{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,7,3]],"date-time":"2026-07-03T15:18:01Z","timestamp":1783091881167,"version":"3.54.6"},"reference-count":50,"publisher":"Elsevier BV","license":[{"start":{"date-parts":[[2026,6,1]],"date-time":"2026-06-01T00:00:00Z","timestamp":1780272000000},"content-version":"tdm","delay-in-days":0,"URL":"https:\/\/www.elsevier.com\/tdm\/userlicense\/1.0\/"},{"start":{"date-parts":[[2026,6,1]],"date-time":"2026-06-01T00:00:00Z","timestamp":1780272000000},"content-version":"tdm","delay-in-days":0,"URL":"https:\/\/www.elsevier.com\/legal\/tdmrep-license"},{"start":{"date-parts":[[2026,6,1]],"date-time":"2026-06-01T00:00:00Z","timestamp":1780272000000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-017"},{"start":{"date-parts":[[2026,6,1]],"date-time":"2026-06-01T00:00:00Z","timestamp":1780272000000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-037"},{"start":{"date-parts":[[2026,6,1]],"date-time":"2026-06-01T00:00:00Z","timestamp":1780272000000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-012"},{"start":{"date-parts":[[2026,6,1]],"date-time":"2026-06-01T00:00:00Z","timestamp":1780272000000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2026,6,1]],"date-time":"2026-06-01T00:00:00Z","timestamp":1780272000000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-004"}],"funder":[{"DOI":"10.13039\/501100001809","name":"National Natural Science Foundation of China","doi-asserted-by":"publisher","award":["62072290"],"award-info":[{"award-number":["62072290"]}],"id":[{"id":"10.13039\/501100001809","id-type":"DOI","asserted-by":"publisher"}]},{"DOI":"10.13039\/501100001809","name":"National Natural Science Foundation of China","doi-asserted-by":"publisher","award":["62573277"],"award-info":[{"award-number":["62573277"]}],"id":[{"id":"10.13039\/501100001809","id-type":"DOI","asserted-by":"publisher"}]}],"content-domain":{"domain":["elsevier.com","sciencedirect.com"],"crossmark-restriction":true},"short-container-title":["Speech Communication"],"published-print":{"date-parts":[[2026,6]]},"DOI":"10.1016\/j.specom.2026.103409","type":"journal-article","created":{"date-parts":[[2026,4,23]],"date-time":"2026-04-23T15:17:05Z","timestamp":1776957425000},"page":"103409","update-policy":"https:\/\/doi.org\/10.1016\/elsevier_cm_policy","source":"Crossref","is-referenced-by-count":0,"special_numbering":"C","title":["Joint acoustic\u2013semantic alignment network for advanced speech emotion recognition"],"prefix":"10.1016","volume":"181","author":[{"ORCID":"https:\/\/orcid.org\/0009-0000-3581-7537","authenticated-orcid":false,"given":"Yihong","family":"Meng","sequence":"first","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-5727-7834","authenticated-orcid":false,"given":"Hong","family":"Wang","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Yanshen","family":"Sun","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Aijun","family":"Li","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"78","reference":[{"key":"10.1016\/j.specom.2026.103409_b1","doi-asserted-by":"crossref","first-page":"1533","DOI":"10.1109\/TASLP.2014.2339736","article-title":"Convolutional neural networks for speech recognition","author":"Abdel-Hamid","year":"2014","journal-title":"IEEE\/ACM Trans. Audio, Speech, Lang. Process."},{"key":"10.1016\/j.specom.2026.103409_b2","doi-asserted-by":"crossref","first-page":"433","DOI":"10.1002\/wics.101","article-title":"Principal component analysis","author":"Abdi","year":"2010","journal-title":"WIREs Comput. Stat."},{"key":"10.1016\/j.specom.2026.103409_b3","doi-asserted-by":"crossref","first-page":"82","DOI":"10.1016\/j.inffus.2019.12.012","article-title":"Explainable artificial intelligence (XAI): Concepts, taxonomies, opportunities and challenges toward responsible AI","author":"Barredo Arrieta","year":"2020","journal-title":"Inf. Fusion"},{"key":"10.1016\/j.specom.2026.103409_b4","doi-asserted-by":"crossref","unstructured":"Bie, F., Wang, D., Zheng, T.F., Tejedor, J., Chen, R., 2013. Emotional adaptive training for speaker verification. In: Asia-Pacific Signal and Information Processing Association Annual Summit and Conference. pp. 1\u20134.","DOI":"10.1109\/APSIPA.2013.6694123"},{"key":"10.1016\/j.specom.2026.103409_b5","doi-asserted-by":"crossref","first-page":"335","DOI":"10.1007\/s10579-008-9076-6","article-title":"IEMOCAP: interactive emotional dyadic motion capture database","author":"Busso","year":"2008","journal-title":"Lang. Resour. Eval."},{"key":"10.1016\/j.specom.2026.103409_b6","doi-asserted-by":"crossref","unstructured":"Chen, T., Guestrin, C., 2016. XGBoost: A Scalable Tree Boosting System. In: Proceedings of the 22nd ACM SIGKDD International Conference on Knowledge Discovery and Data Mining. pp. 785\u2013794.","DOI":"10.1145\/2939672.2939785"},{"key":"10.1016\/j.specom.2026.103409_b7","doi-asserted-by":"crossref","unstructured":"Chen, W., Xing, X., Xu, X., Yang, J., Pang, J., 2022. Key-Sparse Transformer for Multimodal Speech Emotion Recognition. In: IEEE International Conference on Acoustics, Speech and Signal Processing. pp. 6897\u20136901.","DOI":"10.1109\/ICASSP43922.2022.9746598"},{"key":"10.1016\/j.specom.2026.103409_b8","series-title":"Interspeech","first-page":"3301","article-title":"Multi-stream attention-based BLSTM with feature segmentation for speech emotion recognition","author":"Chiba","year":"2020"},{"key":"10.1016\/j.specom.2026.103409_b9","doi-asserted-by":"crossref","unstructured":"Choi, W.Y., Song, K.Y., Lee, C.W., 2018. Convolutional Attention Networks for Multimodal Emotion Recognition from Speech and Text Data. In: Proceedings of Grand Challenge and Workshop on Human Multimodal Language. pp. 28\u201334.","DOI":"10.18653\/v1\/W18-3304"},{"key":"10.1016\/j.specom.2026.103409_b10","series-title":"Empirical evaluation of gated recurrent neural networks on sequence modeling","author":"Chung","year":"2014"},{"key":"10.1016\/j.specom.2026.103409_b11","doi-asserted-by":"crossref","first-page":"273","DOI":"10.1023\/A:1022627411411","article-title":"Support-vector networks","author":"Cortes","year":"1995","journal-title":"Mach. Learn."},{"key":"10.1016\/j.specom.2026.103409_b12","doi-asserted-by":"crossref","unstructured":"Devlin, J., Chang, M.-W., Lee, K., Toutanova, K., 2019. BERT: Pre-training of Deep Bidirectional Transformers for Language Understanding. In: Proceedings of the 2021 Conference of the North American Chapter of the Association for Computational Linguistics: Human Language Technologies. pp. 4171\u20134186.","DOI":"10.18653\/v1\/N19-1423"},{"key":"10.1016\/j.specom.2026.103409_b13","doi-asserted-by":"crossref","first-page":"179","DOI":"10.1111\/j.1469-1809.1936.tb02137.x","article-title":"The use of multiple measurements in taxonomic problems","author":"FISHER","year":"1936","journal-title":"Ann. Eugen."},{"key":"10.1016\/j.specom.2026.103409_b14","doi-asserted-by":"crossref","unstructured":"Gao, Y., Liu, J., Wang, L., Dang, J., 2021. Domain-Adversarial Autoencoder with Attention Based Feature Level Fusion for Speech Emotion Recognition. In: IEEE International Conference on Acoustics, Speech and Signal Processing. pp. 6314\u20136318.","DOI":"10.1109\/ICASSP39728.2021.9413710"},{"key":"10.1016\/j.specom.2026.103409_b15","doi-asserted-by":"crossref","unstructured":"Gu, Y., Chen, S., Marsic, I., 2018. Deep Mul Timodal Learning for Emotion Recognition in Spoken Language. In: IEEE International Conference on Acoustics, Speech and Signal Processing. pp. 5079\u20135083.","DOI":"10.1109\/ICASSP.2018.8462440"},{"key":"10.1016\/j.specom.2026.103409_b16","doi-asserted-by":"crossref","unstructured":"Hou, M., Zhang, Z., Lu, G., 2022. Multi-Modal Emotion Recognition with Self-Guided Modality Calibration. In: IEEE International Conference on Acoustics, Speech and Signal Processing. pp. 4688\u20134692.","DOI":"10.1109\/ICASSP43922.2022.9747859"},{"key":"10.1016\/j.specom.2026.103409_b17","doi-asserted-by":"crossref","DOI":"10.1016\/j.eswa.2023.122946","article-title":"MSER: Multimodal speech emotion recognition using cross-attention with deep fusion","author":"Khan","year":"2024","journal-title":"Expert Syst. Appl."},{"key":"10.1016\/j.specom.2026.103409_b18","series-title":"Interspeech","first-page":"1748","article-title":"Towards the explainability of multimodal speech emotion recognition","author":"Kumar","year":"2021"},{"key":"10.1016\/j.specom.2026.103409_b19","doi-asserted-by":"crossref","first-page":"2278","DOI":"10.1109\/5.726791","article-title":"Gradient-based learning applied to document recognition","author":"LeCun","year":"1998","journal-title":"Proc. IEEE"},{"key":"10.1016\/j.specom.2026.103409_b20","series-title":"Interspeech","first-page":"3087","article-title":"An attention pooling based representation learning method for speech emotion recognition","author":"Li","year":"2018"},{"key":"10.1016\/j.specom.2026.103409_b21","series-title":"Interspeech","first-page":"2013","article-title":"Context-aware multimodal fusion for emotion recognition","author":"Li","year":"2022"},{"key":"10.1016\/j.specom.2026.103409_b22","doi-asserted-by":"crossref","unstructured":"Lin, Y.-L., Wei, G., 2005. Speech emotion recognition based on HMM and SVM. In: International Conference on Machine Learning and Cybernetics. pp. 4898\u20134901.","DOI":"10.1109\/ICMLC.2005.1527805"},{"key":"10.1016\/j.specom.2026.103409_b23","series-title":"Interspeech","first-page":"379","article-title":"Group gated fusion on attention-based bidirectional alignment for multimodal emotion recognition","author":"Liu","year":"2020"},{"key":"10.1016\/j.specom.2026.103409_b24","unstructured":"Lundberg, S.M., Lee, S.-I., 2017. A unified approach to interpreting model predictions. In: Proceedings of the 31st International Conference on Neural Information Processing Systems. pp. 4768\u20134777."},{"key":"10.1016\/j.specom.2026.103409_b25","series-title":"IEEE International Conference on Acoustics, Speech and Signal Processing","first-page":"1","article-title":"Cross-modal fusion techniques for utterance-level emotion recognition from text and speech","author":"Luo","year":"2023"},{"key":"10.1016\/j.specom.2026.103409_b26","doi-asserted-by":"crossref","unstructured":"Luo, D., Zou, Y., Huang, D., 2017. Speech emotion recognition via ensembling neural networks. In: Asia-Pacific Signal and Information Processing Association Annual Summit and Conference. pp. 1351\u20131355.","DOI":"10.1109\/APSIPA.2017.8282242"},{"key":"10.1016\/j.specom.2026.103409_b27","doi-asserted-by":"crossref","first-page":"2203","DOI":"10.1109\/TMM.2014.2360798","article-title":"Learning salient features for speech emotion recognition using convolutional neural networks","author":"Mao","year":"2014","journal-title":"IEEE Trans. Multimed."},{"key":"10.1016\/j.specom.2026.103409_b28","doi-asserted-by":"crossref","DOI":"10.1016\/j.inffus.2023.101869","article-title":"A review of deep learning techniques for speech processing","author":"Mehrish","year":"2023","journal-title":"Inf. Fusion"},{"key":"10.1016\/j.specom.2026.103409_b29","doi-asserted-by":"crossref","unstructured":"Mirsamadi, S., Barsoum, E., Zhang, C., 2017. Automatic speech emotion recognition using recurrent neural networks with local attention. In: IEEE International Conference on Acoustics, Speech and Signal Processing. pp. 2227\u20132231.","DOI":"10.1109\/ICASSP.2017.7952552"},{"key":"10.1016\/j.specom.2026.103409_b30","first-page":"63","article-title":"An overview of independent component analysis and its applications","author":"Naik","year":"2011","journal-title":"Informatica"},{"key":"10.1016\/j.specom.2026.103409_b31","doi-asserted-by":"crossref","unstructured":"Pardede, H.F., Zilvan, V., Krisnandi, D., Heryana, A., Kusumo, R.B.S., 2019. Generalized Filter-bank Features for Robust Speech Recognition Against Reverberation. In: International Conference on Computer, Control, Informatics and Its Applications. pp. 19\u201324.","DOI":"10.1109\/IC3INA48034.2019.8949593"},{"key":"10.1016\/j.specom.2026.103409_b32","doi-asserted-by":"crossref","unstructured":"Poria, S., Hazarika, D., Majumder, N., Naik, G., Cambria, E., Mihalcea, R., 2019. MELD: A Multimodal Multi-Party Dataset for Emotion Recognition in Conversations. In: Proceedings of the 57th Annual Meeting of the Association for Computational Linguistics. pp. 527\u2013536.","DOI":"10.18653\/v1\/P19-1050"},{"key":"10.1016\/j.specom.2026.103409_b33","doi-asserted-by":"crossref","first-page":"257","DOI":"10.1109\/5.18626","article-title":"A tutorial on hidden Markov models and selected applications in speech recognition","author":"Rabiner","year":"1989","journal-title":"Proc. IEEE"},{"key":"10.1016\/j.specom.2026.103409_b34","doi-asserted-by":"crossref","DOI":"10.1016\/j.specom.2025.103342","article-title":"A review on speech emotion recognition for low-resource and indigenous languages","author":"Rathnayake","year":"2026","journal-title":"Speech Commun."},{"key":"10.1016\/j.specom.2026.103409_b35","series-title":"Interspeech","first-page":"1089","article-title":"Efficient emotion recognition from speech using deep learning on spectrograms","author":"Satt","year":"2017"},{"key":"10.1016\/j.specom.2026.103409_b36","doi-asserted-by":"crossref","unstructured":"Sefara, T.J., Mokgonyane, T.B., 2020. Emotional Speaker Recognition based on Machine and Deep Learning. In: 2nd International Multidisciplinary Information Technology and Engineering Conference. pp. 1\u20138.","DOI":"10.1109\/IMITEC50163.2020.9334138"},{"key":"10.1016\/j.specom.2026.103409_b37","doi-asserted-by":"crossref","DOI":"10.1016\/j.knosys.2021.107316","article-title":"A multimodal hierarchical approach to speech emotion recognition from audio and text","author":"Singh","year":"2021","journal-title":"Knowl.-Based Syst."},{"key":"10.1016\/j.specom.2026.103409_b38","doi-asserted-by":"crossref","unstructured":"Stauffer, C., Grimson, W., 1999. Adaptive background mixture models for real-time tracking. In: IEEE Computer Society Conference on Computer Vision and Pattern Recognition. pp. 246\u2013252.","DOI":"10.1109\/CVPR.1999.784637"},{"key":"10.1016\/j.specom.2026.103409_b39","doi-asserted-by":"crossref","unstructured":"Sun, L., Liu, B., Tao, J., Lian, Z., 2021. Multimodal Cross- and Self-Attention Network for Speech Emotion Recognition. In: IEEE International Conference on Acoustics, Speech and Signal Processing. pp. 4275\u20134279.","DOI":"10.1109\/ICASSP39728.2021.9414654"},{"key":"10.1016\/j.specom.2026.103409_b40","doi-asserted-by":"crossref","unstructured":"Tzirakis, P., Zhang, J., Schuller, B.W., 2018. End-to-End Speech Emotion Recognition Using Deep Neural Networks. In: IEEE International Conference on Acoustics, Speech and Signal Processing. pp. 5089\u20135093.","DOI":"10.1109\/ICASSP.2018.8462677"},{"key":"10.1016\/j.specom.2026.103409_b41","series-title":"Attention is all you need","author":"Vaswani","year":"2017"},{"key":"10.1016\/j.specom.2026.103409_b42","series-title":"Long short-term memory RNN","author":"Venner\u00f8d","year":"2021"},{"key":"10.1016\/j.specom.2026.103409_b43","doi-asserted-by":"crossref","unstructured":"Wang, S., Ma, Y., Ding, Y., 2023. Exploring Complementary Features in Multi-Modal Speech Emotion Recognition. In: IEEE International Conference on Acoustics, Speech and Signal Processing. pp. 1\u20135.","DOI":"10.1109\/ICASSP49357.2023.10096709"},{"key":"10.1016\/j.specom.2026.103409_b44","doi-asserted-by":"crossref","unstructured":"Wu, Z., Lu, Y., Dai, X., 2023. An Empirical Study and Improvement for Speech Emotion Recognition. In: IEEE International Conference on Acoustics, Speech and Signal Processing. pp. 1\u20135.","DOI":"10.1109\/ICASSP49357.2023.10095042"},{"key":"10.1016\/j.specom.2026.103409_b45","doi-asserted-by":"crossref","first-page":"11","DOI":"10.1016\/j.specom.2020.03.005","article-title":"Speech emotion recognition using fusion of three multi-task learning-based classifiers: HSF-DNN, MS-CNN and LLD-rnn","author":"Yao","year":"2020","journal-title":"Speech Commun."},{"key":"10.1016\/j.specom.2026.103409_b46","first-page":"6","article-title":"Speech emotion recognition using support vector machine","author":"Yashpalsing Chavhan","year":"2010","journal-title":"Int. J. Comput. Appl."},{"key":"10.1016\/j.specom.2026.103409_b47","series-title":"Recurrent neural network regularization","author":"Zaremba","year":"2014"},{"key":"10.1016\/j.specom.2026.103409_b48","doi-asserted-by":"crossref","unstructured":"Zhang, R., Wu, H., Li, W., Jiang, D., Zou, W., Li, X., 2021. Transformer based unsupervised pre-training for acoustic representation learning. In: IEEE International Conference on Acoustics, Speech and Signal Processing. pp. 6933\u20136937.","DOI":"10.1109\/ICASSP39728.2021.9414996"},{"key":"10.1016\/j.specom.2026.103409_b49","doi-asserted-by":"crossref","DOI":"10.1016\/j.iot.2024.101069","article-title":"A multimodal teacher speech emotion recognition method in the smart classroom","author":"Zhao","year":"2024","journal-title":"Internet Things"},{"key":"10.1016\/j.specom.2026.103409_b50","doi-asserted-by":"crossref","unstructured":"Zou, H., Si, Y., Chen, C., Rajan, D., Chng, E.S., 2022. Speech Emotion Recognition with Co-Attention Based Multi-Level Acoustic Information. In: IEEE International Conference on Acoustics, Speech and Signal Processing. pp. 7367\u20137371.","DOI":"10.1109\/ICASSP43922.2022.9747095"}],"container-title":["Speech Communication"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/api.elsevier.com\/content\/article\/PII:S0167639326000579?httpAccept=text\/xml","content-type":"text\/xml","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/api.elsevier.com\/content\/article\/PII:S0167639326000579?httpAccept=text\/plain","content-type":"text\/plain","content-version":"vor","intended-application":"text-mining"}],"deposited":{"date-parts":[[2026,7,3]],"date-time":"2026-07-03T14:25:02Z","timestamp":1783088702000},"score":1,"resource":{"primary":{"URL":"https:\/\/linkinghub.elsevier.com\/retrieve\/pii\/S0167639326000579"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2026,6]]},"references-count":50,"alternative-id":["S0167639326000579"],"URL":"https:\/\/doi.org\/10.1016\/j.specom.2026.103409","relation":{},"ISSN":["0167-6393"],"issn-type":[{"value":"0167-6393","type":"print"}],"subject":[],"published":{"date-parts":[[2026,6]]},"assertion":[{"value":"Elsevier","name":"publisher","label":"This article is maintained by"},{"value":"Joint acoustic\u2013semantic alignment network for advanced speech emotion recognition","name":"articletitle","label":"Article Title"},{"value":"Speech Communication","name":"journaltitle","label":"Journal Title"},{"value":"https:\/\/doi.org\/10.1016\/j.specom.2026.103409","name":"articlelink","label":"CrossRef DOI link to publisher maintained version"},{"value":"article","name":"content_type","label":"Content Type"},{"value":"\u00a9 2026 Elsevier B.V. All rights are reserved, including those for text and data mining, AI training, and similar technologies.","name":"copyright","label":"Copyright"}],"article-number":"103409"}}