{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,9,30]],"date-time":"2026-09-30T19:02:59Z","timestamp":1790794979991,"version":"4.1.0"},"reference-count":27,"publisher":"Springer Science and Business Media LLC","issue":"12","license":[{"start":{"date-parts":[[2026,9,1]],"date-time":"2026-09-01T00:00:00Z","timestamp":1788220800000},"content-version":"tdm","delay-in-days":0,"URL":"https:\/\/www.springernature.com\/gp\/researchers\/text-and-data-mining"},{"start":{"date-parts":[[2026,9,1]],"date-time":"2026-09-01T00:00:00Z","timestamp":1788220800000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/www.springernature.com\/gp\/researchers\/text-and-data-mining"}],"content-domain":{"domain":["link.springer.com"],"crossmark-restriction":false},"short-container-title":["SIViP"],"published-print":{"date-parts":[[2026,9]]},"DOI":"10.1007\/s11760-026-05700-z","type":"journal-article","created":{"date-parts":[[2026,9,12]],"date-time":"2026-09-12T08:03:44Z","timestamp":1789200224000},"update-policy":"https:\/\/doi.org\/10.1007\/springer_crossmark_policy","source":"Crossref","is-referenced-by-count":0,"title":["Self-supervised audio representation learning model based on time-frequency decoupling and masked reconstruction"],"prefix":"10.1007","volume":"20","author":[{"given":"Jie","family":"Xu","sequence":"first","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Yuhao","family":"Dai","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Zhifeng","family":"Wang","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"297","published-online":{"date-parts":[[2026,9,12]]},"reference":[{"key":"5700_CR1","doi-asserted-by":"publisher","first-page":"2880","DOI":"10.1109\/TASLP.2020.3030497","volume":"28","author":"Q Kong","year":"2020","unstructured":"Kong, Q., Cao, Y., Iqbal, T., Wang, Y., Wang, W., Plumbley, M.D.: PANNs: large-scale pretrained audio neural networks for audio pattern recognition. IEEE\/ACM Trans. Audio Speech Lang. 28, 2880\u20132894 (2020). https:\/\/doi.org\/10.1109\/TASLP.2020.3030497","journal-title":"IEEE\/ACM Trans. Audio Speech Lang."},{"key":"5700_CR2","first-page":"5998","volume":"30","author":"A Vaswani","year":"2017","unstructured":"Vaswani, A., Shazeer, N., Parmar, N., Uszkoreit, J., Jones, L., Gomez, A.N., Kaiser, L., Polosukhin, I.: Attention is all you need. Adv. Neural. Inf. Process. Syst. 30, 5998\u20136008 (2017)","journal-title":"Adv. Neural. Inf. Process. Syst."},{"key":"5700_CR3","unstructured":"Dosovitskiy, A., Beyer, L., Kolesnikov, A., Weissenborn, D., Zhai, X., Unterthiner, T., Dehghani, M., Minderer, M., Heigold, G., Gelly, S., Uszkoreit, J., Houlsby, N.: An image is worth 16$$\\times $$16 words: transformers for image recognition at scale. In: International Conference on Learning Representations (2021)"},{"key":"5700_CR4","doi-asserted-by":"publisher","unstructured":"Gong, Y., Chung, Y.-A., Glass, J.: AST: audio spectrogram transformer. In: Interspeech 2021, pp. 571\u2013575 (2021). https:\/\/doi.org\/10.21437\/Interspeech.2021-698","DOI":"10.21437\/Interspeech.2021-698"},{"issue":"16","key":"5700_CR5","doi-asserted-by":"publisher","first-page":"17647","DOI":"10.1609\/aaai.v38i16.29716","volume":"38","author":"T Alex","year":"2024","unstructured":"Alex, T., Ahmed, S., Mustafa, A., Awais, M., Jackson, P.J.B.: DTF-AT: decoupled time-frequency audio transformer for event classification. Proc. AAAI Conf. Artif. Intell. 38(16), 17647\u201317655 (2024). https:\/\/doi.org\/10.1609\/aaai.v38i16.29716","journal-title":"Proc. AAAI Conf. Artif. Intell."},{"key":"5700_CR6","doi-asserted-by":"publisher","unstructured":"Feng, J., Erol, M.H., Chung, J.S., Senocak, A.: FlexiAST: flexibility is what AST needs. arXiv:2307.09286 (2023). https:\/\/doi.org\/10.48550\/arXiv.2307.09286","DOI":"10.48550\/arXiv.2307.09286"},{"key":"5700_CR7","doi-asserted-by":"publisher","unstructured":"Feng, J., Erol, M.H., Chung, J.S., Senocak, A.: ElasticAST: an audio spectrogram transformer for all length and resolutions. In: Interspeech 2024, pp. 4743\u20134747 (2024). https:\/\/doi.org\/10.21437\/Interspeech.2024-1890","DOI":"10.21437\/Interspeech.2024-1890"},{"key":"5700_CR8","doi-asserted-by":"crossref","unstructured":"He, K., Chen, X., Xie, S., Li, Y., Doll\u00e1r, P., Girshick, R.: Masked autoencoders are scalable vision learners. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition, pp. 16000\u201316009 (2022)","DOI":"10.1109\/CVPR52688.2022.01553"},{"key":"5700_CR9","doi-asserted-by":"publisher","first-page":"28708","DOI":"10.52202\/068431-2081","volume":"35","author":"P-Y Huang","year":"2022","unstructured":"Huang, P.-Y., Xu, H., Li, J., Baevski, A., Auli, M., Galuba, W., Metze, F., Feichtenhofer, C.: Masked autoencoders that listen. Adv. Neural. Inf. Process. Syst. 35, 28708\u201328720 (2022)","journal-title":"Adv. Neural. Inf. Process. Syst."},{"key":"5700_CR10","unstructured":"Yadav, S., Theodoridis, S., Hansen, L.K., Tan, Z.-H.: Masked autoencoders with multi-window localglobal attention are better audio learners. In: International Conference on Learning Representations (2024)"},{"key":"5700_CR11","doi-asserted-by":"publisher","unstructured":"Chong, D., Wang, H., Zhou, P., Zeng, Q.: Masked spectrogram prediction for self-supervised audio pre-training. arXiv:2204.12768 (2022). https:\/\/doi.org\/10.48550\/arXiv.2204.12768","DOI":"10.48550\/arXiv.2204.12768"},{"key":"5700_CR12","first-page":"21271","volume":"33","author":"J-B Grill","year":"2020","unstructured":"Grill, J.-B., Strub, F., Altch\u00e9, F., Tallec, C., Richemond, P.H., Buchatskaya, E., Doersch, C., Pires, B.A., Guo, Z.D., Azar, M.G., Piot, B., Kavukcuoglu, K., Munos, R., Valko, M.: Bootstrap your own latent: a new approach to self-supervised learning. Adv. Neural. Inf. Process. Syst. 33, 21271\u201321284 (2020)","journal-title":"Adv. Neural. Inf. Process. Syst."},{"key":"5700_CR13","doi-asserted-by":"publisher","unstructured":"Li, X., Li, X.: ATST: audio representation learning with teacher-student transformer. In: Interspeech 2022, pp. 4172\u20134176 (2022). https:\/\/doi.org\/10.21437\/Interspeech.2022-10126","DOI":"10.21437\/Interspeech.2022-10126"},{"key":"5700_CR14","doi-asserted-by":"publisher","first-page":"1827","DOI":"10.1109\/TASLP.2024.3352248","volume":"32","author":"X Li","year":"2024","unstructured":"Li, X., Shao, N., Li, X.: Self-supervised audio teacher-student transformer for both clip-level and frame-level tasks. IEEE\/ACM Trans. Audio Speech Lang. Process. 32, 1827\u20131841 (2024). https:\/\/doi.org\/10.1109\/TASLP.2024.3352248","journal-title":"IEEE\/ACM Trans. Audio Speech Lang. Process."},{"key":"5700_CR15","doi-asserted-by":"publisher","unstructured":"Gong, Y., Lai, C.-I., Chung, Y.-A., Glass, J.: SSAST: self-supervised audio spectrogram transformer. Proc. AAAI Conf. Artif. Intell. 36(10), 10699\u201310709 (2022). https:\/\/doi.org\/10.1609\/aaai.v36i10.21315","DOI":"10.1609\/aaai.v36i10.21315"},{"key":"5700_CR16","doi-asserted-by":"publisher","unstructured":"Shams, S., Dindar, S.S., Jiang, X., Mesgarani, N.: SSAMBA: Self-supervised audio representation learning with mamba state space model. In: 2024 IEEE Spoken Language Technology Workshop (SLT), pp. 1053\u20131059 (2024). https:\/\/doi.org\/10.1109\/SLT61566.2024.10832304. arXiv:2405.11831","DOI":"10.1109\/SLT61566.2024.10832304"},{"key":"5700_CR17","doi-asserted-by":"crossref","unstructured":"Araujo, E., Rouditchenko, A., Gong, Y., Bhati, S., Thomas, S., Kingsbury, B., Karlinsky, L., Feris, R., Glass, J.R., Kuehne, H.: CAV-MAE Sync: improving contrastive audio-visual mask autoencoders via fine-grained alignment. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition, pp. 18794\u201318803 (2025)","DOI":"10.1109\/CVPR52734.2025.01751"},{"key":"5700_CR18","unstructured":"Chen, S., Wu, Y., Wang, C., Liu, S., Tompkins, D., Chen, Z., Che, W., Yu, X., Wei, F.: BEATs: audio pre-training with acoustic tokenizers. In: Proceedings of the 40th International Conference on Machine Learning. Proceedings of Machine Learning Research, vol. 202, pp. 5178\u20135193. PMLR, Honolulu, HI, USA (2023)"},{"key":"5700_CR19","doi-asserted-by":"publisher","unstructured":"Chen, W., Liang, Y., Ma, Z., Zheng, Z., Chen, X.: EAT: Self-supervised pre-training with efficient audio transformer. In: Proceedings of the Thirty-Third International Joint Conference on Artificial Intelligence, pp. 3807\u20133815 (2024). https:\/\/doi.org\/10.24963\/ijcai.2024\/421","DOI":"10.24963\/ijcai.2024\/421"},{"key":"5700_CR20","doi-asserted-by":"crossref","unstructured":"Huang, G., Sun, Y., Liu, Z., Sedra, D., Weinberger, K.Q.: Deep networks with stochastic depth. In: European Conference on Computer Vision, pp. 646\u2013661. Springer, Cham (2016)","DOI":"10.1007\/978-3-319-46493-0_39"},{"key":"5700_CR21","unstructured":"Zhang, H., Cisse, M., Dauphin, Y.N., Lopez-Paz, D.: Mixup: beyond empirical risk minimization. In: International Conference on Learning Representations (2018)"},{"key":"5700_CR22","doi-asserted-by":"publisher","unstructured":"Gemmeke, J.F., Ellis, D.P.W., Freedman, D., Jansen, A., Lawrence, W., Moore, R.C., Plakal, M., Ritter, M.: Audio set: an ontology and human-labeled dataset for audio events. In: 2017 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP), pp. 776\u2013780. IEEE, New Orleans, LA, USA (2017). https:\/\/doi.org\/10.1109\/ICASSP.2017.7952261","DOI":"10.1109\/ICASSP.2017.7952261"},{"key":"5700_CR23","doi-asserted-by":"publisher","unstructured":"Salamon, J., Jacoby, C., Bello, J.P.: A dataset and taxonomy for urban sound research. In: Proceedings of the 22nd ACM International Conference on Multimedia, pp. 1041\u20131044. ACM, Orlando, Florida, USA (2014). https:\/\/doi.org\/10.1145\/2647868.2655045","DOI":"10.1145\/2647868.2655045"},{"key":"5700_CR24","doi-asserted-by":"publisher","unstructured":"Warden, P.: Speech commands: a dataset for limited-vocabulary speech recognition (2018). https:\/\/doi.org\/10.48550\/arXiv.1804.03209","DOI":"10.48550\/arXiv.1804.03209"},{"key":"5700_CR25","doi-asserted-by":"publisher","unstructured":"Nagrani, A., Chung, J.S., Zisserman, A.: VoxCeleb: a large-scale speaker identification dataset. In: Interspeech 2017, pp. 2616\u20132620 (2017). https:\/\/doi.org\/10.21437\/Interspeech.2017-950. arXiv:1706.08612","DOI":"10.21437\/Interspeech.2017-950"},{"key":"5700_CR26","unstructured":"Engel, J., Resnick, C., Roberts, A., Dieleman, S., Eck, D., Simonyan, K., Norouzi, M.: Neural audio synthesis of musical notes with WaveNet autoencoders. In: Proceedings of the 34th International Conference on Machine Learning. Proceedings of Machine Learning Research, vol. 70, pp. 1068\u20131077. PMLR, Sydney, Australia (2017)"},{"key":"5700_CR27","unstructured":"Loshchilov, I., Hutter, F.: Decoupled weight decay regularization. In: International Conference on Learning Representations (2019)"}],"container-title":["Signal, Image and Video Processing"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/link.springer.com\/content\/pdf\/10.1007\/s11760-026-05700-z.pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/link.springer.com\/article\/10.1007\/s11760-026-05700-z","content-type":"text\/html","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/link.springer.com\/content\/pdf\/10.1007\/s11760-026-05700-z.pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2026,9,30]],"date-time":"2026-09-30T18:52:07Z","timestamp":1790794327000},"score":1,"resource":{"primary":{"URL":"https:\/\/link.springer.com\/10.1007\/s11760-026-05700-z"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2026,9]]},"references-count":27,"journal-issue":{"issue":"12","published-print":{"date-parts":[[2026,9]]}},"alternative-id":["5700"],"URL":"https:\/\/doi.org\/10.1007\/s11760-026-05700-z","relation":{"has-preprint":[{"id-type":"doi","id":"10.21203\/rs.3.rs-8361849\/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":[[2026,9]]},"assertion":[{"value":"15 December 2025","order":1,"name":"received","label":"Received","group":{"name":"ArticleHistory","label":"Article History"}},{"value":"27 August 2026","order":2,"name":"revised","label":"Revised","group":{"name":"ArticleHistory","label":"Article History"}},{"value":"31 August 2026","order":3,"name":"accepted","label":"Accepted","group":{"name":"ArticleHistory","label":"Article History"}},{"value":"12 September 2026","order":4,"name":"first_online","label":"First Online","group":{"name":"ArticleHistory","label":"Article History"}},{"value":"The authors declare no conflict of interest.","order":1,"name":"Ethics","label":"Conflict of interest","group":{"name":"EthicsHeading","label":"Declarations"}},{"value":"This declaration is not applicable.","order":2,"name":"Ethics","label":"Ethical approval","group":{"name":"EthicsHeading","label":"Declarations"}},{"value":"This declaration is not applicable.","order":3,"name":"Ethics","label":"Informed consent","group":{"name":"EthicsHeading","label":"Declarations"}}],"article-number":"636"}}