{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,6,26]],"date-time":"2026-06-26T09:48:15Z","timestamp":1782467295359,"version":"3.54.5"},"publisher-location":"Cham","reference-count":65,"publisher":"Springer Nature Switzerland","isbn-type":[{"value":"9783032295477","type":"print"},{"value":"9783032295484","type":"electronic"}],"license":[{"start":{"date-parts":[[2026,1,1]],"date-time":"2026-01-01T00:00:00Z","timestamp":1767225600000},"content-version":"tdm","delay-in-days":0,"URL":"https:\/\/www.springernature.com\/gp\/researchers\/text-and-data-mining"},{"start":{"date-parts":[[2026,1,1]],"date-time":"2026-01-01T00:00:00Z","timestamp":1767225600000},"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":[[2026]]},"DOI":"10.1007\/978-3-032-29548-4_16","type":"book-chapter","created":{"date-parts":[[2026,6,26]],"date-time":"2026-06-26T09:20:12Z","timestamp":1782465612000},"page":"238-256","update-policy":"https:\/\/doi.org\/10.1007\/springer_crossmark_policy","source":"Crossref","is-referenced-by-count":0,"title":["A Multimodal Fusion Framework for Speech Emotion Recognition in Human-AI Interaction"],"prefix":"10.1007","author":[{"given":"Nisal Thiwanka","family":"Nandasena","sequence":"first","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Supunmali","family":"Ahangama","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Dulani","family":"Jayasuriya","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"297","published-online":{"date-parts":[[2026,6,27]]},"reference":[{"key":"16_CR1","doi-asserted-by":"publisher","unstructured":"Gladys, A.A., Vetriselvi, V.: Survey on multimodal approaches to emotion recognition. Neurocomputing 556, 126693 (2023). https:\/\/doi.org\/10.1016\/j.neucom.2023.126693","DOI":"10.1016\/j.neucom.2023.126693"},{"key":"16_CR2","doi-asserted-by":"publisher","unstructured":"Hu, G., et al.: Recent Trends of Multimodal Affective Computing: A Survey from NLP Perspective, 2024. arXiv: arXiv:2409.07388. https:\/\/doi.org\/10.48550\/arXiv.2409.07388","DOI":"10.48550\/arXiv.2409.07388"},{"key":"16_CR3","doi-asserted-by":"publisher","unstructured":"Wang, X., Li, X., Yin, Z., Wu, Y., Jia, L.: Emotional Intelligence of Large Language Models, 2023. arXiv: arXiv:2307.09042. https:\/\/doi.org\/10.48550\/arXiv.2307.09042","DOI":"10.48550\/arXiv.2307.09042"},{"key":"16_CR4","doi-asserted-by":"publisher","unstructured":"Klapach, N.: The Comparative Emotional Capabilities of Five Popular Large Language Models, 2023. https:\/\/doi.org\/10.58445\/rars.645","DOI":"10.58445\/rars.645"},{"key":"16_CR5","doi-asserted-by":"publisher","unstructured":"Devlin, J., Chang, M.-W., Lee, K., Toutanova, K.: BERT: Pre-training of Deep Bidirectional Transformers for Language Understanding, 2018. arXiv. https:\/\/doi.org\/10.48550\/ARXIV.1810.04805","DOI":"10.48550\/ARXIV.1810.04805"},{"key":"16_CR6","doi-asserted-by":"publisher","unstructured":"Baevski, A., Zhou, H., Mohamed, A., Auli, M.: Wav2vec 2.0: A Framework for Self-Supervised Learning of Speech Representations, 2020. arXiv. https:\/\/doi.org\/10.48550\/ARXIV.2006.11477","DOI":"10.48550\/ARXIV.2006.11477"},{"key":"16_CR7","doi-asserted-by":"publisher","unstructured":"Pepino, L., Riera, P., Ferrer, L., Gravano, A.: Fusion approaches for emotion recognition from speech using acoustic and text-based features. In: ICASSP 2020 - 2020 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP), May 2020, pp. 6484\u20136488, 2020. https:\/\/doi.org\/10.1109\/ICASSP40776.2020.9054709","DOI":"10.1109\/ICASSP40776.2020.9054709"},{"key":"16_CR8","doi-asserted-by":"publisher","unstructured":"Li, Q., Wu, C., Zheng, K., Wang, Z.: Hierarchical Transformer Network for Utterance-level Emotion Recognition, 2020. arXiv: arXiv:2002.07551. https:\/\/doi.org\/10.48550\/arXiv.2002.07551","DOI":"10.48550\/arXiv.2002.07551"},{"issue":"7","key":"16_CR9","doi-asserted-by":"publisher","first-page":"418","DOI":"10.3390\/biomimetics10070418","volume":"10","author":"Y Wu","year":"2025","unstructured":"Wu, Y., Mi, Q., Gao, T.: A comprehensive review of multimodal emotion recognition: techniques, challenges, and future directions. Biomimetics 10(7), 418 (2025). https:\/\/doi.org\/10.3390\/biomimetics10070418","journal-title":"Biomimetics"},{"key":"16_CR10","doi-asserted-by":"publisher","unstructured":"Geetha, A.V., Mala, T., Priyanka, D., Uma, E.J.I.F.,: Multimodal emotion recognition with deep learning: advancements, challenges, and future directions. Inf. Fusion 105, 102218 (2024). https:\/\/doi.org\/10.1016\/j.inffus.2023.102218","DOI":"10.1016\/j.inffus.2023.102218"},{"key":"16_CR11","doi-asserted-by":"publisher","unstructured":"Belikova, J., Kosenko, D.: DeepPavlov at SemEval-2024 task 3: multimodal large language models in emotion reasoning. In: Proceedings of the 18th International Workshop on Semantic Evaluation (SemEval-2024), Mexico City, Mexico: Association for Computational Linguistics, pp. 1747\u20131757, 2024. https:\/\/doi.org\/10.18653\/v1\/2024.semeval-1.249","DOI":"10.18653\/v1\/2024.semeval-1.249"},{"key":"16_CR12","doi-asserted-by":"publisher","unstructured":"Lian, Z., et al.: Explainable Multimodal Emotion Recognition, 2023. arXiv. https:\/\/doi.org\/10.48550\/ARXIV.2306.15401","DOI":"10.48550\/ARXIV.2306.15401"},{"key":"16_CR13","doi-asserted-by":"publisher","unstructured":"Dutta, S., Ganapathy, S.: LLM supervised Pre-training for Multimodal Emotion Recognition in Conversations, 2025. arXiv. https:\/\/doi.org\/10.48550\/ARXIV.2501.11468","DOI":"10.48550\/ARXIV.2501.11468"},{"key":"16_CR14","doi-asserted-by":"publisher","unstructured":"Cheng, H., et al.: VAEmo: efficient representation learning for visual-audio emotion with knowledge injection. In: Proceedings of the 33rd ACM International Conference on Multimedia, Oct., pp. 5547\u20135556, 2025. https:\/\/doi.org\/10.1145\/3746027.3754924","DOI":"10.1145\/3746027.3754924"},{"key":"16_CR15","doi-asserted-by":"publisher","unstructured":"Praveen, R.G., et al.: A Joint Cross-Attention Model for Audio-Visual Fusion in Dimensional Emotion Recognition, 2022. arXiv. https:\/\/doi.org\/10.48550\/ARXIV.2203.14779","DOI":"10.48550\/ARXIV.2203.14779"},{"key":"16_CR16","doi-asserted-by":"publisher","first-page":"103976","DOI":"10.1109\/ACCESS.2024.3430850","volume":"12","author":"S Kalateh","year":"2024","unstructured":"Kalateh, S., Estrada-Jimenez, L.A., Nikghadam-Hojjati, S., Barata, J.: A systematic review on multimodal emotion recognition: building blocks, current state, applications, and challenges. IEEE Access 12, 103976\u2013104019 (2024). https:\/\/doi.org\/10.1109\/ACCESS.2024.3430850","journal-title":"IEEE Access"},{"key":"16_CR17","doi-asserted-by":"publisher","unstructured":"J. Kyung, Heo, S., Chang, J.-H.: Enhancing multimodal emotion recognition through ASR error compensation and LLM Fine-tuning. In: Interspeech 2024, ISCA, 2024, pp. 4683\u20134687pp.. A, 2024. https:\/\/doi.org\/10.21437\/Interspeech.2024-2364","DOI":"10.21437\/Interspeech.2024-2364"},{"key":"16_CR18","doi-asserted-by":"publisher","unstructured":"Gandhi, K., Adhvaryu, S.. Poria, Cambria, E., Hussain, A.: Multimodal sentiment analysis: a systematic review of history, datasets, multimodal fusion methods, applications, challenges and future directions. Inf. Fusion 91, 424\u2013444 (2023). https:\/\/doi.org\/10.1016\/j.inffus.2022.09.025","DOI":"10.1016\/j.inffus.2022.09.025"},{"key":"16_CR19","doi-asserted-by":"publisher","unstructured":"Poria, S., Hazarika, D., Majumder, N., Naik, G., Cambria, E., Mihalcea, R.: MELD: a multimodal multi-party dataset for emotion recognition in conversations, 2018. arXiv. https:\/\/doi.org\/10.48550\/ARXIV.1810.02508","DOI":"10.48550\/ARXIV.1810.02508"},{"key":"16_CR20","doi-asserted-by":"publisher","unstructured":"Priyasad, D., Fernando, T., Denman, S., Fookes, C., Sridharan, S.: Attention Driven Fusion for Multi-Modal Emotion Recognition, 2020. arXiv: arXiv:2009.10991. https:\/\/doi.org\/10.48550\/arXiv.2009.10991","DOI":"10.48550\/arXiv.2009.10991"},{"key":"16_CR21","doi-asserted-by":"publisher","unstructured":"Nouisser, N. Khediri, M.K., Charfi, F.: ATFSC: audio-text fusion for sentiment classification. In: Proceedings of the 17th International Conference on Agents and Artificial Intelligence, Porto, Portugal: SCITEPRESS - Science and Technology Publications, pp. 750\u2013757, 2025. https:\/\/doi.org\/10.5220\/0013178300003890","DOI":"10.5220\/0013178300003890"},{"key":"16_CR22","doi-asserted-by":"publisher","unstructured":"Cathy, J., Pradeepkumar, S.: Enhancing Emotional Intelligence in LLM Responses Using Speech Emotion Recognition, 2025. Preprints. https:\/\/doi.org\/10.36227\/techrxiv.174123778.82557359\/v1","DOI":"10.36227\/techrxiv.174123778.82557359\/v1"},{"key":"16_CR23","doi-asserted-by":"publisher","unstructured":"Xu, Y., Zhou, Y., Cai, Y., Xie, J., Ye, R., Wu, Z.: Multimodal emotion captioning using large language model with prompt engineering. In: Proceedings of the 2nd International Workshop on Multimodal and Responsible Affective Computing, Melbourne VIC Australia: ACM, Oct. 2024, pp. 104\u2013109 (2024). https:\/\/doi.org\/10.1145\/3689092.3689403","DOI":"10.1145\/3689092.3689403"},{"key":"16_CR24","doi-asserted-by":"publisher","first-page":"1183132","DOI":"10.3389\/fnins.2023.1183132","volume":"17","author":"F Li","year":"2023","unstructured":"Li, F., Luo, J., Wang, L., Liu, W., Sang, X.: GCF2-Net: global-aware cross-modal feature fusion network for speech emotion recognition. Front. Neurosci. 17, 1183132 (2023). https:\/\/doi.org\/10.3389\/fnins.2023.1183132","journal-title":"Front. Neurosci."},{"issue":"10","key":"16_CR25","doi-asserted-by":"publisher","first-page":"1440","DOI":"10.3390\/e25101440","volume":"25","author":"H Lian","year":"2023","unstructured":"Lian, H., Lu, C., Li, S., Zhao, Y., Tang, C., Zong, Y.: A survey of deep learning-based multimodal emotion recognition: speech, text, and face. Entropy 25(10), 1440 (2023). https:\/\/doi.org\/10.3390\/e25101440","journal-title":"Entropy"},{"issue":"1","key":"16_CR26","doi-asserted-by":"publisher","first-page":"34","DOI":"10.1111\/j.1467-9280.1992.tb00253.x","volume":"3","author":"P Ekman","year":"1992","unstructured":"Ekman, P.: Facial expressions of emotion: new findings, new questions. Psychol. Sci. 3(1), 34\u201338 (1992). https:\/\/doi.org\/10.1111\/j.1467-9280.1992.tb00253.x","journal-title":"Psychol. Sci."},{"key":"16_CR27","doi-asserted-by":"publisher","unstructured":"Boateng, G.: Towards real-time multimodal emotion recognition among couples. In: Proceedings of the 2020 International Conference on Multimodal Interaction. Association for Computing Machinery, Virtual Event, Netherlands, pp. 748\u2013753, 2020. https:\/\/doi.org\/10.1145\/3382507.3421154","DOI":"10.1145\/3382507.3421154"},{"key":"16_CR28","unstructured":"Eleftheriou, Koromilas, P: Automatic assessment of speaking skills using aural and textual information. In: Proceedings of the 4th \u2026 2021 - Aclanthologyorg"},{"key":"16_CR29","doi-asserted-by":"publisher","unstructured":"Bayerl, S.P., Tammewar, A., Riedhammer, K., Riccardi, G.: Detecting Emotion Carriers by Combining Acoustic and Lexical Representations, 2021. arXiv: arXiv:2112.06603. https:\/\/doi.org\/10.48550\/arXiv.2112.06603","DOI":"10.48550\/arXiv.2112.06603"},{"key":"16_CR30","doi-asserted-by":"publisher","first-page":"125538","DOI":"10.1109\/ACCESS.2022.3225684","volume":"10","author":"S Kakuba","year":"2022","unstructured":"Kakuba, S., Poulose, A., Han, D.S.: Deep learning-based speech emotion recognition using multi-level fusion of concurrent features. IEEE Access 10, 125538\u2013125551 (2022). https:\/\/doi.org\/10.1109\/ACCESS.2022.3225684","journal-title":"IEEE Access"},{"issue":"1","key":"16_CR31","doi-asserted-by":"publisher","first-page":"951","DOI":"10.1007\/s40747-022-00841-3","volume":"9","author":"Y Xu","year":"2023","unstructured":"Xu, Y., Su, H., Ma, G., Liu, X.: A novel dual-modal emotion recognition algorithm with fusing hybrid features of audio signal and speech context. Complex Intell. Syst. 9(1), 951\u2013963 (2023). https:\/\/doi.org\/10.1007\/s40747-022-00841-3","journal-title":"Complex Intell. Syst."},{"key":"16_CR32","doi-asserted-by":"publisher","unstructured":"Porjazovski, D., Getman, Y., Gr\u00f3sz, T,. Kurimo, M.: Advancing audio emotion and intent recognition with large pre-trained models and Bayesian inference. In: Proceedings of the 31st ACM International Conference on Multimedia. Association for Computing Machinery, Ottawa ON, Canada, pp. 9477\u20139481, 2023. https:\/\/doi.org\/10.1145\/3581783.3612848","DOI":"10.1145\/3581783.3612848"},{"key":"16_CR33","doi-asserted-by":"publisher","unstructured":"Rudd, D.H., Huo, H., Islam, M.R., Xu, G.: Churn Prediction via Multimodal Fusion Learning: Integrating Customer Financial Literacy, Voice, and Behavioral Data, 2023. arXiv: arXiv:2312.01301. https:\/\/doi.org\/10.48550\/arXiv.2312.01301","DOI":"10.48550\/arXiv.2312.01301"},{"key":"16_CR34","doi-asserted-by":"publisher","unstructured":"Luo, J., Phan, H., Reiss, J.: Cross-modal fusion techniques for utterance-level emotion recognition from text and speech, 2023. arXiv: arXiv:2302.02447. https:\/\/doi.org\/10.48550\/arXiv.2302.02447","DOI":"10.48550\/arXiv.2302.02447"},{"issue":"2","key":"16_CR35","doi-asserted-by":"publisher","first-page":"1365","DOI":"10.1007\/s11760-023-02845-z","volume":"18","author":"S Mehra","year":"2024","unstructured":"Mehra, S., Ranga, V., Agarwal, R.: Improving speech command recognition through decision-level fusion of deep filtered speech cues. Signal Image Video Process. 18(2), 1365\u20131373 (2024). https:\/\/doi.org\/10.1007\/s11760-023-02845-z","journal-title":"Signal Image Video Process."},{"key":"16_CR36","doi-asserted-by":"publisher","unstructured":"Deschamps-Berger, T., Lamel, L., Devillers, L.: Investigating transformer encoders and fusion strategies for speech emotion recognition in emergency call center conversations. In: Companion Publication of the 2022 International Conference on Multimodal Interaction. Association for Computing Machinery, Bengaluru, India, pp. 144\u2013153, 2022. https:\/\/doi.org\/10.1145\/3536220.3558038","DOI":"10.1145\/3536220.3558038"},{"key":"16_CR37","doi-asserted-by":"publisher","unstructured":"Tran, T., et al.: Multimodal analysis and assessment of therapist empathy in motivational interviews. In: Proceedings of the 25th International Conference on Multimodal Interaction. Association for Computing Machinery, Paris, France, pp. 406\u2013415, 2023. https:\/\/doi.org\/10.1145\/3577190.3614105","DOI":"10.1145\/3577190.3614105"},{"key":"16_CR38","doi-asserted-by":"publisher","unstructured":"Tafti, Z.D., BabaAli, B.: Audio-Textual Emotion Recognition using Pre-trained models: Investigating Various Representations and Fusion Techniques, 2024. In Review. https:\/\/doi.org\/10.21203\/rs.3.rs-4963739\/v1","DOI":"10.21203\/rs.3.rs-4963739\/v1"},{"issue":"9","key":"16_CR39","doi-asserted-by":"publisher","first-page":"225","DOI":"10.1007\/s10462-024-10869-1","volume":"57","author":"N-C Ristea","year":"2024","unstructured":"Ristea, N.-C., Anghel, A., Ionescu, R.T.: Cascaded cross-modal transformer for audio\u2013textual classification. Artif. Intell. Rev. 57(9), 225 (2024). https:\/\/doi.org\/10.1007\/s10462-024-10869-1","journal-title":"Artif. Intell. Rev."},{"key":"16_CR40","doi-asserted-by":"publisher","unstructured":"Jing, Y., Zhao, X.: DQ-Former: querying transformer with dynamic modality priority for cognitive-aligned multimodal emotion recognition in conversation. In: Proceedings of the 32nd ACM International Conference on Multimedia. Association for Computing Machinery, Melbourne VIC, Australia, pp. 4795\u20134804, 2024. https:\/\/doi.org\/10.1145\/3664647.3681599","DOI":"10.1145\/3664647.3681599"},{"issue":"1","key":"16_CR41","doi-asserted-by":"publisher","first-page":"8855","DOI":"10.1038\/s41598-025-89758-8","volume":"15","author":"Y Wu","year":"2025","unstructured":"Wu, Y., Zhang, S., Li, P.: Multi-modal emotion recognition in conversation based on prompt learning with text-audio fusion features. Sci. Rep. 15(1), 8855 (2025). https:\/\/doi.org\/10.1038\/s41598-025-89758-8","journal-title":"Sci. Rep."},{"key":"16_CR42","doi-asserted-by":"publisher","unstructured":"Zheng, H., Miao, S., Yu, Q., Mu, Y., Jin, X., Yan, K.: Semantic enhancement network integrating label knowledge for multi-modal emotion recognition. In: Huang, D.-S., Zhang, X., Zhang, C. (eds.), Advanced Intelligent Computing Technology and Applications, LNCS, vol. 14879, pp. 473\u2013484. Springer, Singapore (2024). https:\/\/doi.org\/10.1007\/978-981-97-5675-9_40","DOI":"10.1007\/978-981-97-5675-9_40"},{"issue":"1","key":"16_CR43","doi-asserted-by":"publisher","first-page":"8880804","DOI":"10.1049\/2024\/8880804","volume":"2024","author":"Y Dui","year":"2024","unstructured":"Dui, Y., Hu, H.: Social media public opinion detection using multimodal natural language processing and attention mechanisms. IET Inf. Secur. 2024(1), 8880804 (2024). https:\/\/doi.org\/10.1049\/2024\/8880804","journal-title":"IET Inf. Secur."},{"key":"16_CR44","doi-asserted-by":"publisher","unstructured":"Altaibek, M., Zulkhazhav, A., Yergesh, B., Bekmanova, G., Aibol, T.: A multimodal framework for speech emotion recognition in low-resource languages. J. Artif. Intell. Technol. (2025). https:\/\/doi.org\/10.37965\/jait.2025.0781","DOI":"10.37965\/jait.2025.0781"},{"key":"16_CR45","doi-asserted-by":"publisher","first-page":"64330","DOI":"10.1109\/ACCESS.2025.3559339","volume":"13","author":"E Dikbiyik","year":"2025","unstructured":"Dikbiyik, E., Demir, O., Dogan, B.: BiMER: design and implementation of a bimodal emotion recognition system enhanced by data augmentation techniques. IEEE Access 13, 64330\u201364352 (2025). https:\/\/doi.org\/10.1109\/ACCESS.2025.3559339","journal-title":"IEEE Access"},{"key":"16_CR46","doi-asserted-by":"publisher","unstructured":"Balasubramaniyam, H., Priyadarshana, Y.H.P.P.,: EmoShiftNet: A Shift-Aware Multi-Task Learning Framework with Fusion Strategies for Emotion Recognition in Multi-Party Conversations, 2025, https:\/\/doi.org\/10.13140\/RG.2.2.15533.60643","DOI":"10.13140\/RG.2.2.15533.60643"},{"key":"16_CR47","doi-asserted-by":"publisher","unstructured":"He, J., Shi, X., Hu, C.-H., Mi, J., Li, X., Toda, T.: M4SER: Multimodal, Multirepresentation, Multitask, and Multistrategy Learning for Speech Emotion Recognition, 2025. arXiv: arXiv:2509.18706. https:\/\/doi.org\/10.48550\/arXiv.2509.18706","DOI":"10.48550\/arXiv.2509.18706"},{"issue":"5","key":"16_CR48","doi-asserted-by":"publisher","first-page":"82","DOI":"10.1007\/s44443-025-00094-3","volume":"37","author":"X Li","year":"2025","unstructured":"Li, X., Ma, Y., An, X., Xing, J., Liu, R., Ren, Y.: Multi-level fusion with fine-grained alignment for multimodal sentiment analysis. J. King Saud Univ. Comput. Inf. Sci. 37(5), 82 (2025). https:\/\/doi.org\/10.1007\/s44443-025-00094-3","journal-title":"J. King Saud Univ. Comput. Inf. Sci."},{"key":"16_CR49","doi-asserted-by":"publisher","unstructured":"Koren, L., Stipancic, T.: Multimodal emotion analysis based on acoustic and linguistic features of the voice. In: Meiselwitz, G. (ed.), Social Computing and Social Media: Experience Design and Social Network Analysis, LNCS, vol. 12774, pp. 301\u2013311. Springer, Cham (2021). https:\/\/doi.org\/10.1007\/978-3-030-77626-8_20","DOI":"10.1007\/978-3-030-77626-8_20"},{"key":"16_CR50","unstructured":"Bhardwaj, A.K., Pareek - Synth, P.K.: Next-Generation Speech Analysis for Emotion Recognition and PTSD Detection with Advanced Machine and Deep Learning Models, Multidiscip. \u2026 2023 - Macawpublicationscom"},{"key":"16_CR51","doi-asserted-by":"publisher","unstructured":"Zadeh, A., Chen, M., Poria, S., Cambria, E., Morency, L.-P.: Tensor fusion network for multimodal sentiment analysis. In: Proceedings of the 2017 Conference on Empirical Methods in Natural Language Processing, Copenhagen, Denmark: Association for Computational Linguistics, pp. 1103\u20131114, 2017. https:\/\/doi.org\/10.18653\/v1\/D17-1115","DOI":"10.18653\/v1\/D17-1115"},{"key":"16_CR52","doi-asserted-by":"publisher","unstructured":"Baltru\u0161aitis, T., Ahuja, C., Morency, L.-P.: Multimodal Machine Learning: A Survey and Taxonomy, 2017. arXiv: arXiv:1705.09406. https:\/\/doi.org\/10.48550\/arXiv.1705.09406","DOI":"10.48550\/arXiv.1705.09406"},{"key":"16_CR53","unstructured":"Harrington, M.J., Tremblay, S.L.: Robust Multimodal Sentiment Analysis under Incomplete and Noisy Modality Conditions"},{"key":"16_CR54","doi-asserted-by":"publisher","DOI":"10.3389\/fnbot.2021.784514","volume":"15","author":"S Zhang","year":"2021","unstructured":"Zhang, S., Liu, R., Tao, X., Zhao, X.: Deep cross-corpus speech emotion recognition: recent advances and perspectives. Front. Neurorobotics 15, 784514 (2021). https:\/\/doi.org\/10.3389\/fnbot.2021.784514","journal-title":"Front. Neurorobotics"},{"key":"16_CR55","doi-asserted-by":"publisher","unstructured":"Asokan, R., Kumar, N., Ragam, A.V., Sharath, S.S.: Interpretability for Multimodal Emotion Recognition using Concept Activation Vectors, 2022. arXiv: arXiv:2202.01072. https:\/\/doi.org\/10.48550\/arXiv.2202.01072","DOI":"10.48550\/arXiv.2202.01072"},{"key":"16_CR56","doi-asserted-by":"publisher","unstructured":"Jawahar, G., Sagot, B., Seddah, D.: What does BERT learn about the structure of language? In: Proceedings of the 57th Annual Meeting of the Association for Computational Linguistics, Florence, Italy: Association for Computational Linguistics, pp. 3651\u20133657, 2019. https:\/\/doi.org\/10.18653\/v1\/P19-1356","DOI":"10.18653\/v1\/P19-1356"},{"key":"16_CR57","unstructured":"Weston, J., Lenain, R., Meepegama, U., Fristed, E.: Learning De-identified Representations of Prosody from Raw Audio"},{"key":"16_CR58","doi-asserted-by":"publisher","unstructured":"Sajjad, H., Durrani, N., Dalvi, F., Alam, F., Khan, A., Xu, J.: Analyzing encoded concepts in transformer language models. In: Proceedings of the 2022 Conference of the North American Chapter of the Association for Computational Linguistics: Human Language Technologies, Seattle, United States: Association for Computational Linguistics, pp. 3082\u20133101, 2022. https:\/\/doi.org\/10.18653\/v1\/2022.naacl-main.225","DOI":"10.18653\/v1\/2022.naacl-main.225"},{"key":"16_CR59","doi-asserted-by":"publisher","unstructured":"Peters, M., et al.: Deep contextualized word representations. In: Proceedings of the 2018 Conference of the North American Chapter of the Association for Computational Linguistics: Human Language Technologies, Volume 1 (Long Papers), New Orleans, Louisiana: Association for Computational Linguistics, pp. 2227\u20132237, 2018. https:\/\/doi.org\/10.18653\/v1\/N18-1202","DOI":"10.18653\/v1\/N18-1202"},{"key":"16_CR60","doi-asserted-by":"publisher","unstructured":"Tsai, Y.-H.H., Bai, S., Liang, P.P., Kolter, J.Z., Morency, L.-P., Salakhutdinov, R.: Multimodal transformer for unaligned multimodal language sequences. In: Proceedings of the 57th Annual Meeting of the Association for Computational Linguistics, Florence, Italy: Association for Computational Linguistics, pp. 6558\u20136569, 2019. https:\/\/doi.org\/10.18653\/v1\/P19-1656","DOI":"10.18653\/v1\/P19-1656"},{"key":"16_CR61","doi-asserted-by":"publisher","DOI":"10.1016\/j.csi.2024.103856","volume":"90","author":"R Pan","year":"2024","unstructured":"Pan, R., Garc\u00eda-D\u00edaz, J.A., Rodr\u00edguez-Garc\u00eda, M.\u00c1., Valencia-Garc\u00eda, R.: Spanish MEACorpus 2023: a multimodal speech\u2013text corpus for emotion analysis in Spanish from natural environments. Comput. Stand. Interfaces 90, 103856 (2024). https:\/\/doi.org\/10.1016\/j.csi.2024.103856","journal-title":"Comput. Stand. Interfaces"},{"key":"16_CR62","doi-asserted-by":"publisher","unstructured":"Wu, Z. Gong, Z., Ai, L., Shi, P., Donbekci, K., Hirschberg, J.: Beyond Silent Letters: Amplifying LLMs in Emotion Recognition with Vocal Nuances, 2024. arXiv. https:\/\/doi.org\/10.48550\/ARXIV.2407.21315","DOI":"10.48550\/ARXIV.2407.21315"},{"issue":"4","key":"16_CR63","doi-asserted-by":"publisher","first-page":"335","DOI":"10.1007\/s10579-008-9076-6","volume":"42","author":"C Busso","year":"2008","unstructured":"Busso, C., et al.: IEMOCAP: interactive emotional dyadic motion capture database. Lang Resour. Eval. 42(4), 335\u2013359 (2008). https:\/\/doi.org\/10.1007\/s10579-008-9076-6","journal-title":"Lang Resour. Eval."},{"issue":"5","key":"16_CR64","doi-asserted-by":"publisher","DOI":"10.1371\/journal.pone.0196391","volume":"13","author":"SR Livingstone","year":"2018","unstructured":"Livingstone, S.R., Russo, F.A.: The ryerson audio-visual database of emotional speech and song (RAVDESS): a dynamic, multimodal set of facial and vocal expressions in North American English. PLoS ONE 13(5), e0196391 (2018). https:\/\/doi.org\/10.1371\/journal.pone.0196391","journal-title":"PLoS ONE"},{"key":"16_CR65","doi-asserted-by":"publisher","unstructured":"Poria, S., Hazarika, D., Majumder, N., Naik, G., Cambria, E., Mihalcea, R.: MELD: a multimodal multi-party dataset for emotion recognition in conversations. In: Proceedings of the 57th Annual Meeting of the Association for Computational Linguistics, Florence, Italy: Association for Computational Linguistics, pp. 527\u2013536, 2019. https:\/\/doi.org\/10.18653\/v1\/P19-1050","DOI":"10.18653\/v1\/P19-1050"}],"container-title":["Lecture Notes in Computer Science","Augmenting Cognition in the AI-Accelerated Era"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/link.springer.com\/content\/pdf\/10.1007\/978-3-032-29548-4_16","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2026,6,26]],"date-time":"2026-06-26T09:20:21Z","timestamp":1782465621000},"score":1,"resource":{"primary":{"URL":"https:\/\/link.springer.com\/10.1007\/978-3-032-29548-4_16"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2026]]},"ISBN":["9783032295477","9783032295484"],"references-count":65,"URL":"https:\/\/doi.org\/10.1007\/978-3-032-29548-4_16","relation":{},"ISSN":["0302-9743","1611-3349"],"issn-type":[{"value":"0302-9743","type":"print"},{"value":"1611-3349","type":"electronic"}],"subject":[],"published":{"date-parts":[[2026]]},"assertion":[{"value":"27 June 2026","order":1,"name":"first_online","label":"First Online","group":{"name":"ChapterHistory","label":"Chapter History"}},{"value":"HCII","order":1,"name":"conference_acronym","label":"Conference Acronym","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"International Conference on Human-Computer Interaction","order":2,"name":"conference_name","label":"Conference Name","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"Montreal, QC","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":"26 July 2026","order":7,"name":"conference_start_date","label":"Conference Start Date","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"31 July 2026","order":8,"name":"conference_end_date","label":"Conference End Date","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"28","order":9,"name":"conference_number","label":"Conference Number","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"hcii2026","order":10,"name":"conference_id","label":"Conference ID","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"https:\/\/2026.hci.international\/","order":11,"name":"conference_url","label":"Conference URL","group":{"name":"ConferenceInfo","label":"Conference Information"}}]}}