{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,6,27]],"date-time":"2026-06-27T16:47:56Z","timestamp":1782578876920,"version":"3.54.5"},"reference-count":47,"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"}],"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.2026.103424","type":"journal-article","created":{"date-parts":[[2026,5,28]],"date-time":"2026-05-28T15:01:53Z","timestamp":1779980513000},"page":"103424","update-policy":"https:\/\/doi.org\/10.1016\/elsevier_cm_policy","source":"Crossref","is-referenced-by-count":0,"special_numbering":"C","title":["D-CrossNet: A dual-path cross-attention network with adaptive multi-spectral joint loss for speech enhancement in UAV noise"],"prefix":"10.1016","volume":"182","author":[{"given":"Tao","family":"Zhang","sequence":"first","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Ruifeng","family":"Tian","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Yang","family":"Jiao","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Weiwei","family":"Zhang","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-4837-7857","authenticated-orcid":false,"given":"Yanzhang","family":"Geng","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"78","reference":[{"issue":"2","key":"10.1016\/j.specom.2026.103424_b1","doi-asserted-by":"crossref","first-page":"192","DOI":"10.1111\/j.1469-7580.2011.01384.x","article-title":"The three-dimensional shape of serrations at barn owl wings: towards a typical natural serration as a role model for biomimetic applications","volume":"219","author":"Bachmann","year":"2011","journal-title":"J. Anat."},{"key":"10.1016\/j.specom.2026.103424_b2","doi-asserted-by":"crossref","unstructured":"Bi, H., Ma, F., Abhayapala, T.D., Samarasinghe, P.N., 2021. Spherical array based drone noise measurements and modelling for drone noise reduction via propeller phase control. In: IEEE Workshop Applications of Signal Processing to Audio and Acoustics. WASPAA, pp. 286\u2013290.","DOI":"10.1109\/WASPAA52581.2021.9632719"},{"key":"10.1016\/j.specom.2026.103424_b3","doi-asserted-by":"crossref","unstructured":"Bi, H., Ma, F., Abhayapala, T.D., Samarasinghe, P.N., 2022. Spherical sector harmonics based directional drone noise reduction. In: International Workshop on Acoustic Signal Enhancement. IWAENC, pp. 1\u20135.","DOI":"10.1109\/IWAENC53105.2022.9914790"},{"issue":"12","key":"10.1016\/j.specom.2026.103424_b4","doi-asserted-by":"crossref","DOI":"10.1121\/10.0039953","article-title":"Directional active noise control for drone noise reduction","volume":"5","author":"Bi","year":"2025","journal-title":"JASA Express Lett."},{"key":"10.1016\/j.specom.2026.103424_b5","series-title":"Microphone Arrays: Signal Processing Techniques and Applications","author":"Brandstein","year":"2001"},{"key":"10.1016\/j.specom.2026.103424_b6","doi-asserted-by":"crossref","unstructured":"Bu, H., Du, J., Na, X., et al., 2017. AISHELL-1: An open-source mandarin speech recognition baseline. In: 2017 20th Conference of the Oriental Chapter of the International Coordinating Committee on Speech Databases and Speech I\/O Systems and Assessment. pp. 1\u20135.","DOI":"10.1109\/ICSDA.2017.8384449"},{"key":"10.1016\/j.specom.2026.103424_b7","unstructured":"Chaitanya, P., Narayanan, S., Phillip, J., et al., 2016. Leading edge serration geometries for significantly enhanced leading edge noise reductions. In: 22nd AIAA\/CEAS Aeroacoustics Conference. p. 2736."},{"key":"10.1016\/j.specom.2026.103424_b8","doi-asserted-by":"crossref","unstructured":"Chen, X., Bi, H., Lai, W.-T., et al., 2024a. Monaural speech enhancement on drone via adapter based transfer learning. In: 2024 18th International Workshop on Acoustic Signal Enhancement. IWAENC, pp. 85\u201389.","DOI":"10.1109\/IWAENC61483.2024.10694014"},{"key":"10.1016\/j.specom.2026.103424_b9","doi-asserted-by":"crossref","unstructured":"Chen, X., Bi, H., Lai, W.-T., et al., 2024b. Monaural speech enhancement on drone via adapter based transfer learning. In: 2024 18th International Workshop on Acoustic Signal Enhancement. IWAENC, pp. 85\u201389.","DOI":"10.1109\/IWAENC61483.2024.10694014"},{"key":"10.1016\/j.specom.2026.103424_b10","doi-asserted-by":"crossref","unstructured":"Chen, F., Kong, M., Pan, Z., Ding, B., Peng, J., 2025. Lightweight neural networks for speech enhancement under drone noise: A comprehensive evaluation. In: International Conference Informatics Networking and Computing. ICINC.","DOI":"10.1117\/12.3056881"},{"key":"10.1016\/j.specom.2026.103424_b11","unstructured":"Choi, H., Kim, J.H., Huh, J., et al., 2018. Phase-aware speech enhancement with deep complex U-Net. In: International Conference on Learning Representations. ICLR."},{"key":"10.1016\/j.specom.2026.103424_b12","doi-asserted-by":"crossref","unstructured":"Chun, C., Jeon, K.M., Kim, T., et al., 2019a. Drone noise reduction using deep convolutional autoencoder for UAV acoustic sensor networks. In: 2019 IEEE 16th International Conference on Mobile Ad Hoc and Sensor Systems Workshops. MASSW, pp. 168\u2013169.","DOI":"10.1109\/MASSW.2019.00043"},{"key":"10.1016\/j.specom.2026.103424_b13","doi-asserted-by":"crossref","unstructured":"Chun, C., Jeon, K.M., Kim, T., et al., 2019b. Drone noise reduction using deep convolutional autoencoder for UAV acoustic sensor networks. In: 2019 IEEE 16th International Conference on Mobile Ad Hoc and Sensor Systems Workshops. MASSW, pp. 168\u2013169.","DOI":"10.1109\/MASSW.2019.00043"},{"key":"10.1016\/j.specom.2026.103424_b14","unstructured":"Fernandes, R.P., Santos, E.C., 2015. A first approach to signal enhancement for quadcopters using piezoelectric sensors. In: International Conference on Transformative Science and Engineering, Business and Social Innovation. pp. 536\u2013541."},{"issue":"1\u20132","key":"10.1016\/j.specom.2026.103424_b15","first-page":"5","article-title":"A speech enhancement method based on the combination of microphone array and parabolic reflector","volume":"70","author":"Geng","year":"2022","journal-title":"J. Audio Eng. Soc."},{"key":"10.1016\/j.specom.2026.103424_b16","unstructured":"Hammond, D., McKinley, R., Hale, B., 1998. Noise Reduction Efforts for Special Operations C-130 Aircraft Using Active Synchrophaser Control. Tech. Rep. AD-A434029."},{"key":"10.1016\/j.specom.2026.103424_b17","series-title":"Active Control of Noise and Vibration","author":"Hansen","year":"2010"},{"key":"10.1016\/j.specom.2026.103424_b18","series-title":"DCCRN: deep complex convolution recurrent network for phase-aware speech enhancement","author":"Hu","year":"2020"},{"issue":"8","key":"10.1016\/j.specom.2026.103424_b19","doi-asserted-by":"crossref","first-page":"1271","DOI":"10.2514\/3.9431","article-title":"Noise control characteristics of synchrophasin part 2: experimental investigation","volume":"24","author":"Jones","year":"1986","journal-title":"AIAA J."},{"key":"10.1016\/j.specom.2026.103424_b20","unstructured":"Kurtz, D.W., Marte, J.E., 1970. A Review of Aerodynamic Noise from Propellers, Rotors, and Lift Fans. Tech. Rep. NASA-CR-107568, JPL-TR-32-146-2."},{"key":"10.1016\/j.specom.2026.103424_b21","unstructured":"Leventhal, H., Wong, L., 1988. A Review of Active Attenuation and Development of an Active Attenuator Open Refuge. Tech. Rep."},{"issue":"4","key":"10.1016\/j.specom.2026.103424_b22","doi-asserted-by":"crossref","first-page":"1056","DOI":"10.7305\/automatika.2017.12.1706","article-title":"Active noise control in light aircraft cabin using multichannel coherent method","volume":"58","author":"Miljkovi\u0107","year":"2018","journal-title":"Automatika"},{"key":"10.1016\/j.specom.2026.103424_b23","doi-asserted-by":"crossref","unstructured":"Miljkovi\u0107, D., 2018b. Methods for attenuation of unmanned aerial vehicle noise. In: 2018 41st International Convention on Information and Communication Technology, Electronics and Microelectronics. MIPRO, pp. 0914\u20130919.","DOI":"10.23919\/MIPRO.2018.8400169"},{"key":"10.1016\/j.specom.2026.103424_b24","doi-asserted-by":"crossref","first-page":"22993","DOI":"10.1109\/ACCESS.2023.3253719","article-title":"Deep learning models for single-channel speech enhancement on drones","volume":"11","author":"Mukhutdinov","year":"2023","journal-title":"IEEE Access"},{"issue":"11","key":"10.1016\/j.specom.2026.103424_b25","first-page":"1541","article-title":"Active noise control: A tutorial review","volume":"75","author":"Nelson","year":"1992","journal-title":"IEICE Trans. Fundam. Electron. Commun. Comput. Sci."},{"key":"10.1016\/j.specom.2026.103424_b26","doi-asserted-by":"crossref","unstructured":"Ning, Z., Wlezien, R.W., Hu, H., 2017. An experimental study on small UAV propellers with serrated trailing edges. In: 47th AIAA Fluid Dynamics Conference.","DOI":"10.2514\/6.2017-3813"},{"key":"10.1016\/j.specom.2026.103424_b27","doi-asserted-by":"crossref","unstructured":"Oleson, R.D., Beach, W.P., Patrick, H., 1998. Small aircraft propeller noise with ducted propeller. In: 4th AIAA\/CEAS Aeroacoustics Conference.","DOI":"10.2514\/6.1998-2284"},{"key":"10.1016\/j.specom.2026.103424_b28","series-title":"Acoustics 2012","article-title":"A UAV motor denoising technique to improve localization of surrounding noisy aircrafts: proof of concept for anti-collision systems","author":"Patrick","year":"2012"},{"issue":"1","key":"10.1016\/j.specom.2026.103424_b29","doi-asserted-by":"crossref","first-page":"183","DOI":"10.1109\/TSC.2023.3338488","article-title":"GAN based audio noise suppression for victim detection at disaster sites with UAV","volume":"17","author":"Premachandra","year":"2024","journal-title":"IEEE Trans. Serv. Comput."},{"key":"10.1016\/j.specom.2026.103424_b30","article-title":"AISHELL-3: A multi-speaker mandarin TTS corpus and the baselines","author":"Shi","year":"2020","journal-title":"Comput. Res. Repos."},{"key":"10.1016\/j.specom.2026.103424_b31","series-title":"11th Acusticum","first-page":"1","article-title":"Empirical study on active noise control in UAVs","author":"Steiner","year":"2025"},{"key":"10.1016\/j.specom.2026.103424_b32","doi-asserted-by":"crossref","first-page":"02112","DOI":"10.1051\/epjconf\/201611402112","article-title":"Measurement of noise and its correlation to performance and geometry of small aircraft propellers","volume":"114","author":"\u0160torch","year":"2016","journal-title":"EPJ Web Conf."},{"key":"10.1016\/j.specom.2026.103424_b33","doi-asserted-by":"crossref","unstructured":"Tan, K., Wang, D., 2018. A convolutional recurrent neural network for real-time speech enhancement. In: Proc. Interspeech. pp. 3229\u20133233.","DOI":"10.21437\/Interspeech.2018-1405"},{"key":"10.1016\/j.specom.2026.103424_b34","doi-asserted-by":"crossref","first-page":"200","DOI":"10.1016\/j.jsv.2018.01.017","article-title":"On the study of wavy leading-edge vanes to achieve low fan interaction noise","volume":"419","author":"Tong","year":"2018","journal-title":"J. Sound Vib."},{"key":"10.1016\/j.specom.2026.103424_b35","unstructured":"Vaswani, A., Shazeer, N., Parmar, N., et al., 2017. Attention is all you need. In: Proceedings of the 31st International Conference on Neural Information Processing Systems. Red Hook, NY, USA, pp. 6000\u20136010."},{"key":"10.1016\/j.specom.2026.103424_b36","unstructured":"Wabnitz, A., Epain, N., Jin, C., et al., 2010. Room acoustics simulation for multichannel microphone arrays. In: Proceedings of the International Symposium on Room Acoustics. ISRA, Melbourne, Australia."},{"issue":"1","key":"10.1016\/j.specom.2026.103424_b37","doi-asserted-by":"crossref","DOI":"10.1098\/rsfs.2016.0078","article-title":"Features of owl wings that promote silent flight","volume":"7","author":"Wagner","year":"2017","journal-title":"Interface Focus."},{"issue":"11","key":"10.1016\/j.specom.2026.103424_b38","doi-asserted-by":"crossref","first-page":"4570","DOI":"10.1109\/JSEN.2018.2825879","article-title":"Acoustic sensing from a multi-rotor drone","volume":"18","author":"Wang","year":"2018","journal-title":"IEEE Sens. J."},{"key":"10.1016\/j.specom.2026.103424_b39","doi-asserted-by":"crossref","first-page":"2523","DOI":"10.1109\/TASLP.2020.3015027","article-title":"A blind source separation framework for ego-noise reduction on multi-rotor drones","volume":"28","author":"Wang","year":"2020","journal-title":"IEEE\/ACM Trans. Audio Speech Lang. Process."},{"issue":"6","key":"10.1016\/j.specom.2026.103424_b40","doi-asserted-by":"crossref","first-page":"871","DOI":"10.1109\/TETCI.2020.3014934","article-title":"Deep learning assisted time-frequency processing for speech enhancement on drones","volume":"5","author":"Wang","year":"2021","journal-title":"IEEE Trans. Emerg. Top. Comput. Intell."},{"key":"10.1016\/j.specom.2026.103424_b41","doi-asserted-by":"crossref","first-page":"3221","DOI":"10.1109\/TASLP.2023.3304482","article-title":"TF-GridNet: Integrating full- and sub-band modeling for speech separation","volume":"31","author":"Wang","year":"2023","journal-title":"IEEE\/ACM Trans. Audio Speech Lang. Process."},{"key":"10.1016\/j.specom.2026.103424_b42","series-title":"ICASSP","first-page":"1","article-title":"TF-GRIDNET: Making time-frequency domain models great again for monaural speaker separation","author":"Wang","year":"2023"},{"issue":"4","key":"10.1016\/j.specom.2026.103424_b43","doi-asserted-by":"crossref","first-page":"767","DOI":"10.1007\/s42235-020-0054-z","article-title":"Noise reduction of UAV using biomimetic propellers with varied morphologies leading-edge serration","volume":"17","author":"Wei","year":"2020","journal-title":"J. Bionic Eng."},{"key":"10.1016\/j.specom.2026.103424_b44","doi-asserted-by":"crossref","first-page":"2491","DOI":"10.1109\/TASLP.2023.3288410","article-title":"Rotor noise-aware noise covariance matrix estimation for unmanned aerial vehicle audition","volume":"31","author":"Yen","year":"2023","journal-title":"IEEE\/ACM Trans. Audio Speech Lang. Process."},{"key":"10.1016\/j.specom.2026.103424_b45","doi-asserted-by":"crossref","unstructured":"Yoon, S., Park, S., Yoo, S., 2016. Two-stage adaptive noise reduction system for broadcasting multicopters. In: 2016 IEEE International Conference on Consumer Electronics. ICCE, pp. 219\u2013222.","DOI":"10.1109\/ICCE.2016.7430588"},{"key":"10.1016\/j.specom.2026.103424_b46","article-title":"NRSRNet: Speech enhancement network based on noise reduction and restoration module under extremely low SNR conditions","volume":"241","author":"Zhang","year":"2025","journal-title":"Appl. Acoust."},{"key":"10.1016\/j.specom.2026.103424_b47","series-title":"2022 IEEE International Conference on Acoustics, Speech and Signal Processing","article-title":"FRCRN: Boosting feature representation using frequency recurrence for monaural speech enhancement","author":"Zhao","year":"2022"}],"container-title":["Speech Communication"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/api.elsevier.com\/content\/article\/PII:S0167639326000725?httpAccept=text\/xml","content-type":"text\/xml","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/api.elsevier.com\/content\/article\/PII:S0167639326000725?httpAccept=text\/plain","content-type":"text\/plain","content-version":"vor","intended-application":"text-mining"}],"deposited":{"date-parts":[[2026,6,27]],"date-time":"2026-06-27T16:17:48Z","timestamp":1782577068000},"score":1,"resource":{"primary":{"URL":"https:\/\/linkinghub.elsevier.com\/retrieve\/pii\/S0167639326000725"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2026,7]]},"references-count":47,"alternative-id":["S0167639326000725"],"URL":"https:\/\/doi.org\/10.1016\/j.specom.2026.103424","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":"D-CrossNet: A dual-path cross-attention network with adaptive multi-spectral joint loss for speech enhancement in UAV noise","name":"articletitle","label":"Article Title"},{"value":"Speech Communication","name":"journaltitle","label":"Journal Title"},{"value":"https:\/\/doi.org\/10.1016\/j.specom.2026.103424","name":"articlelink","label":"CrossRef DOI link to publisher maintained version"},{"value":"article","name":"content_type","label":"Content Type"},{"value":"\u00a9 2026 Published by Elsevier B.V.","name":"copyright","label":"Copyright"}],"article-number":"103424"}}