{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,5,22]],"date-time":"2026-05-22T03:05:27Z","timestamp":1779419127553,"version":"3.53.1"},"publisher-location":"Singapore","reference-count":21,"publisher":"Springer Nature Singapore","isbn-type":[{"value":"9789819500086","type":"print"},{"value":"9789819500093","type":"electronic"}],"license":[{"start":{"date-parts":[[2025,1,1]],"date-time":"2025-01-01T00:00:00Z","timestamp":1735689600000},"content-version":"tdm","delay-in-days":0,"URL":"https:\/\/www.springernature.com\/gp\/researchers\/text-and-data-mining"},{"start":{"date-parts":[[2025,1,1]],"date-time":"2025-01-01T00:00:00Z","timestamp":1735689600000},"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":[],"published-print":{"date-parts":[[2025]]},"DOI":"10.1007\/978-981-95-0009-3_14","type":"book-chapter","created":{"date-parts":[[2025,7,24]],"date-time":"2025-07-24T13:24:49Z","timestamp":1753363489000},"page":"159-170","update-policy":"https:\/\/doi.org\/10.1007\/springer_crossmark_policy","source":"Crossref","is-referenced-by-count":0,"title":["TSMDM-Net: A Speech Emotion Recognition Model Based on Multi-scale Time Series Dynamic Modeling"],"prefix":"10.1007","author":[{"given":"Wei","family":"Wei","sequence":"first","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Yibing","family":"Wang","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Bingkun","family":"Zhang","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Xiaodong","family":"Duan","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"297","published-online":{"date-parts":[[2025,7,25]]},"reference":[{"key":"14_CR1","doi-asserted-by":"crossref","unstructured":"Itzik, G., Nir, N.: Speech emotion recognition systems and their security aspects. Artif. Intell. Rev. 57(6) (2024)","DOI":"10.1007\/s10462-024-10760-z"},{"issue":"5","key":"14_CR2","doi-asserted-by":"publisher","first-page":"90","DOI":"10.1145\/3129340","volume":"61","author":"BW Schuller","year":"2018","unstructured":"Schuller, B.W.: Speech emotion recognition: two decades in a nutshell, benchmarks, and ongoing trends. Commun. ACM 61(5), 90\u201399 (2018)","journal-title":"Commun. ACM"},{"key":"14_CR3","doi-asserted-by":"crossref","unstructured":"Kang, X.: Speech emotion recognition algorithm of intelligent robot based on ACO-SVM. Int. J. Cognitive Comput. Eng. 6131\u2013142 (2025)","DOI":"10.1016\/j.ijcce.2024.11.008"},{"key":"14_CR4","doi-asserted-by":"crossref","unstructured":"Elsayed, N., et al.: Speech emotion recognition using supervised deep recurrent system for mental health monitoring. In: 2022 IEEE 8th World Forum on Internet of Things, WF-IOT, pp. 1\u20136 (2022)","DOI":"10.1109\/WF-IoT54382.2022.10152117"},{"key":"14_CR5","doi-asserted-by":"publisher","first-page":"106646","DOI":"10.1016\/j.cmpb.2022.106646","volume":"215","author":"M Maithri","year":"2022","unstructured":"Maithri, M., et al.: Automated emotion recognition: current trends and future perspectives. Comput. Methods Biomed. Programs 215, 106646 (2022)","journal-title":"Comput. Methods Biomed. Programs"},{"key":"14_CR6","doi-asserted-by":"crossref","unstructured":"Wang, Y., Shen, G., Xu, Y., Li, J., Zhao, Z: Learning mutual correlation in multimodal transformer for speech emotion recognition. In: Interspeech, pp. 4518\u20134522 (2021)","DOI":"10.21437\/Interspeech.2021-2004"},{"key":"14_CR7","doi-asserted-by":"crossref","unstructured":"Chen, W., Xing, X., Xu, X., Yang, J., Pang, J.: Key-sparse transformer for multimodal speech emotion recognition. In: ICASSP 2022\u20132022 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP), pp. 6897\u20136901 (2022)","DOI":"10.1109\/ICASSP43922.2022.9746598"},{"key":"14_CR8","unstructured":"Xingyu, C., Jiahong, Y., Renjie, Z., Liang, H., Kenneth, C., et al.: Speech emotion recognition with multi-task learning. In: Conference of the International Speech Communication Association (2021)"},{"issue":"4","key":"14_CR9","doi-asserted-by":"publisher","first-page":"587","DOI":"10.1109\/TSM.2020.3020985","volume":"33","author":"W Junliang","year":"2020","unstructured":"Junliang, W., Chuqiao, X., Zhengliang, Y., Jie, Z., Xiaoou, L., et al.: Deformable convolutional networks for efficient mixed-type wafer defect pattern recognition. IEEE Trans. Semicond. Manuf. 33(4), 587\u2013596 (2020)","journal-title":"IEEE Trans. Semicond. Manuf."},{"key":"14_CR10","doi-asserted-by":"crossref","unstructured":"Ren, P., et al.: Beyond fixation: dynamic window visual transformer. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition, pp. 11987\u201311997 (2022)","DOI":"10.1109\/CVPR52688.2022.01168"},{"key":"14_CR11","doi-asserted-by":"publisher","first-page":"108472","DOI":"10.1016\/j.knosys.2022.108472","volume":"243","author":"L Liu","year":"2022","unstructured":"Liu, L., Liu, W., Zhou, J., Deng, H., Feng, L.: ATDA: Attentional temporal dynamic activation for speech emotion recognition. Knowl.-Based Syst. 243, 108472 (2022)","journal-title":"Knowl.-Based Syst."},{"key":"14_CR12","doi-asserted-by":"crossref","unstructured":"Liu, J., Liu, Z., Wang, L., Gao, Y., Guo, L., Dang, J.: Temporal attention convolutional network for speech emotion recognition with latent representation. In: INTERSPEECH, pp. 2337\u20132341 (2020)","DOI":"10.21437\/Interspeech.2020-1520"},{"key":"14_CR13","doi-asserted-by":"crossref","unstructured":"Chen, W., Xing, X., Xu, X., Pang, J., Du, L.: SpeechFormer: a hierarchical efficient framework incorporating the characteristics of speech. Conference of the International Speech Communication Association, pp. 346\u2013350 (2022)","DOI":"10.21437\/Interspeech.2022-74"},{"key":"14_CR14","doi-asserted-by":"crossref","unstructured":"Zou, H., Si, Y., Chen, C., Rajan, D., Chng, E.S.: Speech emotion recognition with co-attention based multi-level acoustic information. In: IEEE International Conference on Acoustics, Speech, and Signal Processing, pp. 7367\u20137371 (2022)","DOI":"10.1109\/ICASSP43922.2022.9747095"},{"key":"14_CR15","doi-asserted-by":"crossref","unstructured":"Chen, W., Xing, X., Xu, X., Pang, J., Du, L.: DST: deformable speech transformer for emotion recognition. In: ICASSP 2023 - IEEE International Conference on Acoustics, Speech, and Signal Processing, pp. 1\u20135 (2023)","DOI":"10.1109\/ICASSP49357.2023.10096966"},{"key":"14_CR16","doi-asserted-by":"crossref","unstructured":"Shen, S., Liu, F., Zhou, A.: Mingling or misalignment? Temporal shift for speech emotion recognition with pre-trained representations. In: ICASSP 2023 - IEEE International Conference on Acoustics, Speech, and Signal Processing, pp. 1\u20135 (2023)","DOI":"10.1109\/ICASSP49357.2023.10095193"},{"key":"14_CR17","doi-asserted-by":"crossref","unstructured":"Chen, S., Xing, X., Zhang, W., et al.: DWFormer: dynamic window transformer for speech emotion recognition. In: ICASSP 2023 - IEEE International Conference on Acoustics, Speech, and Signal Processing (ICASSP), pp. 1\u20135 (2023)","DOI":"10.1109\/ICASSP49357.2023.10094651"},{"key":"14_CR18","doi-asserted-by":"crossref","unstructured":"Striletchi, V., Striletchi, C., Stan, A.: TBDM-Net: bidirectional dense networks with gender information for speech emotion recognition. CoRR, abs\/2409.10056 (2024)","DOI":"10.1109\/MLSP58920.2024.10734746"},{"key":"14_CR19","doi-asserted-by":"crossref","unstructured":"Dou, H., Xiaolong, H., Lingwei, W., Lianxin, J., Yang, M., et al.: MM-DFN: multimodal dynamic fusion network for emotion recognition in conversations. In: IEEE International Conference on Acoustics, Speech, and Signal Processing, pp. 7037\u20137041 (2022)","DOI":"10.1109\/ICASSP43922.2022.9747397"},{"key":"14_CR20","doi-asserted-by":"crossref","unstructured":"Lian, Z., Liu, B., Tao, J.: SMIN: semi-supervised multi-modal interaction network for conversational emotion recognition. IEEE Trans. Affect. Comput. 1 (2022)","DOI":"10.1109\/TAFFC.2022.3141237"},{"key":"14_CR21","unstructured":"Vaswani, A., et al.: Attention is all you need. In: Proceedings of the 31st International Conference on Neural Information Processing Systems, pp. 6000\u2013\u20136010 (2017)"}],"container-title":["Lecture Notes in Computer Science","Advanced Intelligent Computing Technology and Applications"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/link.springer.com\/content\/pdf\/10.1007\/978-981-95-0009-3_14","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2026,5,22]],"date-time":"2026-05-22T02:22:53Z","timestamp":1779416573000},"score":1,"resource":{"primary":{"URL":"https:\/\/link.springer.com\/10.1007\/978-981-95-0009-3_14"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2025]]},"ISBN":["9789819500086","9789819500093"],"references-count":21,"URL":"https:\/\/doi.org\/10.1007\/978-981-95-0009-3_14","relation":{},"ISSN":["0302-9743","1611-3349"],"issn-type":[{"value":"0302-9743","type":"print"},{"value":"1611-3349","type":"electronic"}],"subject":[],"published":{"date-parts":[[2025]]},"assertion":[{"value":"25 July 2025","order":1,"name":"first_online","label":"First Online","group":{"name":"ChapterHistory","label":"Chapter History"}},{"value":"The authors have no competing interests to declare relevant to the con-tent of this article.","order":1,"name":"Ethics","group":{"name":"EthicsHeading","label":"Disclosure of Interests"}},{"value":"ICIC","order":1,"name":"conference_acronym","label":"Conference Acronym","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"International Conference on Intelligent Computing","order":2,"name":"conference_name","label":"Conference Name","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"Ningbo","order":3,"name":"conference_city","label":"Conference City","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"China","order":4,"name":"conference_country","label":"Conference Country","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"2025","order":5,"name":"conference_year","label":"Conference Year","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"26 July 2025","order":7,"name":"conference_start_date","label":"Conference Start Date","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"29 July 2025","order":8,"name":"conference_end_date","label":"Conference End Date","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"21","order":9,"name":"conference_number","label":"Conference Number","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"icic2025","order":10,"name":"conference_id","label":"Conference ID","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"http:\/\/www.ic-icc.cn\/icg\/","order":11,"name":"conference_url","label":"Conference URL","group":{"name":"ConferenceInfo","label":"Conference Information"}}]}}