{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,9,17]],"date-time":"2026-09-17T19:47:34Z","timestamp":1789674454420,"version":"4.0.1"},"reference-count":55,"publisher":"Springer Science and Business Media LLC","issue":"3","license":[{"start":{"date-parts":[[2026,3,10]],"date-time":"2026-03-10T00:00:00Z","timestamp":1773100800000},"content-version":"tdm","delay-in-days":0,"URL":"https:\/\/www.springernature.com\/gp\/researchers\/text-and-data-mining"},{"start":{"date-parts":[[2026,3,10]],"date-time":"2026-03-10T00:00:00Z","timestamp":1773100800000},"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":["Multimedia Systems"],"published-print":{"date-parts":[[2026,6]]},"DOI":"10.1007\/s00530-026-02252-7","type":"journal-article","created":{"date-parts":[[2026,3,10]],"date-time":"2026-03-10T13:59:36Z","timestamp":1773151176000},"update-policy":"https:\/\/doi.org\/10.1007\/springer_crossmark_policy","source":"Crossref","is-referenced-by-count":4,"title":["Salient structural modeling in multimodal music emotion recognition via graph neural networks"],"prefix":"10.1007","volume":"32","author":[{"given":"Yan","family":"Wu","sequence":"first","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Wei","family":"Hu","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"297","published-online":{"date-parts":[[2026,3,10]]},"reference":[{"key":"2252_CR1","doi-asserted-by":"publisher","unstructured":"J. Kang and D. Herremans, Towards unified music emotion recognition across dimensional and categorical models, arXiv:2502.03979, 2025. https:\/\/doi.org\/10.48550\/arXiv.2502.03979","DOI":"10.48550\/arXiv.2502.03979"},{"key":"2252_CR2","doi-asserted-by":"publisher","unstructured":"K. N. Watcharasupat, Y. Ding, T. A. Ma, P. Seshadri, and A. Lerch, Uncertainty estimation in the real world: A study on music emotion recognition, in Proc. European Conf. Information Retrieval (ECIR), 2025, pp. 218\u2013232. https:\/\/doi.org\/10.1007\/978-3-031-88711-6_14","DOI":"10.1007\/978-3-031-88711-6_14"},{"key":"2252_CR3","doi-asserted-by":"publisher","unstructured":"H. Redinho, P. L. Louro, A. C. Santos, R. Malheiro, et al., Exploiting automatic source separation and music transcription for music emotion recognition, in Pattern Recognition. ICPR 2024 Int. Workshops and Challenges, Cham, Switzerland: Springer, 2025, pp. 67\u201382. https:\/\/doi.org\/10.1007\/978-3-031-87657-8_5","DOI":"10.1007\/978-3-031-87657-8_5"},{"issue":"1","key":"2252_CR4","doi-asserted-by":"publisher","first-page":"020054","DOI":"10.1063\/5.0262831","volume":"3270","author":"GJ Royal","year":"2025","unstructured":"Royal, G.J., Sriramya, P.: Intervention of novel speech emotion recognition to improve accuracy using SVM over convolutional neural network. AIP Conf. Proc. 3270(1), 020054 (2025)","journal-title":"AIP Conf. Proc."},{"key":"2252_CR5","doi-asserted-by":"publisher","first-page":"688","DOI":"10.1109\/ACCESS.2014.6843353","volume":"2","author":"K Markov","year":"2014","unstructured":"Markov, K., Matsui, T.: Music genre and emotion recognition using Gaussian processes. IEEE Access 2, 688\u2013697 (2014). https:\/\/doi.org\/10.1109\/ACCESS.2014.6843353","journal-title":"IEEE Access"},{"issue":"3","key":"2252_CR6","doi-asserted-by":"publisher","first-page":"032102","DOI":"10.1088\/2631-8695\/ad5e7b","volume":"6","author":"BA Demiss","year":"2024","unstructured":"Demiss, B.A., Elsaigh, W.A.: Application of novel hybrid deep learning architectures combining convolutional neural networks (CNN) and recurrent neural networks (RNN): construction duration estimates prediction considering preconstruction uncertainties. Eng. Res. Express 6(3), 032102 (2024). https:\/\/doi.org\/10.1088\/2631-8695\/ad5e7b","journal-title":"Eng. Res. Express"},{"issue":"9","key":"2252_CR7","doi-asserted-by":"publisher","DOI":"10.3390\/info15090517","volume":"15","author":"ID Mienye","year":"2024","unstructured":"Mienye, I.D., Swart, T.G., Obaido, G.: Recurrent neural networks: a comprehensive review of architectures, variants, and applications. Information 15(9), 517 (2024). https:\/\/doi.org\/10.3390\/info15090517","journal-title":"Information"},{"issue":"9","key":"2252_CR8","doi-asserted-by":"publisher","DOI":"10.3390\/a17090398","volume":"17","author":"Y He","year":"2024","unstructured":"He, Y., Huang, P., Hong, W., et al.: In-depth insights into the application of recurrent neural networks (RNNs) in traffic prediction: a comprehensive review. Algorithms 17(9), 398 (2024). https:\/\/doi.org\/10.3390\/a17090398","journal-title":"Algorithms"},{"key":"2252_CR9","doi-asserted-by":"publisher","DOI":"10.1016\/j.neucom.2023.126649","volume":"556","author":"J Xie","year":"2023","unstructured":"Xie, J., Wang, J., Wang, Q., et al.: A multimodal fusion emotion recognition method based on multitask learning and attention mechanism. Neurocomputing 556, 126649 (2023). https:\/\/doi.org\/10.1016\/j.neucom.2023.126649","journal-title":"Neurocomputing"},{"key":"2252_CR10","doi-asserted-by":"publisher","unstructured":"D. Greco, P. Barra, L. D\u2019Errico, et al., Multimodal interfaces for emotion recognition: Models, challenges and opportunities, in Proc. Int. Conf. Human-Computer Interaction, Cham, Switzerland: Springer, 2024, pp. 152\u2013162. https:\/\/doi.org\/10.1007\/978-3-031-60428-7_11","DOI":"10.1007\/978-3-031-60428-7_11"},{"key":"2252_CR11","unstructured":"E. Boitel, Deep learning framework for multimodal emotion recognition, Ph.D. dissertation, Univ. of Portsmouth, Portsmouth, U.K., 2024."},{"key":"2252_CR12","doi-asserted-by":"publisher","DOI":"10.1017\/ATSIP.2018.6","volume":"7","author":"KH Tan","year":"2018","unstructured":"Tan, K.H., Lim, B.P.: The artificial intelligence renaissance: deep learning and the road to human-level machine intelligence. APSIPA Trans. Signal Inf. Process. 7, e6 (2018). https:\/\/doi.org\/10.1017\/ATSIP.2018.6","journal-title":"APSIPA Trans. Signal Inf. Process."},{"key":"2252_CR13","unstructured":"R. Chen, Musical instrument recognition using convolutional neural networks and spectrograms, M.S. thesis, Auckland Univ. of Technology, Auckland, New Zealand, 2024."},{"issue":"6","key":"2252_CR14","doi-asserted-by":"publisher","first-page":"1365","DOI":"10.1007\/s11760-013-0579-2","volume":"9","author":"M Naji","year":"2015","unstructured":"Naji, M., Firoozabadi, M., Azadfallah, P.: Emotion classification during music listening from forehead biosignals. Signal Image Video Process. 9(6), 1365\u20131375 (2015). https:\/\/doi.org\/10.1007\/s11760-013-0579-2","journal-title":"Signal Image Video Process."},{"key":"2252_CR15","unstructured":"E. Koh, Emotion based music and audio understanding, M.S. thesis, Univ. of California, San Diego, CA, USA, 2022."},{"key":"2252_CR16","doi-asserted-by":"publisher","DOI":"10.1016\/j.asoc.2024.112034","volume":"164","author":"X Han","year":"2024","unstructured":"Han, X., Chen, F., Ban, J.: A GAI-based multi-scale convolution and attention mechanism model for music emotion recognition and recommendation from physiological data. Appl. Soft Comput. 164, 112034 (2024). https:\/\/doi.org\/10.1016\/j.asoc.2024.112034","journal-title":"Appl. Soft Comput."},{"key":"2252_CR17","doi-asserted-by":"publisher","DOI":"10.1016\/j.eswa.2023.121692","volume":"237","author":"S Zhang","year":"2024","unstructured":"Zhang, S., Yang, Y., Chen, C., et al.: Deep learning-based multimodal emotion recognition from audio, visual, and text modalities: a systematic review of recent advancements and future prospects. Expert Syst. Appl. 237, 121692 (2024). https:\/\/doi.org\/10.1016\/j.eswa.2023.121692","journal-title":"Expert Syst. Appl."},{"issue":"3","key":"2252_CR18","doi-asserted-by":"publisher","DOI":"10.3390\/s25030666","volume":"25","author":"S Zhang","year":"2025","unstructured":"Zhang, S., Liu, Y., Zhou, M.: Graph neural network and LSTM integration for enhanced multi-label style classification of piano sonatas. Sensors 25(3), 666 (2025). https:\/\/doi.org\/10.3390\/s25030666","journal-title":"Sensors"},{"key":"2252_CR19","unstructured":"G. Balazs, Machine learning for grid-based sensor fusion in automotive applications, Ph.D. dissertation, Technische Universit\u00e4t M\u00fcnchen, Munich, Germany, 2022."},{"key":"2252_CR20","unstructured":"E. A. A. Abdrabuh, AI-synthesized speech: Generation and detection, M.S. thesis, State Univ. of New York at Albany, Albany, NY, USA, 2022."},{"key":"2252_CR21","doi-asserted-by":"publisher","unstructured":"F. Huang, X. Li, C. Yuan, et al., Attention-emotion-enhanced convolutional LSTM for sentiment analysis, IEEE Trans. Neural Netw. Learn. Syst., vol. 33, no. 9, pp. 4332\u20134345, Sep. 2022. https:\/\/doi.org\/10.1109\/TNNLS.2021.3056148","DOI":"10.1109\/TNNLS.2021.3056148"},{"issue":"50","key":"2252_CR22","doi-asserted-by":"publisher","DOI":"10.21105\/joss.02154","volume":"5","author":"R Hennequin","year":"2020","unstructured":"Hennequin, R., Khlif, A., Voituret, F., et al.: Spleeter: a fast and efficient music source separation tool with pre-trained models. J. Open Source Softw. 5(50), 2154 (2020). https:\/\/doi.org\/10.21105\/joss.02154","journal-title":"J. Open Source Softw."},{"key":"2252_CR23","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., et al.: Panns: large-scale pretrained audio neural networks for audio pattern recognition. IEEE\/ACM Trans. Audio Speech Lang. Process. 28, 2880\u20132894 (2020). https:\/\/doi.org\/10.1109\/TASLP.2020.3030497","journal-title":"IEEE\/ACM Trans. Audio Speech Lang. Process."},{"key":"2252_CR24","doi-asserted-by":"publisher","first-page":"1196","DOI":"10.1016\/j.procs.2023.01.100","volume":"218","author":"VR Revathy","year":"2023","unstructured":"Revathy, V.R., Pillai, A.S., Daneshfar, F.: LyEmoBERT: classification of lyrics\u2019 emotion and recommendation using a pre-trained model. Procedia Comput. Sci. 218, 1196\u20131208 (2023). https:\/\/doi.org\/10.1016\/j.procs.2023.01.100","journal-title":"Procedia Comput. Sci."},{"key":"2252_CR25","doi-asserted-by":"publisher","unstructured":"E. \u00c7ano and M. Morisio, MoodyLyrics: A sentiment annotated lyrics dataset, in Proc. Int. Conf. Intelligent Systems, Metaheuristics & Swarm Intelligence, 2017, pp. 118\u2013124. https:\/\/doi.org\/10.1145\/3059336.3059348","DOI":"10.1145\/3059336.3059348"},{"key":"2252_CR26","doi-asserted-by":"publisher","unstructured":"F. Eyben, M. W\u00f6llmer, and B. Schuller, OpenSMILE: The Munich versatile and fast open-source audio feature extractor, in Proc. 18th ACM Int. Conf. Multimedia, 2010, pp. 1459\u20131462. https:\/\/doi.org\/10.1145\/1873951.1874246","DOI":"10.1145\/1873951.1874246"},{"key":"2252_CR27","doi-asserted-by":"publisher","unstructured":"F. Eyben, K. R. Scherer, B. W. Schuller, et al., The Geneva minimalistic acoustic parameter set (GeMAPS) for voice research and affective computing, IEEE Trans. Affect. Comput., vol. 7, no. 2, pp. 190\u2013202, Apr.-Jun. 2016. https:\/\/doi.org\/10.1109\/TAFFC.2015.2465937","DOI":"10.1109\/TAFFC.2015.2465937"},{"key":"2252_CR28","doi-asserted-by":"publisher","unstructured":"A. Avila and C. Pinz\u00f3n, Comparative analysis of VGGish and YAMNet models for welding defect detection, in Proc. Int. Scientific-Technical Conf. MANUFACTURING, Cham, Switzerland: Springer, 2024, pp. 184\u2013199. https:\/\/doi.org\/10.1007\/978-3-031-50339-9_15","DOI":"10.1007\/978-3-031-50339-9_15"},{"key":"2252_CR29","doi-asserted-by":"publisher","unstructured":"R. K. Kaliyar, A multi-layer bidirectional transformer encoder for pre-trained word embedding: A survey of BERT, in Proc. 10th Int. Conf. Cloud Computing, Data Science & Engineering (Confluence), 2020, pp. 336\u2013340. https:\/\/doi.org\/10.1109\/Confluence47617.2020.9057808","DOI":"10.1109\/Confluence47617.2020.9057808"},{"key":"2252_CR30","doi-asserted-by":"publisher","unstructured":"L. Jiang, X. Li, L. Wu, et al., \"Bearing fault diagnosis method based on a multi-head graph attention network,\" Meas. Sci. Technol., vol. 33, no. 7, p. 075012, 2022. [Online]. Available: https:\/\/doi.org\/10.1088\/1361-6501\/ac5e7b","DOI":"10.1088\/1361-6501\/ac5e7b"},{"key":"2252_CR31","doi-asserted-by":"publisher","unstructured":"K. Zhang, H. Zhang, S. Li, et al., The PMEmo dataset for music emotion recognition, in Proc. 2018 ACM Int. Conf. Multimedia Retrieval, 2018, pp. 135\u2013142. https:\/\/doi.org\/10.1145\/3206025.3206037","DOI":"10.1145\/3206025.3206037"},{"issue":"3","key":"2252_CR32","doi-asserted-by":"publisher","DOI":"10.1371\/journal.pone.0173392","volume":"12","author":"A Aljanaki","year":"2017","unstructured":"Aljanaki, A., Yang, Y.H., Soleymani, M.: Developing a benchmark for emotional analysis of music. PLoS ONE 12(3), e0173392 (2017). https:\/\/doi.org\/10.1371\/journal.pone.0173392","journal-title":"PLoS ONE"},{"key":"2252_CR33","doi-asserted-by":"publisher","unstructured":"B. McFee, C. Raffel, D. Liang, et al., librosa: Audio and music signal analysis in Python, in Proc. 14th Python in Science Conf., 2015, pp. 18\u201324. https:\/\/doi.org\/10.25080\/Majora-7b98e3ed-003","DOI":"10.25080\/Majora-7b98e3ed-003"},{"issue":"9","key":"2252_CR34","doi-asserted-by":"publisher","first-page":"2231","DOI":"10.1016\/j.patcog.2010.09.022","volume":"44","author":"YS Jeong","year":"2011","unstructured":"Jeong, Y.S., Jeong, M.K., Omitaomu, O.A.: Weighted dynamic time warping for time series classification. Pattern Recognit. 44(9), 2231\u20132240 (2011). https:\/\/doi.org\/10.1016\/j.patcog.2010.09.022","journal-title":"Pattern Recognit."},{"key":"2252_CR35","doi-asserted-by":"publisher","unstructured":"S. Garcia, E. Martinez, J. Cuadrado, et al., VerbaNexAI Lab at SemEval-2024 Task 10: Emotion recognition and reasoning in mixed-coded conversations based on an NRC VAD approach, in Proc. 18th Int. Workshop Semantic Evaluation (SemEval-2024), 2024, pp. 1332\u20131338. https:\/\/doi.org\/10.18653\/v1\/2024.semeval-1.192","DOI":"10.18653\/v1\/2024.semeval-1.192"},{"key":"2252_CR36","doi-asserted-by":"publisher","unstructured":"J. X. Morris, E. Lifland, J. Y. Yoo, et al., TextAttack: A framework for adversarial attacks, data augmentation, and adversarial training in NLP, arXiv:2005.05909, 2020. https:\/\/doi.org\/10.48550\/arXiv.2005.05909","DOI":"10.48550\/arXiv.2005.05909"},{"key":"2252_CR37","doi-asserted-by":"publisher","unstructured":"J. Wang, A. Sharifi, T. R. Gadekallu, et al., MMD-MII model: A multilayered analysis and multimodal integration interaction approach revolutionizing music emotion classification, Int. J. Comput. Intell. Syst., vol. 17, no. 1, p. 99, 2024. https:\/\/doi.org\/10.1007\/s44196-024-00507-0","DOI":"10.1007\/s44196-024-00507-0"},{"key":"2252_CR38","doi-asserted-by":"publisher","unstructured":"Y. Zhang, A. Jia, B. Wang, et al., M3GAT: A multi-modal, multi-task interactive graph attention network for conversational sentiment analysis and emotion recognition, ACM Trans. Inf. Syst., vol. 42, no. 1, pp. 1\u201332, 2023. https:\/\/doi.org\/10.1145\/3569942","DOI":"10.1145\/3569942"},{"key":"2252_CR39","doi-asserted-by":"publisher","unstructured":"J. Zhao, G. Ru, Y. Yu, et al., Multimodal music emotion recognition with hierarchical cross-modal attention network, in Proc. 2022 IEEE Int. Conf. Multimedia and Expo (ICME), 2022, pp. 1\u20136. https:\/\/doi.org\/10.1109\/ICME52920.2022.9859960","DOI":"10.1109\/ICME52920.2022.9859960"},{"key":"2252_CR40","doi-asserted-by":"publisher","unstructured":"J. Qiu, C. L. Chen, and T. Zhang, A novel multi-task learning method for symbolic music emotion recognition, arXiv:2201.05782, 2022. https:\/\/doi.org\/10.48550\/arXiv.2201.05782","DOI":"10.48550\/arXiv.2201.05782"},{"issue":"13","key":"2252_CR41","doi-asserted-by":"publisher","DOI":"10.3390\/app14135761","volume":"14","author":"LJM Raboy","year":"2024","unstructured":"Raboy, L.J.M., Taparugssanagorn, A.: Verse1-chorus-verse2 structure: a stacked ensemble approach for enhanced music emotion recognition. Appl. Sci. 14(13), 5761 (2024). https:\/\/doi.org\/10.3390\/app14135761","journal-title":"Appl. Sci."},{"key":"2252_CR42","doi-asserted-by":"publisher","DOI":"10.1016\/j.patcog.2023.110200","volume":"148","author":"PC Chang","year":"2024","unstructured":"Chang, P.C., Chen, Y.S., Lee, C.H.: IIOF: intra- and inter-feature orthogonal fusion of local and global features for music emotion recognition. Pattern Recogn. 148, 110200 (2024). https:\/\/doi.org\/10.1016\/j.patcog.2023.110200","journal-title":"Pattern Recogn."},{"key":"2252_CR43","doi-asserted-by":"publisher","unstructured":"Z. Ying, D. Bourgeois, J. You, et al., \"GNNExplainer: Generating explanations for graph neural networks,\" in Advances in Neural Information Processing Systems, vol. 32, 2019. [Online]. Available: https:\/\/doi.org\/10.48550\/arXiv.1903.03894","DOI":"10.48550\/arXiv.1903.03894"},{"key":"2252_CR44","doi-asserted-by":"publisher","DOI":"10.1016\/j.patcog.2024.111340","volume":"161","author":"M Li","year":"2025","unstructured":"Li, M., Shi, J., Bai, L., et al.: FrameERC: framelet transform based multimodal graph neural networks for emotion recognition in conversation. Pattern Recogn. 161, 111340 (2025). https:\/\/doi.org\/10.1016\/j.patcog.2024.111340","journal-title":"Pattern Recogn."},{"key":"2252_CR45","doi-asserted-by":"publisher","DOI":"10.1016\/j.ins.2024.121393","volume":"686","author":"J Shi","year":"2025","unstructured":"Shi, J., Li, M., Chen, Y., et al.: Multimodal graph learning with framelet-based stochastic configuration networks for emotion recognition in conversation. Inf. Sci. 686, 121393 (2025). https:\/\/doi.org\/10.1016\/j.ins.2024.121393","journal-title":"Inf. Sci."},{"key":"2252_CR46","doi-asserted-by":"crossref","unstructured":"J. Shi, M. Li, L. Bai, F. Cao, K. Lu, and J. Liang, MATCH: Modality-calibrated hypergraph fusion network for conversational emotion recognition, in Proc. Int. Joint Conf. Artificial Intelligence (IJCAI), 2025.","DOI":"10.24963\/ijcai.2025\/686"},{"key":"2252_CR47","unstructured":"A. C. Mendes da Silva and D. F. Silva, Heterogeneous graph neural network for music emotion recognition, in Proc. Int. Soc. Music Information Retrieval Conf. (ISMIR), 2022."},{"key":"2252_CR48","doi-asserted-by":"publisher","first-page":"2587","DOI":"10.1109\/ACCESS.2024.3350123","volume":"13","author":"J Guo","year":"2025","unstructured":"Guo, J., Wan, P.: Music emotion classification based on heterogeneous graph neural networks. IEEE Access 13, 2587\u20132598 (2025). https:\/\/doi.org\/10.1109\/ACCESS.2024.3350123","journal-title":"IEEE Access"},{"key":"2252_CR49","doi-asserted-by":"publisher","unstructured":"M. Won, S. Chun, and X. Serra, Toward interpretable music tagging with self-attention, arXiv preprint arXiv:1906.04972, 2019. https:\/\/doi.org\/10.48550\/arXiv.1906.04972","DOI":"10.48550\/arXiv.1906.04972"},{"key":"2252_CR50","doi-asserted-by":"crossref","unstructured":"D. Li, Y. Wang, K. Funakoshi, and M. Okumura, Joyful: Joint modality fusion and graph contrastive learning for multimodal emotion recognition, in\u00a0Proc. Conf. Empirical Methods in Natural Language Processing (EMNLP), 2023, pp. 1\u201313.","DOI":"10.18653\/v1\/2023.emnlp-main.996"},{"key":"2252_CR51","doi-asserted-by":"crossref","unstructured":"V. Parisae, D. Yushmanth, N. M. Sree, and J. Jannu, Classification and Detection of Apple Leaf Disease Using DenseNet201 and YOLOV8, in\u00a0Proc. 9th Int. Conf. Inventive Systems and Control (ICISC), 2025, pp. 70\u201377.","DOI":"10.1109\/ICISC65841.2025.11188291"},{"key":"2252_CR52","doi-asserted-by":"crossref","unstructured":"C. Jannu, D. Bharath, V. N. Sanjay, and V. Parisae, Deep Learning-Based Speech Emotion Recognition: Evaluating CNN, CLSTM, and LSTM Models, in\u00a0Proc. 9th Int. Conf. Inventive Systems and Control (ICISC), 2025, pp. 108\u2013115.","DOI":"10.1109\/ICISC65841.2025.11188229"},{"issue":"6","key":"2252_CR53","doi-asserted-by":"publisher","first-page":"4224","DOI":"10.1007\/s00034-025-03010-2","volume":"44","author":"C Jannu","year":"2025","unstructured":"Jannu, C., Burra, M., Vanambathina, S.D., Parisae, V.: Single channel speech enhancement using a complex dual-path multi axial transformer with frequency prompt. Circuits Syst. Signal Process. 44(6), 4224\u20134257 (2025)","journal-title":"Circuits Syst. Signal Process."},{"key":"2252_CR54","doi-asserted-by":"crossref","unstructured":"V. Parisae, S. N. Bhavanam, and M. V. Devi, Progressive learning framework for speech enhancement using multi-scale convolution and s-tcn, in\u00a0Proc. 8th Int. Conf. Inventive Systems and Control (ICISC), 2024, pp. 83\u201389.","DOI":"10.1109\/ICISC62624.2024.00021"},{"key":"2252_CR55","unstructured":"Bertin-Mahieux T, Ellis D P W, Whitman B, et al. The million song dataset. 2011."}],"container-title":["Multimedia Systems"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/link.springer.com\/content\/pdf\/10.1007\/s00530-026-02252-7.pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/link.springer.com\/article\/10.1007\/s00530-026-02252-7","content-type":"text\/html","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/link.springer.com\/content\/pdf\/10.1007\/s00530-026-02252-7.pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2026,7,6]],"date-time":"2026-07-06T05:07:25Z","timestamp":1783314445000},"score":1,"resource":{"primary":{"URL":"https:\/\/link.springer.com\/10.1007\/s00530-026-02252-7"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2026,3,10]]},"references-count":55,"journal-issue":{"issue":"3","published-print":{"date-parts":[[2026,6]]}},"alternative-id":["2252"],"URL":"https:\/\/doi.org\/10.1007\/s00530-026-02252-7","relation":{},"ISSN":["0942-4962","1432-1882"],"issn-type":[{"value":"0942-4962","type":"print"},{"value":"1432-1882","type":"electronic"}],"subject":[],"published":{"date-parts":[[2026,3,10]]},"assertion":[{"value":"21 August 2025","order":1,"name":"received","label":"Received","group":{"name":"ArticleHistory","label":"Article History"}},{"value":"24 January 2026","order":2,"name":"accepted","label":"Accepted","group":{"name":"ArticleHistory","label":"Article History"}},{"value":"10 March 2026","order":3,"name":"first_online","label":"First Online","group":{"name":"ArticleHistory","label":"Article History"}},{"order":1,"name":"Ethics","group":{"name":"EthicsHeading","label":"Declarations"}},{"value":"The authors declare no competing interests.","order":2,"name":"Ethics","group":{"name":"EthicsHeading","label":"Conflict of Interest"}}],"article-number":"209"}}