licenses\/by\/4.0\/"}],"funder":[{"DOI":"10.13039\/501100018628","name":"Scientific Research Foundation of Education Department of Anhui Province of China","doi-asserted-by":"publisher","award":["2025AHGXZK20205"],"award-info":[{"award-number":["2025AHGXZK20205"]}],"id":[{"id":"10.13039\/501100018628","id-type":"DOI","asserted-by":"publisher"}]}],"content-domain":{"domain":["www.plosone.org"],"crossmark-restriction":false},"short-container-title":["PLoS One"],"abstract":"<jats:p>To avoid the additional computational cost and algorithmic latency introduced by short-time Fourier transformation and waveform reconstruction, we propose CGAN-SECA, which incorporates a squeeze-and-excitation channel attention mechanism to enhance noisy speech directly in the time domain. The generator employs a symmetric encoder-decoder backbone with skip connections to reconstruct waveform samples and reduce information loss during down-sampling and up-sampling. SECA adaptively recalibrates channel-wise feature responses, enabling the network to emphasize speech-relevant representations under complex noise. In the discriminator, Virtual Batch Normalization (VBN) and Dropout are introduced to regularize adversarial training. Least-squares adversarial objectives replace cross-entropy-based objectives, and an L1 reconstruction term encourages sample-level fidelity. The method is evaluated on VoiceBank-DEMAND, which contains environmental and babble noise, and on the THCHS30-DNS Challenge dataset under multiple Signal-to-Noise Ratio (SNR) conditions. On VoiceBank-DEMAND, CGAN-SECA achieved PESQ and STOI scores of 3.018 and 0.954, respectively, ranking second only to CMGAN and outperforming the remaining comparison methods. CGAN-SECA also maintained fast inference, with a real-time factor (RTF) of 0.00423. On the THCHS30-DNS Challenge dataset, CGAN-SECA achieved the highest average PESQ and STOI scores among all evaluated methods, reaching 2.274 and 0.838, respectively, across the \u22125, 0, and 5 dB conditions. In particular, it produced the best results for both metrics at 0 and 5 dB, demonstrating effective speech enhancement and good generalization across different noise levels and datasets.<\/jats:p>","DOI":"10.1371\/journal.pone.0359641","type":"journal-article","created":{"date-parts":[[2026,10,1]],"date-time":"2026-10-01T17:26:09Z","timestamp":1790875569000},"page":"e0359641","update-policy":"https:\/\/doi.org\/10.1371\/journal.pone.corrections_policy","source":"Crossref","is-referenced-by-count":0,"title":["Speech enhancement method integrating squeeze and excitation channel attention mechanism and improved CGAN"],"prefix":"10.1371","volume":"21","author":[{"ORCID":"https:\/\/orcid.org\/0000-0002-4395-7553","authenticated-orcid":true,"given":"Yecai","family":"Guo","sequence":"first","affiliation":[{"name":"Anhui Institute of Information Technology","place":["Wuhu, Anhui, China"],"department":["School of Electrical and Electronic Engineering"]},{"name":"Nanjing University of Information Science and Technology","place":["Nanjing, Jiangsu, China"],"department":["College of Electronic and Information Engineering"]}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Meiyu","family":"Liang","sequence":"additional","affiliation":[{"name":"Anhui Institute of Information Technology","place":["Wuhu, Anhui, China"],"department":["School of Electrical and Electronic Engineering"]}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Tianyue","family":"Jiang","sequence":"additional","affiliation":[{"name":"Nanjing University of Information Science and Technology","place":["Nanjing, Jiangsu, China"],"department":["College of Electronic and Information Engineering"]}],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"340","published-online":{"date-parts":[[2026,10,1]]},"reference":[{"issue":"3","key":"pone.0359641.ref001","doi-asserted-by":"crossref","first-page":"2203","DOI":"10.1007\/s11277-022-10039-y","article-title":"Analysis of optimized spectral subtraction method for single channel speech enhancement","volume":"128","author":"M Gupta","year":"2022","journal-title":"Wireless Pers Commun"},{"issue":"7","key":"pone.0359641.ref002","doi-asserted-by":"crossref","first-page":"4343","DOI":"10.1007\/s00034-023-02324-3","article-title":"Single-channel speech enhancement using single dimension change accelerated particle swarm optimization for subspace partitioning","volume":"42","author":"K Ghorpade","year":"2023","journal-title":"Circuits Syst Signal Process"},{"key":"pone.0359641.ref003","doi-asserted-by":"crossref","first-page":"2705","DOI":"10.1109\/TASLP.2022.3196168","article-title":"Modeling speech structure to improve T-F masks for speech enhancement and recognition","volume":"30","author":"S Bu","year":"2022","journal-title":"IEEE\/ACM Trans Audio Speech Lang Process"},{"issue":"7","key":"pone.0359641.ref004","doi-asserted-by":"crossref","first-page":"2039","DOI":"10.1109\/TASL.2011.2109380","article-title":"Ideal binary mask ratio: a novel metric for assessing binary-mask-based sound source separation algorithms","volume":"19","author":"C Hummersone","year":"2011","journal-title":"IEEE Trans Audio Speech Lang Process"},{"key":"pone.0359641.ref005","doi-asserted-by":"crossref","first-page":"110901","DOI":"10.1016\/j.measurement.2022.110901","article-title":"Noise-robust blind reverberation time estimation using noise-aware time\u2013frequency masking","volume":"192","author":"K Zheng","year":"2022","journal-title":"Measurement"},{"key":"pone.0359641.ref006","doi-asserted-by":"crossref","unstructured":"Tan K, Wang D. A convolutional recurrent neural network for real-time speech enhancement. In: Interspeech 2018; 2018. pp. 3229\u201333. https:\/\/doi.org\/10.21437\/interspeech.2018-1405","DOI":"10.21437\/Interspeech.2018-1405"},{"key":"pone.0359641.ref007","article-title":"Phase sensitive masking-based single channel speech enhancement using conditional generative adversarial network","volume":"71","author":"S Saha","year":"2022","journal-title":"Comput Speech Lang"},{"issue":"3","key":"pone.0359641.ref008","doi-asserted-by":"crossref","first-page":"483","DOI":"10.1109\/TASLP.2015.2512042","article-title":"Complex ratio masking for monaural speech separation","volume":"24","author":"DS Williamson","year":"2016","journal-title":"IEEE\/ACM Trans Audio Speech Lang Process"},{"issue":"3","key":"pone.0359641.ref009","first-page":"394","article-title":"Speech enhancement combining accurate ratio sparse and deep neural network for single-channel speech enhancement","volume":"47","author":"H Bai","year":"2022","journal-title":"Comput Sci Syst Eng"},{"key":"pone.0359641.ref010","doi-asserted-by":"crossref","first-page":"380","DOI":"10.1109\/TASLP.2019.2955276","article-title":"Learning complex spectral mapping with gated convolutional recurrent networks for monaural speech enhancement","volume":"28","author":"K Tan","year":"2020","journal-title":"IEEE\/ACM Trans Audio Speech Lang Process"},{"key":"pone.0359641.ref011","doi-asserted-by":"crossref","unstructured":"Fu S-W, Tsao Y, Lu X, Kawai H. Raw waveform-based speech enhancement by fully convolutional networks. In: 2017 Asia-Pacific Signal and Information Processing Association Annual Summit and Conference (APSIPA ASC); 2017. pp. 6\u201312. https:\/\/doi.org\/10.1109\/apsipa.2017.8281993","DOI":"10.1109\/APSIPA.2017.8281993"},{"issue":"1","key":"pone.0359641.ref012","doi-asserted-by":"crossref","first-page":"84","DOI":"10.9781\/ijimai.2019.06.001","article-title":"Deep neural networks for speech enhancement in complex-noisy environments","volume":"6","author":"N Saleem","year":"2020","journal-title":"IJIMAI"},{"key":"pone.0359641.ref013","doi-asserted-by":"crossref","unstructured":"Hou J, Zhao S. A real-time speech enhancement algorithm based on convolutional recurrent network and wiener filter. In: 2021 IEEE 6th International Conference on Computer and Communication Systems (ICCCS); 2021. pp. 683\u20138. https:\/\/doi.org\/10.1109\/icccs52626.2021.9449307","DOI":"10.1109\/ICCCS52626.2021.9449307"},{"key":"pone.0359641.ref014","doi-asserted-by":"crossref","unstructured":"Liu M, Wang Y, Wang J, Wang J, Xie X. Speech enhancement method based on LSTM neural network for speech recognition. In: 2018 14th IEEE International Conference on Signal Processing (ICSP); 2018. pp. 245\u20139. https:\/\/doi.org\/10.1109\/icsp.2018.8652331","DOI":"10.1109\/ICSP.2018.8652331"},{"key":"pone.0359641.ref015","doi-asserted-by":"crossref","unstructured":"Gao T, Du J, Dai L-R, Lee C-H. Densely connected progressive learning for LSTM-based speech enhancement. In: 2018 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP); 2018. pp. 5054\u20138. https:\/\/doi.org\/10.1109\/icassp.2018.8461861","DOI":"10.1109\/ICASSP.2018.8461861"},{"key":"pone.0359641.ref016","author":"X Zhou","year":"2025"},{"key":"pone.0359641.ref017","article-title":"A fully convolutional neural network for speech enhancement","author":"SR Park","year":"2016","journal-title":"arXiv"},{"issue":"7","key":"pone.0359641.ref018","doi-asserted-by":"crossref","first-page":"3461","DOI":"10.3390\/app12073461","article-title":"Hybrid dilated and recursive recurrent convolution network for time-domain speech enhancement","volume":"12","author":"Z Song","year":"2022","journal-title":"Appl Sci"},{"issue":"3","key":"pone.0359641.ref019","doi-asserted-by":"crossref","first-page":"279","DOI":"10.32604\/csse.2021.016524","article-title":"Speech enhancement via residual dense generative adversarial network","volume":"38","author":"L Zhou","year":"2021","journal-title":"Comput Syst Sci Eng"},{"key":"pone.0359641.ref020","unstructured":"Fu SW, Liao CF, Tsao Y, Lin SD. MetricGAN: generative adversarial networks based black-box metric scores optimization for speech enhancement. In: 36th International Conference on Machine Learning (ICML); 2019. https:\/\/doi.org\/10.48550\/arXiv.1905.04874"},{"key":"pone.0359641.ref021","doi-asserted-by":"crossref","unstructured":"Manaswini B, Lakshmi VA, Chintha L, Kotaiah NS. Gated convolutional recurrent networks with efficient channel attention for monaural speech enhancement. In: 2023 Second International Conference on Augmented Intelligence and Sustainable Systems (ICAISS); 2023. 217\u201322. https:\/\/doi.org\/10.1109\/icaiss58487.2023.10250746","DOI":"10.1109\/ICAISS58487.2023.10250746"},{"key":"pone.0359641.ref022","doi-asserted-by":"crossref","unstructured":"Sautter J, Faubel F, Buck M, Schmidt G. Artificial bandwidth extension using a conditional generative adversarial network with discriminative training. In: ICASSP 2019 - 2019 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP); 2019. pp. 7005\u20139. https:\/\/doi.org\/10.1109\/icassp.2019.8682649","DOI":"10.1109\/ICASSP.2019.8682649"},{"key":"pone.0359641.ref023","doi-asserted-by":"crossref","unstructured":"Hu J, Shen L, Sun G. Squeeze-and-excitation networks. In: 2018 IEEE\/CVF Conference on Computer Vision and Pattern Recognition; 2018. pp. 7132\u201341. https:\/\/doi.org\/10.1109\/cvpr.2018.00745","DOI":"10.1109\/CVPR.2018.00745"},{"key":"pone.0359641.ref024","doi-asserted-by":"crossref","first-page":"78979","DOI":"10.1109\/ACCESS.2020.2989861","article-title":"Combining multi-perspective attention mechanism with convolutional networks for monaural speech enhancement","volume":"8","author":"T Lan","year":"2020","journal-title":"IEEE Access"},{"key":"pone.0359641.ref025","doi-asserted-by":"crossref","first-page":"1600","DOI":"10.1109\/TASLP.2022.3155286","article-title":"SkipConvGAN: monaural speech dereverberation using generative adversarial networks via complex time-frequency masking","volume":"30","author":"V Kothapally","year":"2022","journal-title":"IEEE\/ACM Trans Audio Speech Lang Process"},{"key":"pone.0359641.ref026","doi-asserted-by":"crossref","first-page":"853","DOI":"10.1109\/LSP.2023.3293758","article-title":"GAN-in-GAN for monaural speech enhancement","volume":"30","author":"Y Duan","year":"2023","journal-title":"IEEE Signal Process Lett"},{"key":"pone.0359641.ref027","unstructured":"Arjovsky M, Chintala S, Bottou L. Wasserstein generative adversarial networks. In: Proceedings of Machine Learning Research; 2017. pp. 214\u201323. Available from: https:\/\/proceedings.mlr.press\/v70\/arjovsky17a.html"},{"key":"pone.0359641.ref028","doi-asserted-by":"crossref","unstructured":"Spadini T, Imai Aldeia GS, Barreto G, Alves K, Ferreira H, Suyama R, et al. On the application of SEGAN for the attenuation of the ego-noise in the speech sound source localization problem. In: 2019 Workshop on Communication Networks and Power Systems (WCNPS); 2019. pp. 1\u20134. https:\/\/doi.org\/10.1109\/wcnps.2019.8896308","DOI":"10.1109\/WCNPS.2019.8896308"},{"key":"pone.0359641.ref029","doi-asserted-by":"crossref","unstructured":"Mao X, Li Q, Xie H, Lau RYK, Wang Z, Smolley SP. Least squares generative adversarial networks. In: 2017 IEEE International Conference on Computer Vision (ICCV); 2017. pp. 2813\u201321. https:\/\/doi.org\/10.1109\/iccv.2017.304","DOI":"10.1109\/ICCV.2017.304"},{"key":"pone.0359641.ref030","doi-asserted-by":"crossref","unstructured":"Isola P, Zhu J-Y, Zhou T, Efros AA. Image-to-image translation with conditional adversarial networks. In: 2017 IEEE Conference on Computer Vision and Pattern Recognition (CVPR); 2017. pp. 5967\u201376. https:\/\/doi.org\/10.1109\/cvpr.2017.632","DOI":"10.1109\/CVPR.2017.632"},{"key":"pone.0359641.ref031","doi-asserted-by":"crossref","unstructured":"Pascual S, Bonafonte A, Serr\u00e0 J. SEGAN: speech enhancement generative adversarial network. In: Interspeech 2017; 2017. pp. 3642\u20136. https:\/\/doi.org\/10.21437\/interspeech.2017-1428","DOI":"10.21437\/Interspeech.2017-1428"},{"key":"pone.0359641.ref032","author":"C Valentini-Botinhao","year":"2017"},{"key":"pone.0359641.ref033","doi-asserted-by":"crossref","unstructured":"Phan H, Nguyen HL, Chen OY, Koch P, Duong NQK, McLoughlin I, et al. Self-attention generative adversarial network for speech enhancement. In: ICASSP 2021 - 2021 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP); 2021. pp. 7103\u20137. https:\/\/doi.org\/10.1109\/icassp39728.2021.9414265","DOI":"10.1109\/ICASSP39728.2021.9414265"},{"key":"pone.0359641.ref034","doi-asserted-by":"crossref","unstructured":"Kong Z, Ping W, Dantrey A, Catanzaro B. Speech denoising in the waveform domain with self-attention. In: ICASSP 2022 - 2022 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP); 2022. pp. 7867\u201371. https:\/\/doi.org\/10.1109\/icassp43922.2022.9746169","DOI":"10.1109\/ICASSP43922.2022.9746169"},{"key":"pone.0359641.ref035","doi-asserted-by":"crossref","unstructured":"Fu S-W, Yu C, Hsieh T-A, Plantinga P, Ravanelli M, Lu X, et al. MetricGAN+: an improved version of metricgan for speech enhancement. In: Interspeech 2021; 2021. pp. 201\u20135. https:\/\/doi.org\/10.21437\/interspeech.2021-599","DOI":"10.21437\/Interspeech.2021-599"},{"key":"pone.0359641.ref036","doi-asserted-by":"crossref","unstructured":"Cao R, Abdulatif S, Yang B. CMGAN: conformer-based metric gan for speech enhancement. In: Interspeech 2022; 2022. pp. 936\u201340. https:\/\/doi.org\/10.21437\/interspeech.2022-517","DOI":"10.21437\/Interspeech.2022-517"}],"container-title":["PLOS One"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/dx.plos.org\/10.1371\/journal.pone.0359641","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2026,10,1]],"date-time":"2026-10-01T17:26:17Z","timestamp":1790875577000},"score":1,"resource":{"primary":{"URL":"https:\/\/dx.plos.org\/10.1371\/journal.pone.0359641"}},"subtitle":[],"editor":[{"given":"Hashmat","family":"Fida","sequence":"first","affiliation":[{"name":"Lincoln University College","place":["MALAYSIA"]}],"role":[{"vocabulary":"crossref","role":"editor"}]}],"short-title":[],"issued":{"date-parts":[[2026,10,1]]},"references-count":36,"journal-issue":{"issue":"10","published-online":{"date-parts":[[2026,10,1]]}},"URL":"https:\/\/doi.org\/10.1371\/journal.pone.0359641","relation":{},"ISSN":["1932-6203"],"issn-type":[{"value":"1932-6203","type":"electronic"}],"subject":[],"published":{"date-parts":[[2026,10,1]]}}}