{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,3,11]],"date-time":"2026-03-11T03:36:15Z","timestamp":1773200175610,"version":"3.50.1"},"reference-count":27,"publisher":"Springer Science and Business Media LLC","issue":"10","license":[{"start":{"date-parts":[[2025,6,27]],"date-time":"2025-06-27T00:00:00Z","timestamp":1750982400000},"content-version":"tdm","delay-in-days":0,"URL":"https:\/\/www.springernature.com\/gp\/researchers\/text-and-data-mining"},{"start":{"date-parts":[[2025,6,27]],"date-time":"2025-06-27T00:00:00Z","timestamp":1750982400000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/www.springernature.com\/gp\/researchers\/text-and-data-mining"}],"funder":[{"DOI":"10.13039\/501100012579","name":"Natural Science Foundation of Qinghai Province","doi-asserted-by":"publisher","award":["2022-ZJ-925"],"award-info":[{"award-number":["2022-ZJ-925"]}],"id":[{"id":"10.13039\/501100012579","id-type":"DOI","asserted-by":"publisher"}]},{"DOI":"10.13039\/501100001809","name":"National Natural Science Foundation of China","doi-asserted-by":"crossref","award":["62066039"],"award-info":[{"award-number":["62066039"]}],"id":[{"id":"10.13039\/501100001809","id-type":"DOI","asserted-by":"crossref"}]}],"content-domain":{"domain":["link.springer.com"],"crossmark-restriction":false},"short-container-title":["SIViP"],"published-print":{"date-parts":[[2025,10]]},"DOI":"10.1007\/s11760-025-04400-4","type":"journal-article","created":{"date-parts":[[2025,6,27]],"date-time":"2025-06-27T12:25:43Z","timestamp":1751027143000},"update-policy":"https:\/\/doi.org\/10.1007\/springer_crossmark_policy","source":"Crossref","is-referenced-by-count":1,"title":["GD-Conformer: a Conformer-based gated dense encoder-decoder for monaural speech enhancement"],"prefix":"10.1007","volume":"19","author":[{"family":"Gengzangcuomao","sequence":"first","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Heming","family":"Huang","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Feipeng","family":"Da","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"297","published-online":{"date-parts":[[2025,6,27]]},"reference":[{"issue":"1","key":"4400_CR1","doi-asserted-by":"publisher","first-page":"478","DOI":"10.1109\/TCSS.2022.3228649","volume":"11","author":"Y Khurana","year":"2024","unstructured":"Khurana, Y., Gupta, S., Sathyaraj, R., et al.: ROBINNET: A multimodal speech emotion recognition system with speaker recognition for social interactions[J]. IEEE Trans. Comput. Soc. Syst. 11(1), 478\u2013487 (2024)","journal-title":"IEEE Trans. Comput. Soc. Syst."},{"key":"4400_CR2","doi-asserted-by":"publisher","first-page":"3255","DOI":"10.1109\/TASLP.2021.3120630","volume":"29","author":"VW Neo","year":"2021","unstructured":"Neo, V.W., Evers, C., Naylor, P.A.: Enhancement of noisy reverberant speech using polynomial matrix eigenvalue decomposition[J]. IEEE\/ACM Trans. Audio Speech Lang. Process. 29, 3255\u20133266 (2021)","journal-title":"IEEE\/ACM Trans. Audio Speech Lang. Process."},{"key":"4400_CR3","doi-asserted-by":"crossref","unstructured":"Wang, Z.Q., Zhu, X.F., Zhang, Z.H., et al.: SELM: Speech enhancement using discrete tokens and language models[C]. 2024 IEEE International Conference on Acoustics, Speech and Signal Processing, Seoul, Korea, 11561-11565 (2024)","DOI":"10.1109\/ICASSP48485.2024.10447464"},{"key":"4400_CR4","doi-asserted-by":"publisher","first-page":"1457","DOI":"10.1109\/TASLP.2024.3362691","volume":"32","author":"LH Sun","year":"2024","unstructured":"Sun, L.H., Yuan, S., Gong, A.F., Ye, L., et al.: Dual-Branch modeling based on State-Space model for speech enhancement[J]. IEEE\/ACM Trans. Audio Speech Lang. Process. 32, 1457\u20131467 (2024)","journal-title":"IEEE\/ACM Trans. Audio Speech Lang. Process."},{"key":"4400_CR5","doi-asserted-by":"crossref","unstructured":"Zhang, Z., Liang, X., Xu, R., et al.: Hybrid attention Time-Frequency analysis network for Single-Channel speech enhancement[C]. IEEE International Conference on Acoustics, Speech and Signal Processing, Seoul, Korea, 10426-10430 (2024)","DOI":"10.1109\/ICASSP48485.2024.10445944"},{"key":"4400_CR6","doi-asserted-by":"crossref","unstructured":"Fu, Y.H., Liu, Y., Li, J.D., et al.: Uformer: A U-net Based dilated complex & real Dual-Path conformer network for simultaneous speech enhancement and dereverberation[C]. 2022 IEEE International Conference on Acoustics, Speech and Signal Processing, Singapore, Singapore, 7417-7421 (2022)","DOI":"10.1109\/ICASSP43922.2022.9746020"},{"key":"4400_CR7","doi-asserted-by":"crossref","unstructured":"Zhang, S., Qiu, Z., Takeuchi, D., et al.: Unrestricted global phase Bias-Aware Single-Channel speech enhancement with Conformer-Based Metric-GAN[C]. IEEE International Conference on Acoustics, Speech and Signal Processing , Seoul, Korea, 1026-1030 (2024)","DOI":"10.1109\/ICASSP48485.2024.10446743"},{"issue":"1","key":"4400_CR8","first-page":"1","volume":"45","author":"C Jannu","year":"2023","unstructured":"Jannu, C., Vanambathina, S.D.: DCT based densely connected convolutional GRU for real-time speech enhancement[J]. J. Intell. Fuzzy Syst. 45(1), 1\u201314 (2023)","journal-title":"J. Intell. Fuzzy Syst."},{"key":"4400_CR9","doi-asserted-by":"publisher","first-page":"2561","DOI":"10.1109\/TASLP.2021.3092585","volume":"29","author":"L Zhang","year":"2021","unstructured":"Zhang, L., Wang, M.J., Zhang, Q.Q., et al.: PhaseDCN: A Phase-Enhanced Dual-Path dilated convolutional network for Single-Channel speech enhancement[J]. IEEE\/ACM Trans. Audio Speech Lang. Process. 29, 2561\u20132574 (2021)","journal-title":"IEEE\/ACM Trans. Audio Speech Lang. Process."},{"key":"4400_CR10","doi-asserted-by":"crossref","unstructured":"Chen, J.J., Mao, Q.R., Liu, D.: Dual-path transformer network: Direct Context-Aware modeling for End-To-End monaural speech separation[C]. Interspeech, Shanghai, China, 2642-2646 (2020)","DOI":"10.21437\/Interspeech.2020-2205"},{"key":"4400_CR11","doi-asserted-by":"crossref","unstructured":"Deng, F., Jiang, T., Wang, X.R., et al.: NAAGN: Noise-Aware Attention-Gated network for speech enhancement[C]. Interspeech, Shanghai, China, 2457-2461 (2020)","DOI":"10.21437\/Interspeech.2020-1133"},{"key":"4400_CR12","doi-asserted-by":"crossref","unstructured":"Tang, C.X., Luo, C., Zhao, Z.Y., et al.: Joint time frequency and time domain learning for speech enhancement[C]. IEEE International Joint Conference on Artificial Intelligence, Yokohama, Japan, 3816-3822 (2020)","DOI":"10.24963\/ijcai.2020\/528"},{"key":"4400_CR13","doi-asserted-by":"publisher","first-page":"3365","DOI":"10.1109\/TASLP.2024.3423652","volume":"32","author":"X Yu","year":"2024","unstructured":"Yu, X., Guo, D., Zhang, J., et al.: ROSE: A Recognition-Oriented speech enhancement framework in air traffic control using Multi-Objective learning[J]. IEEE\/ACM Trans. Audio Speech Lang. Process. 32, 3365\u20133378 (2024)","journal-title":"IEEE\/ACM Trans. Audio Speech Lang. Process."},{"key":"4400_CR14","doi-asserted-by":"crossref","unstructured":"Yang, L., Liu, W., Meng, R., et al.: Fspen: An Ultra-Lightweight network for real time speech enhancement[C]. IEEE International Conference on Acoustics, Speech and Signal Processing, Seoul, Korea, 10671-10675 (2024)","DOI":"10.1109\/ICASSP48485.2024.10446016"},{"key":"4400_CR15","doi-asserted-by":"crossref","unstructured":"Lu, Y.J., Wang, Z.Q., Watanabe, S., et al.: Conditional diffusion probabilistic model for speech enhancement[C]. IEEE International Conference on Acoustics, Speech and Signal Processing, Singapore, Singapore, 7402-7406 (2022)","DOI":"10.1109\/ICASSP43922.2022.9746901"},{"key":"4400_CR16","doi-asserted-by":"crossref","unstructured":"Schroter, H., Escalante-B, A.N., Rosenkranz, T., et al.: Deepfilternet: A low complexity speech enhancement framework for Full-Band audio based on deep filtering[C]. IEEE International Conference on Acoustics, Speech and Signal Processing, Singapore, Singapore, 7407-7411 (2022)","DOI":"10.1109\/ICASSP43922.2022.9747055"},{"key":"4400_CR17","doi-asserted-by":"publisher","first-page":"250","DOI":"10.1109\/TASLP.2023.3328282","volume":"32","author":"KM Nayem","year":"2024","unstructured":"Nayem, K.M., Williamson, D.S.: Attention-Based speech enhancement using human quality perception modeling[J]. IEEE\/ACM Trans. Audio Speech Lang. Process. 32, 250\u2013260 (2024)","journal-title":"IEEE\/ACM Trans. Audio Speech Lang. Process."},{"key":"4400_CR18","doi-asserted-by":"crossref","unstructured":"Strauss, M., Edler, B.: A Flow-Based neural network for time domain speech enhancement[C]. IEEE International Conference on Acoustics, Speech and Signal Processing, 5754-5758 (2021)","DOI":"10.1109\/ICASSP39728.2021.9413999"},{"key":"4400_CR19","doi-asserted-by":"crossref","unstructured":"Chen, C., Hu, Y., Weng, W., et al.: Metric-Oriented speech enhancement using diffusion probabilistic model[C]. IEEE International Conference on Acoustics, Speech and Signal Processing, Rhodes Island, Greece, 1-5 (2023)","DOI":"10.1109\/ICASSP49357.2023.10095046"},{"key":"4400_CR20","doi-asserted-by":"crossref","unstructured":"Kim, E., Seo, H.: SE-Conformer: Time-Domain speech enhancement using conformer[C]. Interspeech, Czech Republic, 2736-2740 (2021)","DOI":"10.21437\/Interspeech.2021-2207"},{"key":"4400_CR21","doi-asserted-by":"crossref","unstructured":"Tolooshams, B., Giri, R., Song, A.H., et al.: Channel-attention dense U-Net for multichannel speech enhancement[C]. IEEE International Conference on Acoustics, Speech and Signal Processing, Virtual Barcelona, 836\u2013840 (2020)","DOI":"10.1109\/ICASSP40776.2020.9053989"},{"key":"4400_CR22","doi-asserted-by":"crossref","unstructured":"Luo, Y., Chen, Z., Mesgarani, N., et al.: End-to-End microphone permutation and number invariant Multi-Channel speech separation[C]. IEEE International Conference on Acoustics, Speech and Signal Processing, Virtual Barcelona, 6394\u20136398 (2020)","DOI":"10.1109\/ICASSP40776.2020.9054177"},{"key":"4400_CR23","doi-asserted-by":"crossref","unstructured":"Wang, Z.Q., Wang, D.: Multi-Microphone complex spectral mapping for speech dereverberation[C]. IEEE International Conference on Acoustics, Speech and Signal Processing, Virtual Barcelona, 486\u2013490 (2020)","DOI":"10.1109\/ICASSP40776.2020.9053610"},{"key":"4400_CR24","doi-asserted-by":"crossref","unstructured":"Pandey, A., Xu, B., Kumar, A., et al.: TPARN: Triple-Path attentive recurrent network for Time-Domain Multi-Channel speech enhancement[C]. IEEE International Conference on Acoustics, Speech and Signal Processing, Singapore, Singapore, 6497\u20136501 (2022)","DOI":"10.1109\/ICASSP43922.2022.9747373"},{"key":"4400_CR25","doi-asserted-by":"crossref","unstructured":"Pandey, A., Xu, B., Kumar, A., et al., Multichannel speech enhancement without beamforming[C]. IEEE International Conference on Acoustics, Speech and Signal Processing, Singapore, Singapore, 6502\u20136506 (2022)","DOI":"10.1109\/ICASSP43922.2022.9746704"},{"key":"4400_CR26","doi-asserted-by":"crossref","unstructured":"Liu, J., Zhang, X.: DRC-NET: Densely connected recurrent convolutional neural network for speech dereverberation[C]. IEEE International Conference on Acoustics, Speech and Signal Processing, Singapore, Singapore, 166\u2013170 (2022)","DOI":"10.1109\/ICASSP43922.2022.9747111"},{"key":"4400_CR27","doi-asserted-by":"publisher","first-page":"155","DOI":"10.1109\/LSP.2023.3244428","volume":"30","author":"D Lee","year":"2023","unstructured":"Lee, D., Chio, J.W.: DeFT-AN: Dense Frequency-Time attentive network for multichannel speech enhancement[J]. IEEE Signal Process. Lett. 30, 155\u2013159 (2023)","journal-title":"IEEE Signal Process. Lett."}],"container-title":["Signal, Image and Video Processing"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/link.springer.com\/content\/pdf\/10.1007\/s11760-025-04400-4.pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/link.springer.com\/article\/10.1007\/s11760-025-04400-4\/fulltext.html","content-type":"text\/html","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/link.springer.com\/content\/pdf\/10.1007\/s11760-025-04400-4.pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,9,6]],"date-time":"2025-09-06T23:44:45Z","timestamp":1757202285000},"score":1,"resource":{"primary":{"URL":"https:\/\/link.springer.com\/10.1007\/s11760-025-04400-4"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2025,6,27]]},"references-count":27,"journal-issue":{"issue":"10","published-print":{"date-parts":[[2025,10]]}},"alternative-id":["4400"],"URL":"https:\/\/doi.org\/10.1007\/s11760-025-04400-4","relation":{"has-preprint":[{"id-type":"doi","id":"10.21203\/rs.3.rs-6111294\/v1","asserted-by":"object"}]},"ISSN":["1863-1703","1863-1711"],"issn-type":[{"value":"1863-1703","type":"print"},{"value":"1863-1711","type":"electronic"}],"subject":[],"published":{"date-parts":[[2025,6,27]]},"assertion":[{"value":"26 February 2025","order":1,"name":"received","label":"Received","group":{"name":"ArticleHistory","label":"Article History"}},{"value":"9 June 2025","order":2,"name":"revised","label":"Revised","group":{"name":"ArticleHistory","label":"Article History"}},{"value":"13 June 2025","order":3,"name":"accepted","label":"Accepted","group":{"name":"ArticleHistory","label":"Article History"}},{"value":"27 June 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":"Not applicable.","order":2,"name":"Ethics","group":{"name":"EthicsHeading","label":"Ethics approval and consent to participate"}},{"value":"All authors of this study agree to publication.","order":3,"name":"Ethics","group":{"name":"EthicsHeading","label":"Consent for publication"}}],"article-number":"815"}}