{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2025,7,1]],"date-time":"2025-07-01T11:53:34Z","timestamp":1751370814049,"version":"3.37.3"},"reference-count":63,"publisher":"Springer Science and Business Media LLC","issue":"15","license":[{"start":{"date-parts":[[2023,10,16]],"date-time":"2023-10-16T00:00:00Z","timestamp":1697414400000},"content-version":"tdm","delay-in-days":0,"URL":"https:\/\/www.springernature.com\/gp\/researchers\/text-and-data-mining"},{"start":{"date-parts":[[2023,10,16]],"date-time":"2023-10-16T00:00:00Z","timestamp":1697414400000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/www.springernature.com\/gp\/researchers\/text-and-data-mining"}],"funder":[{"name":"Natural Science Foundation of the Colleges and Universities in Anhui Province of China","award":["No. KJ2020A0035","No. KJ2021A0640"],"award-info":[{"award-number":["No. KJ2020A0035","No. KJ2021A0640"]}]},{"name":"Hong Kong Innovation and Technology Commission"}],"content-domain":{"domain":["link.springer.com"],"crossmark-restriction":false},"short-container-title":["Multimed Tools Appl"],"DOI":"10.1007\/s11042-023-17056-4","type":"journal-article","created":{"date-parts":[[2023,10,16]],"date-time":"2023-10-16T08:01:54Z","timestamp":1697443314000},"page":"43871-43906","update-policy":"https:\/\/doi.org\/10.1007\/springer_crossmark_policy","source":"Crossref","is-referenced-by-count":4,"title":["A hybrid neural network model based on optimized margin softmax loss function for music classification"],"prefix":"10.1007","volume":"83","author":[{"ORCID":"https:\/\/orcid.org\/0000-0002-2450-6052","authenticated-orcid":false,"given":"Jingxian","family":"Li","sequence":"first","affiliation":[]},{"given":"Lixin","family":"Han","sequence":"additional","affiliation":[]},{"given":"Xin","family":"Wang","sequence":"additional","affiliation":[]},{"given":"Yang","family":"Wang","sequence":"additional","affiliation":[]},{"given":"Jianhua","family":"Xia","sequence":"additional","affiliation":[]},{"given":"Yi","family":"Yang","sequence":"additional","affiliation":[]},{"given":"Bing","family":"Hu","sequence":"additional","affiliation":[]},{"given":"Shu","family":"Li","sequence":"additional","affiliation":[]},{"given":"Hong","family":"Yan","sequence":"additional","affiliation":[]}],"member":"297","published-online":{"date-parts":[[2023,10,16]]},"reference":[{"issue":"12","key":"17056_CR1","doi-asserted-by":"publisher","first-page":"13568","DOI":"10.1007\/s10489-021-03118-3","volume":"52","author":"HM Abdulwahab","year":"2022","unstructured":"Abdulwahab HM, Ajitha S, Saif MAN (2022) Feature selection techniques in the context of big data: taxonomy and analysis. Appl Intell 52(12):13568\u201313613","journal-title":"Appl Intell"},{"issue":"10","key":"17056_CR2","first-page":"355","volume":"8","author":"S Alhagry","year":"2017","unstructured":"Alhagry S, Fahmy AA, El-Khoribi RA (2017) Emotion recognition based on EEG using LSTM recurrent neural network. Int J Adv Comput Sci Appl 8(10):355\u2013358","journal-title":"Int J Adv Comput Sci Appl"},{"key":"17056_CR3","doi-asserted-by":"crossref","unstructured":"Almalawi A, Khan AI, Alsolami F, Alkhathlan A, Fahad A, Irshad K, ... & Qaiyum S (2022) Arithmetic optimization algorithm with deep learning enabled airborne particle-bound metals size prediction model. Chemosphere 303:134960","DOI":"10.1016\/j.chemosphere.2022.134960"},{"key":"17056_CR4","doi-asserted-by":"publisher","first-page":"1549","DOI":"10.1109\/TASLP.2020.2993152","volume":"28","author":"M Bhattacharjee","year":"2020","unstructured":"Bhattacharjee M, Prasanna SM, Guha P (2020) Speech\/music classification using features from spectral peaks. IEEE\/ACM Trans Audio Speech Lang Process 28:1549\u20131559","journal-title":"IEEE\/ACM Trans Audio Speech Lang Process"},{"key":"17056_CR5","first-page":"1","volume":"2020","author":"C Chen","year":"2020","unstructured":"Chen C, Li Q (2020) A multimodal music emotion classification method based on multifeature combined network classifier. Math Probl Eng 2020:1\u201311","journal-title":"Math Probl Eng"},{"key":"17056_CR6","doi-asserted-by":"crossref","unstructured":"Chen G, Parada C, Sainath TN (2015) Query-by-example keyword spotting using long short-term memory networks. In: Proceedings of 2015 IEEE International Conference on Acoustics, Speech and Signal Processing, pp 5236\u20135240","DOI":"10.1109\/ICASSP.2015.7178970"},{"key":"17056_CR7","unstructured":"Choi K, Fazekas G, Sandler M (2016) Automatic tagging using deep convolutional neural networks. In: Proceedings of the 17th International Society for Music Information Retrieval Conference, pp 805\u2013811"},{"key":"17056_CR8","doi-asserted-by":"crossref","unstructured":"Choi K, Fazekas G, Sandler M, Cho K (2017) Convolutional recurrent neural networks for music classification. In: Proceedings of 2017 IEEE International Conference on Acoustics, Speech and Signal Processing, pp. 2392\u20132396","DOI":"10.1109\/ICASSP.2017.7952585"},{"key":"17056_CR9","doi-asserted-by":"crossref","unstructured":"Chopra S, Hadsell R, LeCun Y (2005) Learning a similarity metric discriminatively, with application to face verification. In: Proceedings of 2005 IEEE Computer Society Conference on Computer Vision and Pattern Recognition, pp. 539\u2013546","DOI":"10.1109\/CVPR.2005.202"},{"key":"17056_CR10","doi-asserted-by":"publisher","first-page":"28","DOI":"10.1016\/j.asoc.2016.12.024","volume":"52","author":"YM Costa","year":"2017","unstructured":"Costa YM, Oliveira LS, Silla CN Jr (2017) An evaluation of convolutional neural networks for music classification using spectrograms. Appl Soft Comput 52:28\u201338","journal-title":"Appl Soft Comput"},{"key":"17056_CR11","doi-asserted-by":"publisher","first-page":"113071","DOI":"10.1016\/j.eswa.2019.113071","volume":"144","author":"ACM da Silva","year":"2020","unstructured":"da Silva ACM, Coelho MAN, Neto RF (2020) A Music Classification model based on metric learning applied to MP3 audio files. Expert Syst Appl 144:113071","journal-title":"Expert Syst Appl"},{"key":"17056_CR12","doi-asserted-by":"crossref","unstructured":"Dai J, Liang S, Xue W, Ni C, Liu W (2016) Long short-term memory recurrent neural network based segment features for music genre classification. In: Proceedings of the 10th International Symposium on Chinese Spoken Language Processing, pp. 1\u20135","DOI":"10.1109\/ISCSLP.2016.7918369"},{"key":"17056_CR13","unstructured":"Defferrard M, Benzi K, Vandergheynst P, Bresson X (2016) FMA: A dataset for music analysis. In: Proceedings of the 18th International Society for Music Information Retrieval Conference, pp. 316\u2013323"},{"key":"17056_CR14","doi-asserted-by":"crossref","unstructured":"Deng J, Guo J, Xue N, Zafeiriou S (2019) Arcface: Additive angular margin loss for deep face recognition. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition, pp. 4690\u20134699","DOI":"10.1109\/CVPR.2019.00482"},{"issue":"4","key":"17056_CR15","doi-asserted-by":"publisher","first-page":"4543","DOI":"10.1007\/s10489-021-02550-9","volume":"52","author":"P Dhal","year":"2021","unstructured":"Dhal P, Azad C (2021) A comprehensive survey on feature selection in the various fields of machine learning. Appl Intell 52(4):4543\u20134581","journal-title":"Appl Intell"},{"issue":"12","key":"17056_CR16","doi-asserted-by":"publisher","first-page":"3150","DOI":"10.1109\/TMM.2019.2918739","volume":"21","author":"Y Dong","year":"2019","unstructured":"Dong Y, Yang X, Zhao X, Li J (2019) Bidirectional convolutional recurrent sparse network (BCRSN): an efficient model for music emotion recognition. IEEE Trans Multimed 21(12):3150\u20133163","journal-title":"IEEE Trans Multimed"},{"issue":"4","key":"17056_CR17","first-page":"48","volume":"103","author":"D Eck","year":"2002","unstructured":"Eck D, Schmidhuber J (2002) A first look at music composition using lstm recurrent neural networks.  Technical report,\u00a0  Istituto Dalle Molle Di Studi Sull Intelligenza Artificiale 103(4):48\u201356","journal-title":"Technical report,\u00a0 Istituto Dalle Molle Di Studi Sull Intelligenza Artificiale"},{"key":"17056_CR18","doi-asserted-by":"crossref","unstructured":"Ferraro A, Bogdanov D, Jay XS, Jeon H, Yoon J (2021) How low can you go? Reducing frequency and time resolution in current CNN architectures for music auto-tagging. In: Proceedings of the 28th European Signal Processing Conference, pp. 131\u2013135","DOI":"10.23919\/Eusipco47968.2020.9287769"},{"issue":"10","key":"17056_CR19","doi-asserted-by":"publisher","first-page":"2222","DOI":"10.1109\/TNNLS.2016.2582924","volume":"28","author":"K Greff","year":"2016","unstructured":"Greff K, Srivastava RK, Koutn\u00edk J, Steunebrink BR, Schmidhuber J (2016) LSTM: A search space odyssey. IEEE Trans Neural Netw Learn Syst 28(10):2222\u20132232","journal-title":"IEEE Trans Neural Netw Learn Syst"},{"key":"17056_CR20","doi-asserted-by":"crossref","unstructured":"Hadsell R, Chopra S, LeCun Y (2006) Dimensionality reduction by learning an invariant mapping. In: Proceedings of 2006 IEEE Computer Society Conference on Computer Vision and Pattern Recognition, pp. 1735\u20131742","DOI":"10.1109\/CVPR.2006.100"},{"issue":"6","key":"17056_CR21","doi-asserted-by":"publisher","first-page":"166335","DOI":"10.1007\/s11704-021-0569-4","volume":"16","author":"D Han","year":"2022","unstructured":"Han D, Kong Y, Han J, Wang G (2022) A survey of music emotion recognition. Front Comp Sci 16(6):166335","journal-title":"Front Comp Sci"},{"issue":"3","key":"17056_CR22","first-page":"760","volume":"24","author":"S Hizlisoy","year":"2021","unstructured":"Hizlisoy S, Yildirim S, Tufekci Z (2021) Music emotion recognition using convolutional long short term memory deep neural networks. Eng Sci Technol 24(3):760\u2013767","journal-title":"Eng Sci Technol"},{"issue":"8","key":"17056_CR23","doi-asserted-by":"publisher","first-page":"1735","DOI":"10.1162\/neco.1997.9.8.1735","volume":"9","author":"S Hochreiter","year":"1997","unstructured":"Hochreiter S, Schmidhuber J (1997) Long short-term memory. Neural Comput 9(8):1735\u20131780","journal-title":"Neural Comput"},{"key":"17056_CR24","doi-asserted-by":"crossref","unstructured":"Hoffer E, Ailon N (2015) Deep metric learning using triplet network. In: Proceedings of the 3rd International Workshop on Similarity-Based Pattern Recognition, pp. 84\u201392","DOI":"10.1007\/978-3-319-24261-3_7"},{"key":"17056_CR25","doi-asserted-by":"publisher","first-page":"136615","DOI":"10.1016\/j.chemosphere.2022.136615","volume":"309","author":"N Islam","year":"2022","unstructured":"Islam N, Irshad K (2022) Artificial ecosystem optimization with Deep Learning Enabled Water Quality Prediction and Classification model. Chemosphere 309:136615","journal-title":"Chemosphere"},{"key":"17056_CR26","doi-asserted-by":"crossref","unstructured":"Jakubik J (2017) Evaluation of gated recurrent neural networks in music classification tasks. In: Proceedings of the International Conference on Information Systems Architecture and Technology, pp. 27\u201337","DOI":"10.1007\/978-3-319-67220-5_3"},{"key":"17056_CR27","doi-asserted-by":"publisher","first-page":"104996","DOI":"10.1016\/j.engappai.2022.104996","volume":"114","author":"AI Khan","year":"2022","unstructured":"Khan AI, Alsolami F, Alqurashi F, Abushark YB, Sarker IH (2022) Novel energy management scheme in IoT enabled smart irrigation system using optimized intelligence methods. Eng Appl Artif Intell 114:104996","journal-title":"Eng Appl Artif Intell"},{"issue":"3","key":"17056_CR28","doi-asserted-by":"publisher","first-page":"102185","DOI":"10.1016\/j.ipm.2019.102185","volume":"57","author":"C Li","year":"2020","unstructured":"Li C, Bao Z, Li L, Zhao Z (2020) Exploring temporal representations by leveraging attention-based bidirectional LSTM-RNNs for multi-modal emotion recognition. Inf Process Manage 57(3):102185","journal-title":"Inf Process Manage"},{"issue":"4","key":"17056_CR29","doi-asserted-by":"publisher","first-page":"4621","DOI":"10.1007\/s11042-020-10465-9","volume":"81","author":"J Li","year":"2022","unstructured":"Li J, Han L, Li X, Zhu J, Yuan B, Gou Z (2022) An evaluation of deep neural network models for music classification using spectrograms. Multimed Tools Applic 81(4):4621\u20134647","journal-title":"Multimed Tools Applic"},{"issue":"13","key":"17056_CR30","doi-asserted-by":"publisher","first-page":"10337","DOI":"10.1007\/s00521-022-06896-0","volume":"34","author":"J Li","year":"2022","unstructured":"Li J, Han L, Wang Y, Yuan B, Yuan X, Yang Y, Yan H (2022) Combined angular margin and cosine margin softmax loss for music classification based on spectrograms. Neural Comput Appl 34(13):10337\u201310353","journal-title":"Neural Comput Appl"},{"key":"17056_CR31","first-page":"3","volume":"2016","author":"T Lidy","year":"2016","unstructured":"Lidy T, Schindler A (2016) Parallel convolutional neural networks for music genre and mood classification. MIREX 2016:3","journal-title":"MIREX"},{"key":"17056_CR32","doi-asserted-by":"crossref","unstructured":"Liu H, Fang Y, Huang Q (2019) Music emotion recognition using a variant of recurrent neural network. In: Proceedings of 2018 International Conference on Mathematics, Modeling, Simulation and Statistics Application. pp. 15\u201318","DOI":"10.2991\/mmssa-18.2019.4"},{"key":"17056_CR33","doi-asserted-by":"crossref","unstructured":"Liu H, Zhu X, Lei Z, Li SZ (2019) Adaptiveface: Adaptive margin and sampling for face recognition. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition, pp. 11947\u201311956","DOI":"10.1109\/CVPR.2019.01222"},{"key":"17056_CR34","doi-asserted-by":"crossref","unstructured":"Liu W, Wen Y, Yu Z, Li M, Raj B, Song L (2017) Sphereface: Deep hypersphere embedding for face recognition. In: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, pp. 212\u2013220","DOI":"10.1109\/CVPR.2017.713"},{"key":"17056_CR35","unstructured":"Liu W, Wen Y, Yu Z, Yang M (2016) Large-margin softmax loss for convolutional neural networks. In: Proceedings of the International Conference on Machine Learning, pp. 507\u2013516"},{"issue":"7553","key":"17056_CR36","doi-asserted-by":"publisher","first-page":"436","DOI":"10.1038\/nature14539","volume":"521","author":"Y LeCun","year":"2015","unstructured":"LeCun Y, Bengio Y, Hinton G (2015) Deep learning. Nature 521(7553):436\u2013444","journal-title":"Nature"},{"issue":"1","key":"17056_CR37","doi-asserted-by":"publisher","first-page":"150","DOI":"10.3390\/app8010150","volume":"8","author":"J Lee","year":"2018","unstructured":"Lee J, Park J, Kim KL, Nam J (2018) SampleCNN: End-to-end deep convolutional neural networks using very small filters for music classification. Appl Sci 8(1):150","journal-title":"Appl Sci"},{"key":"17056_CR38","doi-asserted-by":"crossref","unstructured":"Lyu Q, Wu Z, Zhu J (2015) Polyphonic music modelling with LSTM-RTRBM. In: Proceedings of the 23rd ACM International Conference on Multimedia, pp. 991\u2013994","DOI":"10.1145\/2733373.2806383"},{"issue":"8","key":"17056_CR39","doi-asserted-by":"publisher","first-page":"2203","DOI":"10.1109\/TMM.2014.2360798","volume":"16","author":"Q Mao","year":"2014","unstructured":"Mao Q, Dong M, Huang Z, Zhan Y (2014) Learning salient features for speech emotion recognition using convolutional neural networks. IEEE Trans Multimed 16(8):2203\u20132213","journal-title":"IEEE Trans Multimed"},{"issue":"1","key":"17056_CR40","doi-asserted-by":"publisher","first-page":"41","DOI":"10.1109\/MSP.2018.2874383","volume":"36","author":"J Nam","year":"2018","unstructured":"Nam J, Choi K, Lee J, Chou SY, Yang YH (2018) Deep learning for audio-based music classification and tagging: Teaching computers to distinguish rock from bach. IEEE Signal Process Mag 36(1):41\u201351","journal-title":"IEEE Signal Process Mag"},{"key":"17056_CR41","doi-asserted-by":"crossref","unstructured":"Pons J, Serra X (2019) Randomly weighted cnns for (music) audio classification. In: Proceedings of 2019 IEEE International Conference on Acoustics, Speech and Signal Processing, pp. 336\u2013340","DOI":"10.1109\/ICASSP.2019.8682912"},{"key":"17056_CR42","doi-asserted-by":"publisher","first-page":"16","DOI":"10.1016\/j.procs.2020.03.178","volume":"167","author":"S Rajesh","year":"2020","unstructured":"Rajesh S, Nalini NJ (2020) Musical instrument emotion recognition using deep recurrent neural network. Procedia Comput Sci 167:16\u201325","journal-title":"Procedia Comput Sci"},{"key":"17056_CR43","unstructured":"Ranjan R, Castillo CD, Chellappa R (2017) L2-constrained softmax loss for discriminative face verification. arXiv preprint arXiv:1703.09507"},{"issue":"5","key":"17056_CR44","doi-asserted-by":"publisher","first-page":"102270","DOI":"10.1016\/j.ipm.2020.102270","volume":"57","author":"M Russo","year":"2020","unstructured":"Russo M, Kraljevi\u0107 L, Stella M, Sikora M (2020) Cochleogram-based approach for detecting perceived emotions in music. Inf Process Manage 57(5):102270","journal-title":"Inf Process Manage"},{"key":"17056_CR45","doi-asserted-by":"crossref","unstructured":"Schroff F, Kalenichenko D, Philbin J (2015) Facenet: A unified embedding for face recognition and clustering. In: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, pp. 815\u2013823","DOI":"10.1109\/CVPR.2015.7298682"},{"issue":"20","key":"17056_CR46","doi-asserted-by":"publisher","first-page":"27061","DOI":"10.1007\/s11042-018-5904-x","volume":"77","author":"S Singh","year":"2018","unstructured":"Singh S, Kasana SS (2018) Efficient classification of the hyperspectral images using deep learning. Multimed Tools Applic 77(20):27061\u201327074","journal-title":"Multimed Tools Applic"},{"key":"17056_CR47","doi-asserted-by":"publisher","first-page":"104","DOI":"10.1016\/j.neucom.2018.02.076","volume":"292","author":"G Song","year":"2018","unstructured":"Song G, Wang Z, Han F, Ding S, Iqbal MA (2018) Music auto-tagging using deep Recurrent Neural Networks. Neurocomputing 292:104\u2013110","journal-title":"Neurocomputing"},{"key":"17056_CR48","unstructured":"Tang CP, Chui KL, Yu YK, Zeng Z, Wong KH (2018) Music genre classification using a hierarchical long short term memory (LSTM) model. In: Proceedings of the 3rd International Workshop on Pattern Recognition, pp. 334\u2013340"},{"issue":"5","key":"17056_CR49","doi-asserted-by":"publisher","first-page":"293","DOI":"10.1109\/TSA.2002.800560","volume":"10","author":"G Tzanetakis","year":"2002","unstructured":"Tzanetakis G, Cook P (2002) Musical genre classification of audio signals. IEEE Trans Speech Audio Process 10(5):293\u2013302","journal-title":"IEEE Trans Speech Audio Process"},{"issue":"7","key":"17056_CR50","doi-asserted-by":"publisher","first-page":"926","DOI":"10.1109\/LSP.2018.2822810","volume":"25","author":"F Wang","year":"2018","unstructured":"Wang F, Cheng J, Liu W, Liu H (2018) Additive margin softmax for face verification. IEEE Signal Process Lett 25(7):926\u2013930","journal-title":"IEEE Signal Process Lett"},{"key":"17056_CR51","doi-asserted-by":"crossref","unstructured":"Wang F, Xiang X, Cheng J, Yuille AL (2017) Normface: L2 hypersphere embedding for face verification. In: Proceedings of the 25th ACM International Conference on Multimedia, pp. 1041\u20131049","DOI":"10.1145\/3123266.3123359"},{"key":"17056_CR52","doi-asserted-by":"crossref","unstructured":"Wang H, Wang Y, Zhou Z, Ji X, Gong D, Zhou J, ... & Liu W (2018) Cosface: Large margin cosine loss for deep face recognition. In: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, pp. 5265\u20135274","DOI":"10.1109\/CVPR.2018.00552"},{"key":"17056_CR53","doi-asserted-by":"crossref","unstructured":"Wang J, Song Y, Leung T, Rosenberg C, Wang J, Philbin J, ... & Wu Y (2014) Learning fine-grained image similarity with deep ranking. In: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, pp. 1386\u20131393","DOI":"10.1109\/CVPR.2014.180"},{"key":"17056_CR54","doi-asserted-by":"publisher","first-page":"581","DOI":"10.1109\/TASLP.2019.2959251","volume":"28","author":"J Wang","year":"2019","unstructured":"Wang J, Yu LC, Lai KR, Zhang X (2019) Tree-structured regional CNN-LSTM model for dimensional sentiment analysis. IEEE\/ACM Trans Audio Speech Lang Process 28:581\u2013591","journal-title":"IEEE\/ACM Trans Audio Speech Lang Process"},{"key":"17056_CR55","doi-asserted-by":"crossref","unstructured":"Wang Z, Muknahallipatna S, Fan M, Okray A, Lan C (2019) Music classification using an improved crnn with multi-directional spatial dependencies in both time and frequency dimensions. In: Proceedings of 2019 International Joint Conference on Neural Networks, pp. 1\u20138","DOI":"10.1109\/IJCNN.2019.8852128"},{"key":"17056_CR56","doi-asserted-by":"crossref","unstructured":"Wen Y, Zhang K, Li Z, Qiao Y (2016) A discriminative feature learning approach for deep face recognition. In: Proceedings of the 14th European Conference on Computer Vision, pp. 499\u2013515","DOI":"10.1007\/978-3-319-46478-7_31"},{"issue":"3","key":"17056_CR57","doi-asserted-by":"publisher","first-page":"3017","DOI":"10.1007\/s10489-022-03386-7","volume":"53","author":"W Weng","year":"2023","unstructured":"Weng W, Wei B, Ke W, Fan Y, Wang J, Li Y (2023) Learning label-specific features with global and local label correlation for multi-label classification. Appl Intell 53(3):3017\u20133033","journal-title":"Appl Intell"},{"key":"17056_CR58","doi-asserted-by":"crossref","unstructured":"Wu HH, Kao CC, Tang Q, Sun M, McFee B, Bello JP, Wang C (2021) Multi-task self-supervised pre-training for music classification. In: Proceedings of 2021 IEEE International Conference on Acoustics, Speech and Signal Processing, pp. 556\u2013560","DOI":"10.1109\/ICASSP39728.2021.9414405"},{"key":"17056_CR59","doi-asserted-by":"crossref","unstructured":"Yu Y (2021) Research on Music Emotion Classification Based on CNN-LSTM Network. In: Proceedings of the 5th Asian Conference on Artificial Intelligence Technology, pp. 473\u2013476","DOI":"10.1109\/ACAIT53529.2021.9731277"},{"key":"17056_CR60","doi-asserted-by":"crossref","unstructured":"Zhang W, Lei W, Xu X, Xing X (2016) Improved music genre classification with convolutional neural networks. In: Proceedings of the 17th Annual Conference of the International Speech Communication Association, pp. 3304\u20133308","DOI":"10.21437\/Interspeech.2016-1236"},{"key":"17056_CR61","doi-asserted-by":"publisher","first-page":"312","DOI":"10.1016\/j.bspc.2018.08.035","volume":"47","author":"J Zhao","year":"2019","unstructured":"Zhao J, Mao X, Chen L (2019) Speech emotion recognition using deep 1D & 2D CNN LSTM networks. Biomed Signal Process Control 47:312\u2013323","journal-title":"Biomed Signal Process Control"},{"key":"17056_CR62","doi-asserted-by":"crossref","unstructured":"Zhao K, Li S, Cai J, Wang H, Wang J (2019) An emotional symbolic music generation system based on LSTM networks. In: Proceedings of 2019 IEEE 3rd Information Technology, Networking, Electronic and Automation Control Conference, pp. 2039\u20132043","DOI":"10.1109\/ITNEC.2019.8729266"},{"issue":"1","key":"17056_CR63","doi-asserted-by":"publisher","first-page":"74","DOI":"10.1093\/nsr\/nwy108","volume":"6","author":"ZH Zhou","year":"2019","unstructured":"Zhou ZH, Feng J (2019) Deep forest. National Science Review 6(1):74\u201386","journal-title":"National Science Review"}],"container-title":["Multimedia Tools and Applications"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/link.springer.com\/content\/pdf\/10.1007\/s11042-023-17056-4.pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/link.springer.com\/article\/10.1007\/s11042-023-17056-4\/fulltext.html","content-type":"text\/html","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/link.springer.com\/content\/pdf\/10.1007\/s11042-023-17056-4.pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2024,4,29]],"date-time":"2024-04-29T11:21:44Z","timestamp":1714389704000},"score":1,"resource":{"primary":{"URL":"https:\/\/link.springer.com\/10.1007\/s11042-023-17056-4"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2023,10,16]]},"references-count":63,"journal-issue":{"issue":"15","published-online":{"date-parts":[[2024,5]]}},"alternative-id":["17056"],"URL":"https:\/\/doi.org\/10.1007\/s11042-023-17056-4","relation":{},"ISSN":["1573-7721"],"issn-type":[{"type":"electronic","value":"1573-7721"}],"subject":[],"published":{"date-parts":[[2023,10,16]]},"assertion":[{"value":"24 December 2022","order":1,"name":"received","label":"Received","group":{"name":"ArticleHistory","label":"Article History"}},{"value":"23 August 2023","order":2,"name":"revised","label":"Revised","group":{"name":"ArticleHistory","label":"Article History"}},{"value":"14 September 2023","order":3,"name":"accepted","label":"Accepted","group":{"name":"ArticleHistory","label":"Article History"}},{"value":"16 October 2023","order":4,"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 that they have no conflict of interest.","order":2,"name":"Ethics","group":{"name":"EthicsHeading","label":"Conflict of interest"}}]}}