{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2025,12,31]],"date-time":"2025-12-31T09:42:04Z","timestamp":1767174124697,"version":"build-2238731810"},"reference-count":45,"publisher":"Springer Science and Business Media LLC","issue":"1","license":[{"start":{"date-parts":[[2025,9,2]],"date-time":"2025-09-02T00:00:00Z","timestamp":1756771200000},"content-version":"tdm","delay-in-days":0,"URL":"https:\/\/creativecommons.org\/licenses\/by-nc-nd\/4.0"},{"start":{"date-parts":[[2025,9,2]],"date-time":"2025-09-02T00:00:00Z","timestamp":1756771200000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/creativecommons.org\/licenses\/by-nc-nd\/4.0"}],"funder":[{"name":"Xi\u2019an Science and Technology Plan Project, China Grant","award":["No. 24GXFW0009"],"award-info":[{"award-number":["No. 24GXFW0009"]}]},{"name":"Xi\u2019an Science and Technology Plan Project, China Grant","award":["No. 24GXFW0009"],"award-info":[{"award-number":["No. 24GXFW0009"]}]},{"name":"the Key Laboratory of the Ministry of Culture and Tourism","award":["No.2024-09, No.2023-02"],"award-info":[{"award-number":["No.2024-09, No.2023-02"]}]},{"name":"the Key Laboratory of the Ministry of Culture and Tourism","award":["No.2024-09, No.2023-02"],"award-info":[{"award-number":["No.2024-09, No.2023-02"]}]},{"name":"the Key Laboratory of the Ministry of Culture and Tourism","award":["No.2024-09, No.2023-02"],"award-info":[{"award-number":["No.2024-09, No.2023-02"]}]},{"name":"the Fundamental Research Funds for the Central Universities, China Grant","award":["No.GK202205035, No. GK202101004, No. GK202407007"],"award-info":[{"award-number":["No.GK202205035, No. GK202101004, No. GK202407007"]}]},{"name":"the Shaanxi Key Science and Technology Innovation Team Project","award":["No. 2022TD-26"],"award-info":[{"award-number":["No. 2022TD-26"]}]},{"DOI":"10.13039\/501100001809","name":"the National Natural Science Foundation of China","doi-asserted-by":"crossref","award":["No. 62377034"],"award-info":[{"award-number":["No. 62377034"]}],"id":[{"id":"10.13039\/501100001809","id-type":"DOI","asserted-by":"crossref"}]}],"content-domain":{"domain":["link.springer.com"],"crossmark-restriction":false},"short-container-title":["EURASIP J. Adv. Signal Process."],"DOI":"10.1186\/s13634-025-01249-0","type":"journal-article","created":{"date-parts":[[2025,9,2]],"date-time":"2025-09-02T05:45:16Z","timestamp":1756791916000},"update-policy":"https:\/\/doi.org\/10.1007\/springer_crossmark_policy","source":"Crossref","is-referenced-by-count":1,"title":["TFSWA-ResUNet: music source separation with time\u2013frequency sequence and shifted window attention-based ResUNet"],"prefix":"10.1186","volume":"2025","author":[{"given":"Zhenyu","family":"Yao","sequence":"first","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Yuping","family":"Su","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Honghong","family":"Yang","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Yumei","family":"Zhang","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Xiaojun","family":"Wu","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"297","published-online":{"date-parts":[[2025,9,2]]},"reference":[{"key":"1249_CR1","unstructured":"J.L. Ba, J.R. Kiros, G.E. Hinton, Layer normalization. ArXiv preprint arXiv:1607.06450 (2016)"},{"issue":"1","key":"1249_CR2","doi-asserted-by":"publisher","first-page":"31","DOI":"10.1109\/MSP.2018.2874719","volume":"36","author":"E Cano","year":"2019","unstructured":"E. Cano, D. FitzGerald, A. Liutkus et al., Musical source separation: An introduction. IEEE Signal Process. Mag. 36(1), 31\u201340 (2019)","journal-title":"IEEE Signal Process. Mag."},{"key":"1249_CR3","unstructured":"J. Chen, Y. Lu, Q. Yu, et\u00a0al. Transunet: Transformers make strong encoders for medical image segmentation. ArXiv preprint arXiv:2102.04306 (2021)"},{"key":"1249_CR4","unstructured":"W. Choi, S.L. Walsh, M. Kawasaki, Investigating U-Nets with various intermediate blocks for spectrogram-based singing voice separation. In: Proceedings of the 21st International Society for Music Information Retrieval Conference (ISMIR 2020) (2020)"},{"key":"1249_CR5","doi-asserted-by":"crossref","unstructured":"W. Choi, M. Kim, J. Chung, et\u00a0al., Lasaft: Latent source attentive frequency transformation for conditioned source separation. In: ICASSP 2021-2021 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP), pp 171\u2013175 (2021)","DOI":"10.1109\/ICASSP39728.2021.9413896"},{"key":"1249_CR6","unstructured":"A. Dosovitskiy, L. Beyer, A. Kolesnikov, et\u00a0al., An image is worth 16x16 words: Transformers for image recognition at scale. In: International Conference on Learning Representations (ICLR) (2021)"},{"issue":"1","key":"1249_CR7","doi-asserted-by":"publisher","first-page":"295","DOI":"10.1002\/aris.1440370108","volume":"37","author":"JS Downie","year":"2003","unstructured":"J.S. Downie, Music information retrieval. Ann. Rev. Inf. Sci. Technol. 37(1), 295\u2013340 (2003)","journal-title":"Ann. Rev. Inf. Sci. Technol."},{"key":"1249_CR8","unstructured":"A. D\u00e9fossez, Hybrid spectrogram and waveform source separation. In: Proceedings of the ISMIR 2021 Workshop on Music Source Separation, pp 11\u201318 (2021)"},{"key":"1249_CR9","unstructured":"A. D\u00e9fossez, N. Usunier, L. Bottou, et\u00a0al., Music source separation in the waveform domain. ArXiv preprint arXiv:1911.13254 (2019)"},{"key":"1249_CR10","unstructured":"D. Hendrycks, K. Gimpel, Gaussian error linear units (gelus). ArXiv preprint arXiv:1606.08415 (2016)"},{"issue":"50","key":"1249_CR11","doi-asserted-by":"publisher","first-page":"2154","DOI":"10.21105\/joss.02154","volume":"5","author":"R Hennequin","year":"2020","unstructured":"R. Hennequin, A. Khlif, F. Voituret et al., Spleeter: A fast and efficient music source separation tool with pre-trained models. J. Open Sour. Softwa. 5(50), 2154 (2020)","journal-title":"J. Open Sour. Softwa."},{"key":"1249_CR12","doi-asserted-by":"publisher","first-page":"1517","DOI":"10.1109\/LSP.2022.3187316","volume":"29","author":"Y Hu","year":"2022","unstructured":"Y. Hu, Y. Chen, W. Yang et al., Hierarchic temporal convolutional network with cross-domain encoder for music source separation. IEEE Signal Process. Lett. 29, 1517\u20131521 (2022)","journal-title":"IEEE Signal Process. Lett."},{"key":"1249_CR13","unstructured":"A. Jansson, E.J. Humphrey, N. Montecchio, et\u00a0al., Singing voice separation with deep u-net convolutional networks. In: International Society for Music Information Retrieval Conference, pp 745\u2013751 (2017)"},{"key":"1249_CR14","first-page":"3709","volume":"2023","author":"J Kim","year":"2023","unstructured":"J. Kim, H.G. Kang, Contrastive learning based deep latent masking for music source separation. Interspeech 2023, 3709\u20133713 (2023)","journal-title":"Interspeech"},{"key":"1249_CR15","unstructured":"M. Kim, W. Choi, J. Chung, et\u00a0al., Kuielab-mdx-net: A two-stream neural network for music demixing. In: Proceedings of the MDX Workshop at ISMIR, Online (2021)"},{"key":"1249_CR16","unstructured":"M. Kim, J.H. Lee, S. Jung, Sound demixing challenge 2023 music demixing track technical report: Tfc-tdf-unet v3. ArXiv preprint arXiv:2306.09382 (2023)"},{"key":"1249_CR17","unstructured":"Q. Kong, Y. Cao, H. Liu, et\u00a0al., Decoupling magnitude and phase estimation with deep resunet for music source separation. In: Proceedings of the 22nd International Conference on Music Information Retrieval (ISMIR), pp 342\u2013349 (2021)"},{"key":"1249_CR18","doi-asserted-by":"crossref","unstructured":"T. Li, J. Chen, H. Hou, et\u00a0al., Sams-net: A sliced attention-based neural network for music source separation. In: 2021 12th International Symposium on Chinese Spoken Language Processing (ISCSLP), pp 1\u20135 (2021)","DOI":"10.1109\/ISCSLP49672.2021.9362081"},{"key":"1249_CR19","unstructured":"L. Lin, Q. Kong, J. Jiang, et\u00a0al., A unified model for zero-shot music source separation, transcription and synthesis. In: Proceedings of the 22nd International Society for Music Information Retrieval Conference (ISMIR) (2021)"},{"key":"1249_CR20","first-page":"1241","volume":"2020","author":"H Liu","year":"2020","unstructured":"H. Liu, L. Xie, J. Wu et al., Channel-wise subband input for better voice and accompaniment separation on high resolution music. Interspeech 2020, 1241\u20131245 (2020)","journal-title":"Interspeech"},{"key":"1249_CR21","unstructured":"H. Liu, Q. Kong, J. Liu, Cws-presunet: Music source separation with channel-wise subband phase-aware resunet. In: Proceedings of the 22nd International Society for Music Information Retrieval Conference (ISMIR) (2021a)"},{"key":"1249_CR22","doi-asserted-by":"crossref","unstructured":"Z. Liu, Y. Lin, Y. Cao, et\u00a0al., Swin transformer: Hierarchical vision transformer using shifted windows. In: 2021 IEEE\/CVF International Conference on Computer Vision (ICCV), pp 9992\u201310002 (2021b)","DOI":"10.1109\/ICCV48922.2021.00986"},{"key":"1249_CR23","first-page":"4619","volume":"2019","author":"F Llu\u00eds","year":"2019","unstructured":"F. Llu\u00eds, J. Pons, X. Serra, End-to-end music source separation: Is it possible in the waveform domain? Interspeech 2019, 4619\u20134623 (2019)","journal-title":"Interspeech"},{"key":"1249_CR24","doi-asserted-by":"crossref","unstructured":"W.T. Lu, J.C. Wang, Q. Kong, et\u00a0al., Music source separation with band-split rope transformer. In: ICASSP 2024 - 2024 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP), pp 481\u2013485 (2024)","DOI":"10.1109\/ICASSP48485.2024.10446843"},{"issue":"8","key":"1249_CR25","doi-asserted-by":"publisher","first-page":"1256","DOI":"10.1109\/TASLP.2019.2915167","volume":"27","author":"Y Luo","year":"2019","unstructured":"Y. Luo, N. Mesgarani, Conv-tasnet: Surpassing ideal time-frequency magnitude masking for speech separation. IEEE\/ACM Trans.on Audio, Speech, Language Process. 27(8), 1256\u20131266 (2019)","journal-title":"IEEE\/ACM Trans.on Audio, Speech, Language Process."},{"key":"1249_CR26","doi-asserted-by":"publisher","first-page":"1893","DOI":"10.1109\/TASLP.2023.3271145","volume":"31","author":"Y Luo","year":"2023","unstructured":"Y. Luo, J. Yu, Music source separation with band-split RNN. IEEE\/ACM Trans. Audio, Speech, Language Process. 31, 1893\u20131901 (2023)","journal-title":"IEEE\/ACM Trans. Audio, Speech, Language Process."},{"key":"1249_CR27","doi-asserted-by":"crossref","unstructured":"T. Nakano, K. Yoshii, Y. Wu, et\u00a0al., Joint singing pitch estimation and voice separation based on a neural harmonic structure renderer. In: 2019 IEEE Workshop on Applications of Signal Processing to Audio and Acoustics (WASPAA), pp 160\u2013164 (2019)","DOI":"10.1109\/WASPAA.2019.8937135"},{"key":"1249_CR28","doi-asserted-by":"crossref","unstructured":"A.A. Nugraha, A. Liutkus, E. Vincent, Multichannel music separation with deep neural networks. In: 2016 24th European Signal Processing Conference (EUSIPCO), pp 1748\u20131752 (2016)","DOI":"10.1109\/EUSIPCO.2016.7760548"},{"key":"1249_CR29","unstructured":"A. van\u00a0den Oord, S. Dieleman, H. Zen, et\u00a0al., Wavenet: A generative model for raw audio. In: 9th ISCA Speech Synthesis Workshop (SSW) (2016)"},{"key":"1249_CR30","doi-asserted-by":"crossref","unstructured":"J. Pons, J. Serr\u00e1, S. Pascual, et\u00a0al., Upsampling layers for music source separation. In: 2023 31st European Signal Processing Conference (EUSIPCO), pp 311\u2013315 (2023)","DOI":"10.23919\/EUSIPCO58844.2023.10289768"},{"key":"1249_CR31","doi-asserted-by":"publisher","unstructured":"Z. Rafii, A. Liutkus, F.R. St\u00f6ter, et\u00a0al., MUSDB18: A corpus for music separation. https:\/\/doi.org\/10.5281\/zenodo.1117372 (2017)","DOI":"10.5281\/zenodo.1117372"},{"key":"1249_CR32","first-page":"234","volume":"2015","author":"O Ronneberger","year":"2015","unstructured":"O. Ronneberger, P. Fischer, T. Brox, U-net: Convolutional networks for biomedical image segmentation. Med Image Comput Computer-Assisted Intervention - MICCAI 2015, 234\u2013241 (2015)","journal-title":"Med Image Comput Computer-Assisted Intervention - MICCAI"},{"key":"1249_CR33","doi-asserted-by":"crossref","unstructured":"S. Rouard, F. Massa, A. D\u00e9fossez, Hybrid transformers for music source separation. In: ICASSP 2023 - 2023 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP), pp 1\u20135 (2023)","DOI":"10.1109\/ICASSP49357.2023.10096956"},{"key":"1249_CR34","doi-asserted-by":"crossref","unstructured":"R. Sawata, S. Uhlich, S. Takahashi, et\u00a0al., All for one and one for all: Improving music separation by bridging networks. In: ICASSP 2021 - 2021 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP), pp 51\u201355 (2021)","DOI":"10.1109\/ICASSP39728.2021.9414044"},{"key":"1249_CR35","unstructured":"B. Series, Method for the subjective assessment of intermediate quality level of audio systems. In: Proceedings of the International Telecommunication Union Radiocommunication Assembly, iTU-R BS.1534-3 (2015)"},{"key":"1249_CR36","unstructured":"D. Stoller, S. Ewert, S. Dixon, Wave-u-net: A multi-scale neural network for end-to-end audio source separation. In: Proceedings of the 19th International Society for Music Information Retrieval Conference (ISMIR), pp 334\u2013340 (2018)"},{"issue":"41","key":"1249_CR37","doi-asserted-by":"publisher","first-page":"1667","DOI":"10.21105\/joss.01667","volume":"4","author":"FR St\u00f6ter","year":"2019","unstructured":"F.R. St\u00f6ter, S. Uhlich, A. Liutkus et al., Open-Unmix: A reference implementation for music source separation. J. Open Sour. Softw. 4(41), 1667 (2019)","journal-title":"J. Open Sour. Softw."},{"key":"1249_CR38","doi-asserted-by":"crossref","unstructured":"F.R. St\u00f6ter, A. Liutkus, N. Ito, The 2018 signal separation evaluation campaign. In: International Conference on Latent Variable Analysis and Signal Separation (LVA\/ICA), pp 293\u2013305 (2018)","DOI":"10.1007\/978-3-319-93764-9_28"},{"key":"1249_CR39","doi-asserted-by":"crossref","unstructured":"N. Takahashi, Y. Mitsufuji, Densely connected multidilated convolutional networks for dense prediction tasks. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition (CVPR), pp 993\u20131002 (2021)","DOI":"10.1109\/CVPR46437.2021.00105"},{"key":"1249_CR40","unstructured":"A. Vaswani, N. Shazeer, N. Parmar, et\u00a0al., Attention is all you need. In: Proceedings of the 31st International Conference on Neural Information Processing Systems, pp 6000\u2014-6010 (2017)"},{"issue":"4","key":"1249_CR41","doi-asserted-by":"publisher","first-page":"1462","DOI":"10.1109\/TSA.2005.858005","volume":"14","author":"E Vincent","year":"2006","unstructured":"E. Vincent, R. Gribonval, C. F\u00e9votte, Performance measurement in blind audio source separation. IEEE Trans. Audio Speech Lang. Process. 14(4), 1462\u20131469 (2006)","journal-title":"IEEE Trans. Audio Speech Lang. Process."},{"key":"1249_CR42","unstructured":"J.C. Wang, W.T. Lu, M. Won, Mel-band roformer for music source separation. In: Extended Abstracts for the Late Breaking Demo Session of the 24th Int. Society for Music Information Retrieval Conf (2023)"},{"issue":"3","key":"1249_CR43","doi-asserted-by":"publisher","first-page":"483","DOI":"10.1109\/TASLP.2015.2512042","volume":"24","author":"DS Williamson","year":"2016","unstructured":"D.S. Williamson, Y. Wang, D. Wang, Complex ratio masking for monaural speech separation. IEEE\/ACM Transactions on Audio, Speech, and Language Processing 24(3), 483\u2013492 (2016)","journal-title":"IEEE\/ACM Transactions on Audio, Speech, and Language Processing"},{"key":"1249_CR44","doi-asserted-by":"publisher","unstructured":"Q. Wu, H. Deng, K. Hu et al., Music source separation via hybrid waveform and spectrogram based generative adversarial network. Multimedia Tools and Applications (2024). https:\/\/doi.org\/10.1007\/s11042-024-20038-9","DOI":"10.1007\/s11042-024-20038-9"},{"issue":"4","key":"1249_CR45","doi-asserted-by":"publisher","first-page":"816","DOI":"10.1109\/TASLP.2014.2305252","volume":"22","author":"JR Zapata","year":"2014","unstructured":"J.R. Zapata, M.E.P. Davies, E. Gomez, Multi-feature beat tracking. IEEE\/ACM Transactions on Audio, Speech, and Language Processing 22(4), 816\u2013825 (2014)","journal-title":"IEEE\/ACM Transactions on Audio, Speech, and Language Processing"}],"updated-by":[{"DOI":"10.1186\/s13634-025-01258-z","type":"correction","label":"Correction","source":"publisher","updated":{"date-parts":[[2025,10,6]],"date-time":"2025-10-06T00:00:00Z","timestamp":1759708800000}}],"container-title":["EURASIP Journal on Advances in Signal Processing"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/link.springer.com\/content\/pdf\/10.1186\/s13634-025-01249-0.pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/link.springer.com\/article\/10.1186\/s13634-025-01249-0\/fulltext.html","content-type":"text\/html","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/link.springer.com\/content\/pdf\/10.1186\/s13634-025-01249-0.pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,10,7]],"date-time":"2025-10-07T05:37:30Z","timestamp":1759815450000},"score":1,"resource":{"primary":{"URL":"https:\/\/asp-eurasipjournals.springeropen.com\/articles\/10.1186\/s13634-025-01249-0"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2025,9,2]]},"references-count":45,"journal-issue":{"issue":"1","published-online":{"date-parts":[[2025,12]]}},"alternative-id":["1249"],"URL":"https:\/\/doi.org\/10.1186\/s13634-025-01249-0","relation":{},"ISSN":["1687-6180"],"issn-type":[{"value":"1687-6180","type":"electronic"}],"subject":[],"published":{"date-parts":[[2025,9,2]]},"assertion":[{"value":"20 January 2025","order":1,"name":"received","label":"Received","group":{"name":"ArticleHistory","label":"Article History"}},{"value":"25 August 2025","order":2,"name":"accepted","label":"Accepted","group":{"name":"ArticleHistory","label":"Article History"}},{"value":"2 September 2025","order":3,"name":"first_online","label":"First Online","group":{"name":"ArticleHistory","label":"Article History"}},{"value":"6 October 2025","order":4,"name":"change_date","label":"Change Date","group":{"name":"ArticleHistory","label":"Article History"}},{"value":"Correction","order":5,"name":"change_type","label":"Change Type","group":{"name":"ArticleHistory","label":"Article History"}},{"value":"A Correction to this paper has been published:","order":6,"name":"change_details","label":"Change Details","group":{"name":"ArticleHistory","label":"Article History"}},{"value":"https:\/\/doi.org\/10.1186\/s13634-025-01258-z","URL":"https:\/\/doi.org\/10.1186\/s13634-025-01258-z","order":7,"name":"change_details","label":"Change Details","group":{"name":"ArticleHistory","label":"Article History"}},{"order":1,"name":"Ethics","group":{"name":"EthicsHeading","label":"Declarations"}},{"value":"The authors declare no conflict of interest.","order":2,"name":"Ethics","group":{"name":"EthicsHeading","label":"Conflict of interest"}}],"article-number":"39"}}