{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,7,18]],"date-time":"2026-07-18T21:02:12Z","timestamp":1784408532088,"version":"3.55.0"},"publisher-location":"Singapore","reference-count":17,"publisher":"Springer Nature Singapore","isbn-type":[{"value":"9789819234097","type":"print"},{"value":"9789819234103","type":"electronic"}],"license":[{"start":{"date-parts":[[2026,7,19]],"date-time":"2026-07-19T00:00:00Z","timestamp":1784419200000},"content-version":"tdm","delay-in-days":0,"URL":"https:\/\/www.springernature.com\/gp\/researchers\/text-and-data-mining"},{"start":{"date-parts":[[2026,7,19]],"date-time":"2026-07-19T00:00:00Z","timestamp":1784419200000},"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":[[2027]]},"DOI":"10.1007\/978-981-92-3410-3_30","type":"book-chapter","created":{"date-parts":[[2026,7,18]],"date-time":"2026-07-18T20:06:42Z","timestamp":1784405202000},"page":"352-362","update-policy":"https:\/\/doi.org\/10.1007\/springer_crossmark_policy","source":"Crossref","is-referenced-by-count":0,"title":["WTSM-Net: Speech Emotion Recognition Network Combining Local Dynamic Enhancement and Long-range Sequence Modeling"],"prefix":"10.1007","author":[{"given":"Wei","family":"Wei","sequence":"first","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Qibing","family":"Zhao","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Jianxin","family":"Zhang","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"297","published-online":{"date-parts":[[2026,7,19]]},"reference":[{"key":"30_CR1","doi-asserted-by":"publisher","first-page":"1","DOI":"10.1016\/j.neucom.2023.01.002","volume":"528","author":"J de Lope","year":"2023","unstructured":"de Lope, J., Gra\u00f1a, M.: An ongoing review of speech emotion recognition. Neurocomputing. 528, 1\u201311 (2023)","journal-title":"Neurocomputing"},{"issue":"3","key":"30_CR2","doi-asserted-by":"publisher","first-page":"572","DOI":"10.1016\/j.patcog.2010.09.020","volume":"44","author":"M El Ayadi","year":"2011","unstructured":"El Ayadi, M., Kamel, M.S., Karray, F.: Survey on speech emotion recognition: features, classification schemes, and databases. Pattern Recogn. 44(3), 572\u2013587 (2011)","journal-title":"Pattern Recogn."},{"issue":"9\u201310","key":"30_CR3","doi-asserted-by":"publisher","first-page":"1062","DOI":"10.1016\/j.specom.2011.01.011","volume":"53","author":"B Schuller","year":"2011","unstructured":"Schuller, B., Batliner, A., Steidl, S., et al.: Recognising realistic emotions and affect in speech: state of the art and lessons learnt from the first challenge. Speech Comm. 53(9\u201310), 1062\u20131087 (2011)","journal-title":"Speech Comm."},{"key":"30_CR4","first-page":"12449","volume":"33","author":"A Baevski","year":"2020","unstructured":"Baevski, A., Zhou, Y., Mohamed, A., et al.: wav2vec 2.0: a framework for self-supervised learning of speech representations. Adv. Neural Inf. Proces. Syst. 33, 12449\u201312460 (2020)","journal-title":"Adv. Neural Inf. Proces. Syst."},{"key":"30_CR5","doi-asserted-by":"crossref","unstructured":"Pepino, L., Riera, P., Ferrer, L.: Emotion recognition from speech using wav2vec 2.0 embeddings. arXiv preprint https:\/\/arxiv.org\/abs\/2104.03502. (2021)","DOI":"10.21437\/Interspeech.2021-703"},{"issue":"9","key":"30_CR6","doi-asserted-by":"publisher","first-page":"10745","DOI":"10.1109\/TPAMI.2023.3263585","volume":"45","author":"J Wagner","year":"2023","unstructured":"Wagner, J., Triantafyllopoulos, A., Wierstorf, H., et al.: Dawn of the transformer era in speech emotion recognition: closing the valence gap. IEEE Trans. Pattern Anal. Mach. Intell. 45(9), 10745\u201310759 (2023)","journal-title":"IEEE Trans. Pattern Anal. Mach. Intell."},{"key":"30_CR7","doi-asserted-by":"crossref","unstructured":"Park, D.S., Chan, W., Zhang, Y., et al.: SpecAugment: a simple data augmentation method for automatic speech recognition. arXiv preprint https:\/\/arxiv.org\/abs\/1904.08779. (2019)","DOI":"10.21437\/Interspeech.2019-2680"},{"key":"30_CR8","first-page":"3020","volume-title":"Proceeding of ICASSP","author":"Z Peng","year":"2021","unstructured":"Peng, Z., Lu, Y., Pan, S., et al.: Efficient speech emotion recognition using multi-scale CNN and attention. In: Proceeding of ICASSP, pp. 3020\u20133024 (2021)"},{"key":"30_CR9","first-page":"12271","volume-title":"Proceeding of ICASSP","author":"M Li","year":"2024","unstructured":"Li, M., Zheng, Y., Li, D., et al.: MS-SENet: enhancing speech emotion recognition through multi-scale feature fusion with squeeze-and-excitation blocks. In: Proceeding of ICASSP, pp. 12271\u201312275 (2024)"},{"key":"30_CR10","first-page":"11686","volume-title":"Proceeding of ICASSP","author":"Z Yuan","year":"2024","unstructured":"Yuan, Z., Chen, C.L.P., Li, S., et al.: Disentanglement network: disentangle the emotional features from acoustic features for speech emotion recognition. In: Proceeding of ICASSP, pp. 11686\u201311690 (2024)"},{"key":"30_CR11","first-page":"346","volume-title":"Proceeding of Interspeech","author":"W Chen","year":"2022","unstructured":"Chen, W., Xing, X., Xu, X., Pang, J., Du, L.: SpeechFormer: a hierarchical efficient framework incorporating the characteristics of speech. In: Proceeding of Interspeech, pp. 346\u2013350 (2022)"},{"key":"30_CR12","doi-asserted-by":"publisher","first-page":"775","DOI":"10.1109\/TASLP.2023.3235194","volume":"31","author":"W Chen","year":"2023","unstructured":"Chen, W., Xing, X., Xu, X., et al.: SpeechFormer++: a hierarchical efficient framework for paralinguistic speech processing. IEEE\/ACM Trans. Audio Speech Lang. Process. 31, 775\u2013788 (2023)","journal-title":"IEEE\/ACM Trans. Audio Speech Lang. Process."},{"issue":"2","key":"30_CR13","doi-asserted-by":"publisher","DOI":"10.1371\/journal.pone.0318297","volume":"20","author":"N Wang","year":"2025","unstructured":"Wang, N., Yang, D.: Speech emotion recognition using fine-tuned Wav2Vec2.0 and neural controlled differential equations classifier. PLoS One. 20(2), e0318297 (2025)","journal-title":"PLoS One"},{"key":"30_CR14","doi-asserted-by":"crossref","unstructured":"Shi, J., Zhang, Y., Gao, Y.: CLEP-DG: contrastive learning for speech emotion domain generalization via soft prompt tuning. arXiv preprint https:\/\/arxiv.org\/abs\/2507.04048. (2025)","DOI":"10.21437\/Interspeech.2025-1064"},{"key":"30_CR15","volume-title":"Proceeding of Interspeech","author":"J Mai","year":"2024","unstructured":"Mai, J., Xing, X., Chen, W., et al.: DropFormer: a dynamic noise-dropping transformer for speech emotion recognition. In: Proceeding of Interspeech (2024)"},{"key":"30_CR16","first-page":"1","volume-title":"Proceeding of ICASSP","author":"W Chen","year":"2023","unstructured":"Chen, W., Xing, X., Xu, X., Pang, J., Du, L.: DST: deformable speech transformer for emotion recognition. In: Proceeding of ICASSP, pp. 1\u20135 (2023)"},{"key":"30_CR17","first-page":"1","volume-title":"Proceeding of ICASSP","author":"S Chen","year":"2023","unstructured":"Chen, S., Xing, X., Zhang, W., et al.: DWFormer: dynamic window transformer for speech emotion recognition. In: Proceeding of ICASSP, pp. 1\u20135 (2023)"}],"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\/978-981-92-3410-3_30","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2026,7,18]],"date-time":"2026-07-18T20:06:44Z","timestamp":1784405204000},"score":1,"resource":{"primary":{"URL":"https:\/\/link.springer.com\/10.1007\/978-981-92-3410-3_30"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2026,7,19]]},"ISBN":["9789819234097","9789819234103"],"references-count":17,"URL":"https:\/\/doi.org\/10.1007\/978-981-92-3410-3_30","relation":{},"ISSN":["0302-9743","1611-3349"],"issn-type":[{"value":"0302-9743","type":"print"},{"value":"1611-3349","type":"electronic"}],"subject":[],"published":{"date-parts":[[2026,7,19]]},"assertion":[{"value":"19 July 2026","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 content of this article.","order":1,"name":"Ethics","label":"Disclosure of Interests","group":{"name":"EthicsHeading","label":"Ethics"}},{"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":"Toronto","order":3,"name":"conference_city","label":"Conference City","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"Canada","order":4,"name":"conference_country","label":"Conference Country","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"2026","order":5,"name":"conference_year","label":"Conference Year","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"22 July 2026","order":7,"name":"conference_start_date","label":"Conference Start Date","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"26 July 2026","order":8,"name":"conference_end_date","label":"Conference End Date","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"22","order":9,"name":"conference_number","label":"Conference Number","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"icic2026a","order":10,"name":"conference_id","label":"Conference ID","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"http:\/\/www.ic-icc.cn\/2026\/index.htm","order":11,"name":"conference_url","label":"Conference URL","group":{"name":"ConferenceInfo","label":"Conference Information"}}]}}