{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2025,10,9]],"date-time":"2025-10-09T03:40:57Z","timestamp":1759981257389,"version":"build-2065373602"},"reference-count":29,"publisher":"Springer Science and Business Media LLC","issue":"13","license":[{"start":{"date-parts":[[2025,9,11]],"date-time":"2025-09-11T00:00:00Z","timestamp":1757548800000},"content-version":"tdm","delay-in-days":0,"URL":"https:\/\/www.springernature.com\/gp\/researchers\/text-and-data-mining"},{"start":{"date-parts":[[2025,9,11]],"date-time":"2025-09-11T00:00:00Z","timestamp":1757548800000},"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":[[2025,12]]},"DOI":"10.1007\/s11760-025-04763-8","type":"journal-article","created":{"date-parts":[[2025,9,11]],"date-time":"2025-09-11T14:18:35Z","timestamp":1757600315000},"update-policy":"https:\/\/doi.org\/10.1007\/springer_crossmark_policy","source":"Crossref","is-referenced-by-count":0,"title":["Ensemble Learning for Improved Speech Emotion Recognition: A Control Dimension Analysis of Log-Mel Spectrograms from the CREMA-D Dataset"],"prefix":"10.1007","volume":"19","author":[{"given":"Zineddine Sarhani","family":"Kahhoul","sequence":"first","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Nadjiba","family":"Terki","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Mohamed Lakhdar","family":"Tiar","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Ilyes","family":"Benaissa","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Selma","family":"Boutiba","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"297","published-online":{"date-parts":[[2025,9,11]]},"reference":[{"key":"4763_CR1","doi-asserted-by":"publisher","first-page":"98","DOI":"10.1016\/j.inffus.2017.02.003","volume":"37","author":"S Poria","year":"2017","unstructured":"Poria, S., Cambria, E., Bajpai, R., Hussain, A.: A review of affective computing: From unimodal analysis to multimodal fusion. Information Fusion 37, 98\u2013125 (2017)","journal-title":"Information Fusion"},{"key":"4763_CR2","doi-asserted-by":"crossref","unstructured":"Izard, C.E.: Basic emotions, relations among emotions, and emotion-cognition relations. (1992)","DOI":"10.1007\/978-1-4899-0615-1_3"},{"issue":"1","key":"4763_CR3","doi-asserted-by":"publisher","first-page":"20","DOI":"10.1207\/s15327957pspr1001_2","volume":"10","author":"LF Barrett","year":"2006","unstructured":"Barrett, L.F.: Solving the emotion paradox: Categorization and the experience of emotion. Pers. Soc. Psychol. Rev. 10(1), 20\u201346 (2006)","journal-title":"Pers. Soc. Psychol. Rev."},{"issue":"4","key":"4763_CR4","doi-asserted-by":"publisher","first-page":"377","DOI":"10.1109\/TAFFC.2014.2336244","volume":"5","author":"H Cao","year":"2014","unstructured":"Cao, H., Cooper, D.G., Keutmann, M.K., Gur, R.C., Nenkova, A., Verma, R.: CREMA-D: Crowd-sourced emotional multimodal actors dataset. IEEE Trans. Affect. Comput. 5(4), 377\u2013390 (2014)","journal-title":"IEEE Trans. Affect. Comput."},{"key":"4763_CR5","doi-asserted-by":"crossref","unstructured":"Sacharin, V., Schlegel, K., Scherer, K.R.: Geneva Emotion Wheel rating study. Technical report, University of Geneva, Swiss Center for Affective Sciences (2012)","DOI":"10.1037\/t36935-000"},{"key":"4763_CR6","unstructured":"Kahhoul, Z., Terki, N., Benaissa, I., Baarir, Z.: SpectoResNet: Advancing Speech Emotion Recognition through Deep Learning and Data Augmentation on the CREMA-D Dataset. MDPI (2024)"},{"key":"4763_CR7","doi-asserted-by":"crossref","unstructured":"Gong, Y., Chung, Y.-A., Glass, J.: AST: Audio Spectrogram Transformer. In: Interspeech, pp. 571\u2013575 (2021)","DOI":"10.21437\/Interspeech.2021-698"},{"issue":"2","key":"4763_CR8","doi-asserted-by":"publisher","first-page":"541","DOI":"10.1007\/s10772-023-10035-y","volume":"26","author":"M Tellai","year":"2023","unstructured":"Tellai, M., Gao, L., Mao, Q.: An efficient speech emotion recognition based on a dual-stream cnn-transformer fusion network. Int. J. Speech Technol. 26(2), 541\u2013557 (2023)","journal-title":"Int. J. Speech Technol."},{"issue":"4","key":"4763_CR9","doi-asserted-by":"publisher","first-page":"1099","DOI":"10.1007\/s10772-023-10080-7","volume":"26","author":"M Tellai","year":"2023","unstructured":"Tellai, M., Mao, Q.: Cctg-net: Contextualized convolutional transformer-gru network for speech emotion recognition. Int. J. Speech Technol. 26(4), 1099\u20131116 (2023)","journal-title":"Int. J. Speech Technol."},{"issue":"21","key":"4763_CR10","doi-asserted-by":"publisher","first-page":"59699","DOI":"10.1007\/s11042-023-17803-7","volume":"83","author":"M Tellai","year":"2024","unstructured":"Tellai, M., Gao, L., Mao, Q., Abdelaziz, M.: A novel conversational hierarchical attention network for speech emotion recognition in dyadic conversation. Multimedia Tools and Applications 83(21), 59699\u201359723 (2024)","journal-title":"Multimedia Tools and Applications"},{"key":"4763_CR11","doi-asserted-by":"crossref","unstructured":"Wang, R., Xu, D., Cascone, L., Wang, Y., Chen, H., Zheng, J., Zhu, X.: Raft: Robust adversarial fusion transformer for multimodal sentiment analysis. Array, 100445 (2025)","DOI":"10.1016\/j.array.2025.100445"},{"key":"4763_CR12","doi-asserted-by":"crossref","unstructured":"Wang, R., Guo, C., Shabaz, M., Rida, I., Cambria, E., Zhu, X.: Cime: Contextual interaction-based multimodal emotion analysis with enhanced semantic information. IEEE Transactions on Computational Social Systems (2025)","DOI":"10.22541\/au.173750886.60448227\/v1"},{"key":"4763_CR13","doi-asserted-by":"crossref","unstructured":"Zhu, X., Wang, Y., Cambria, E., Rida, I., L\u00f3pez, J.S., Cui, L., Wang, R.: Rmer-dt: Robust multimodal emotion recognition in conversational contexts based on diffusion and transformers. Information Fusion, 103268 (2025)","DOI":"10.1016\/j.inffus.2025.103268"},{"key":"4763_CR14","doi-asserted-by":"crossref","unstructured":"Wang, R., Wang, Y., Cambria, E., Fan, X., Yu, X., Huang, Y., E, X., Zhu, X.: Contrastive-based removal of negative information in multimodal emotion analysis. Cognitive Computation 17(3), 107 (2025)","DOI":"10.1007\/s12559-025-10463-9"},{"key":"4763_CR15","doi-asserted-by":"crossref","unstructured":"Ristea, N.-C., Ionescu, R.T.: Self-paced ensemble learning for speech and audio classification. arXiv preprint arXiv:2103.11988 (2021)","DOI":"10.21437\/Interspeech.2021-155"},{"key":"4763_CR16","volume-title":"Spoken Language Processing: A Guide to Theory, Algorithm, and System Development","author":"X Huang","year":"2001","unstructured":"Huang, X., Acero, A., Hon, H.-W., Reddy, R.: Spoken Language Processing: A Guide to Theory, Algorithm, and System Development. Prentice Hall PTR, Upper Saddle River, NJ (2001)"},{"issue":"11","key":"4763_CR17","doi-asserted-by":"publisher","first-page":"2278","DOI":"10.1109\/5.726791","volume":"86","author":"Y LeCun","year":"1998","unstructured":"LeCun, Y., Bottou, L., Bengio, Y., Haffner, P.: Gradient-based learning applied to document recognition. Proc. IEEE 86(11), 2278\u20132324 (1998)","journal-title":"Proc. IEEE"},{"key":"4763_CR18","unstructured":"Krizhevsky, A., Sutskever, I., Hinton, G.E.: ImageNet classification with deep convolutional neural networks. In: Advances in Neural Information Processing Systems, pp. 1097\u20131105 (2012)"},{"key":"4763_CR19","unstructured":"Simonyan, K., Zisserman, A.: Very deep convolutional networks for large-scale image recognition. In: International Conference on Learning Representations (2015)"},{"key":"4763_CR20","doi-asserted-by":"crossref","unstructured":"He, K., Zhang, X., Ren, S., Sun, J.: Deep residual learning for image recognition. In: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, pp. 770\u2013778 (2016)","DOI":"10.1109\/CVPR.2016.90"},{"key":"4763_CR21","unstructured":"Iandola, F.N., Han, S., Moskewicz, M.W., Ashraf, K., Dally, W.J., Keutzer, K.: SqueezeNet: AlexNet-level accuracy with 50x fewer parameters and<0.5 MB model size. arXiv preprint arXiv:1602.07360 (2016)"},{"key":"4763_CR22","unstructured":"Howard, A.G., Zhu, M., Chen, B., Kalenichenko, D., Wang, W., Weyand, T., Andreetto, M., Adam, H.: MobileNets: Efficient convolutional neural networks for mobile vision applications. arXiv preprint arXiv:1704.04861 (2017)"},{"key":"4763_CR23","doi-asserted-by":"crossref","unstructured":"Huang, G., Liu, Z., Van Der\u00a0Maaten, L., Weinberger, K.Q.: Densely connected convolutional networks. In: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, pp. 4700\u20134708 (2017)","DOI":"10.1109\/CVPR.2017.243"},{"key":"4763_CR24","unstructured":"Tan, M., Le, Q.V.: EfficientNet: Rethinking model scaling for convolutional neural networks. In: International Conference on Machine Learning, pp. 6105\u20136114 (2019)"},{"key":"4763_CR25","doi-asserted-by":"crossref","unstructured":"Ganaie, M.A., Hu, M., Malik, A.K., Tanveer, M., Suganthan, P.N.: Ensemble deep learning: A review. arXiv preprint arXiv:2104.02395 (2022)","DOI":"10.1016\/j.engappai.2022.105151"},{"issue":"6","key":"4763_CR26","doi-asserted-by":"publisher","first-page":"1161","DOI":"10.1037\/h0077714","volume":"39","author":"JA Russell","year":"1980","unstructured":"Russell, J.A.: A circumplex model of affect. J. Pers. Soc. Psychol. 39(6), 1161\u20131178 (1980)","journal-title":"J. Pers. Soc. Psychol."},{"issue":"2","key":"4763_CR27","doi-asserted-by":"publisher","first-page":"423","DOI":"10.1109\/JSTSP.2019.2955012","volume":"14","author":"Z Zhao","year":"2020","unstructured":"Zhao, Z., Bao, Z., Zhang, Z., Deng, J., Cummins, N., Wang, H., Tao, J., Schuller, B.: Automatic assessment of depression from speech via a hierarchical attention transfer network and attention autoencoders. IEEE Journal of Selected Topics in Signal Processing 14(2), 423\u2013434 (2020)","journal-title":"IEEE Journal of Selected Topics in Signal Processing"},{"key":"4763_CR28","doi-asserted-by":"crossref","unstructured":"Li, Y., Zhao, T., Kawahara, T.: Improved end-to-end speech emotion recognition using self attention mechanism and multitask learning. In: Interspeech, pp. 2803\u20132807 (2019)","DOI":"10.21437\/Interspeech.2019-2594"},{"key":"4763_CR29","doi-asserted-by":"crossref","unstructured":"Croitoru, F.-A., Ristea, N.-C., Ionescu, R.T., Sebe, N.: Learning Rate Curriculum. International Journal of Computer Vision, 1\u201324 (2024)","DOI":"10.1007\/s11263-024-02186-5"}],"container-title":["Signal, Image and Video Processing"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/link.springer.com\/content\/pdf\/10.1007\/s11760-025-04763-8.pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/link.springer.com\/article\/10.1007\/s11760-025-04763-8\/fulltext.html","content-type":"text\/html","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/link.springer.com\/content\/pdf\/10.1007\/s11760-025-04763-8.pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,10,9]],"date-time":"2025-10-09T03:26:14Z","timestamp":1759980374000},"score":1,"resource":{"primary":{"URL":"https:\/\/link.springer.com\/10.1007\/s11760-025-04763-8"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2025,9,11]]},"references-count":29,"journal-issue":{"issue":"13","published-print":{"date-parts":[[2025,12]]}},"alternative-id":["4763"],"URL":"https:\/\/doi.org\/10.1007\/s11760-025-04763-8","relation":{},"ISSN":["1863-1703","1863-1711"],"issn-type":[{"type":"print","value":"1863-1703"},{"type":"electronic","value":"1863-1711"}],"subject":[],"published":{"date-parts":[[2025,9,11]]},"assertion":[{"value":"6 August 2025","order":1,"name":"received","label":"Received","group":{"name":"ArticleHistory","label":"Article History"}},{"value":"31 August 2025","order":2,"name":"revised","label":"Revised","group":{"name":"ArticleHistory","label":"Article History"}},{"value":"6 September 2025","order":3,"name":"accepted","label":"Accepted","group":{"name":"ArticleHistory","label":"Article History"}},{"value":"11 September 2025","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 no conflicts of interest.","order":2,"name":"Ethics","group":{"name":"EthicsHeading","label":"Conflicts of Interest"}},{"value":"The authors declare no competing interests.","order":3,"name":"Ethics","group":{"name":"EthicsHeading","label":"Competing interests"}}],"article-number":"1135"}}