{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,7,2]],"date-time":"2026-07-02T16:31:36Z","timestamp":1783009896699,"version":"3.54.5"},"reference-count":64,"publisher":"Springer Science and Business Media LLC","issue":"5-6","license":[{"start":{"date-parts":[[2025,4,1]],"date-time":"2025-04-01T00:00:00Z","timestamp":1743465600000},"content-version":"tdm","delay-in-days":0,"URL":"https:\/\/www.springernature.com\/gp\/researchers\/text-and-data-mining"},{"start":{"date-parts":[[2025,4,1]],"date-time":"2025-04-01T00:00:00Z","timestamp":1743465600000},"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":["Ann. Telecommun."],"published-print":{"date-parts":[[2025,6]]},"DOI":"10.1007\/s12243-025-01088-y","type":"journal-article","created":{"date-parts":[[2025,4,3]],"date-time":"2025-04-03T17:48:58Z","timestamp":1743702538000},"page":"379-399","update-policy":"https:\/\/doi.org\/10.1007\/springer_crossmark_policy","source":"Crossref","is-referenced-by-count":9,"title":["Efficient bimodal emotion recognition system based on speech\/text embeddings and ensemble learning fusion"],"prefix":"10.1007","volume":"80","author":[{"given":"Adil","family":"Chakhtouna","sequence":"first","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Sara","family":"Sekkate","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Abdellah","family":"Adib","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"297","published-online":{"date-parts":[[2025,4,1]]},"reference":[{"key":"1088_CR1","unstructured":"Frijda NH (1993) Moods, emotion episodes, and emotions. The Guilford Press"},{"key":"1088_CR2","doi-asserted-by":"crossref","unstructured":"Feng Y, Devillers L (2023) End-to-end continuous speech emotion recognition in real-life customer service call center conversations. In: 2023 11th International conference on Affective Computing and Intelligent Interaction Workshops and Demos (ACIIW), pp 1\u20138","DOI":"10.1109\/ACIIW59127.2023.10388120"},{"issue":"21","key":"1088_CR3","doi-asserted-by":"publisher","first-page":"16002","DOI":"10.1109\/JIOT.2020.3038631","volume":"8","author":"T Zhang","year":"2020","unstructured":"Zhang T, Liu M, Yuan T, Al-Nabhan N (2020) Emotion-aware and intelligent internet of medical things toward emotion recognition during covid-19 pandemic. IEEE Internet Things J 8(21):16002\u201316013","journal-title":"IEEE Internet Things J"},{"key":"1088_CR4","doi-asserted-by":"crossref","unstructured":"Cen L, Wu F, Yu ZL, Hu F (2016) Chapter 2 - a real-time speech emotion recognition system and its application in online learning. Emotions, technology, design, and learning. Emotions and technology. Academic Press, San Diego, pp 27\u201346","DOI":"10.1016\/B978-0-12-801856-9.00002-5"},{"key":"1088_CR5","doi-asserted-by":"crossref","unstructured":"Yong, H., Lee, J., Choi, J.: Emotion recognition in gamers wearing head-mounted display. In: 2019 IEEE Conference on virtual reality and 3D user interfaces (VR), pp. 1251\u20131252 (2019)","DOI":"10.1109\/VR.2019.8797736"},{"key":"1088_CR6","doi-asserted-by":"crossref","unstructured":"Spezialetti M, Placidi G, Rossi S (2020) Emotion recognition for human-robot interaction: Recent advances and future perspectives. Frontiers in robotics and AI. 7","DOI":"10.3389\/frobt.2020.532279"},{"key":"1088_CR7","unstructured":"Mordor I (2024) Emotion detection and recognition market size & share analysis - growth trends & forecasts (2024-2029). https:\/\/www.mordorintelligence.com\/industry-reports\/emotion-detection-and-recognition-edr-market. Accessed 06 Jan 2024"},{"key":"1088_CR8","doi-asserted-by":"crossref","unstructured":"Geetha AV, Mala T, Priyanka D, Uma E (2024) Multimodal emotion recognition with deep learning: advancements, challenges, and future directions. Information fusion. 105","DOI":"10.1016\/j.inffus.2023.102218"},{"key":"1088_CR9","doi-asserted-by":"crossref","unstructured":"Tao, J., Tan, T.: Affective computing: a review. In: Affective computing and intelligent interaction, pp. 981\u2013995. Springer, Berlin, Heidelberg (2005)","DOI":"10.1007\/11573548_125"},{"key":"1088_CR10","doi-asserted-by":"publisher","first-page":"11","DOI":"10.1016\/j.specom.2022.03.002","volume":"140","author":"BT Atmaja","year":"2022","unstructured":"Atmaja BT, Sasou A, Akagi M (2022) Survey on bimodal speech emotion recognition from acoustic and linguistic information fusion. Speech Commun 140:11\u201328","journal-title":"Speech Commun"},{"key":"1088_CR11","doi-asserted-by":"publisher","first-page":"187","DOI":"10.1016\/j.neucom.2020.07.056","volume":"417","author":"LE Bouny","year":"2020","unstructured":"Bouny LE, Khalil M, Adib A (2020) An end-to-end multi-level wavelet convolutional neural networks for heart diseases diagnosis. Neurocomputing 417:187\u2013201","journal-title":"Neurocomputing"},{"key":"1088_CR12","doi-asserted-by":"publisher","first-page":"402","DOI":"10.1016\/j.procs.2024.05.047","volume":"236","author":"S Akil","year":"2024","unstructured":"Akil S, Sekkate S, Adib A (2024) Multimodal deep learning for oil price forecasting using economic indicators. Procedia Computer Science. 236:402\u2013409","journal-title":"Procedia Computer Science."},{"key":"1088_CR13","doi-asserted-by":"crossref","unstructured":"Riyad M, Khalil M, Adib A (2022) Dimensionality reduction of MI-EEG data via convolutional autoencoders with a low size dataset. In: Business intelligence, pp 263\u2013278. Springer, Cham","DOI":"10.1007\/978-3-031-06458-6_22"},{"key":"1088_CR14","doi-asserted-by":"crossref","unstructured":"Chakhtouna A, Sekkate S, Adib A (2024) A statistical WAVLM embedding features with auto-encoder for speech emotion recognition. In: Biologically inspired cognitive architectures 2023, pp 159\u2013168. Springer, Cham","DOI":"10.1007\/978-3-031-50381-8_19"},{"key":"1088_CR15","doi-asserted-by":"publisher","first-page":"428","DOI":"10.1016\/j.procs.2024.05.050","volume":"236","author":"A Chakhtouna","year":"2024","unstructured":"Chakhtouna A, Sekkate S, Adib A (2024) Modeling speech emotion recognition via ImageBind representations. Procedia Comput Sci 236:428\u2013435","journal-title":"Procedia Comput Sci"},{"issue":"02","key":"1088_CR16","doi-asserted-by":"publisher","first-page":"2450009","DOI":"10.1142\/S0219649224500096","volume":"23","author":"B Nouhaila","year":"2024","unstructured":"Nouhaila B, Habib A, Abdellah A, Abdelhamid IEF (2024) Assessing the impact of static, contextual and character embeddings for Arabic machine translation. J Inf Knowl Manag 23(02):2450009","journal-title":"J Inf Knowl Manag"},{"issue":"19","key":"1088_CR17","doi-asserted-by":"publisher","first-page":"57661","DOI":"10.1007\/s11042-023-17213-9","volume":"83","author":"N Remzan","year":"2024","unstructured":"Remzan N, Hachimi YE, Tahiry K, Farchi A (2024) Ensemble learning based-features extraction for brain MR images classification with machine learning classifiers. Multimed Tools Appl 83(19):57661\u201357684","journal-title":"Multimed Tools Appl"},{"key":"1088_CR18","doi-asserted-by":"crossref","unstructured":"Mait, H.A., Aboutabit, N.: Unsupervised phoneme segmentation of continuous Arabic speech. International journal of speech technology, 1\u201312 (2024)","DOI":"10.1007\/s10772-024-10099-4"},{"key":"1088_CR19","doi-asserted-by":"crossref","unstructured":"Chakhtouna A, Sekkate S, Adib A (2023) Speaker and gender dependencies in within\/cross linguistic speech emotion recognition. International journal of speech technology, pp 1\u201317","DOI":"10.1007\/s10772-023-10038-9"},{"key":"1088_CR20","doi-asserted-by":"crossref","unstructured":"Alzubaidi L, Zhang J, Humaidi AJ, Al-Dujaili A, Duan Y, Al-Shamma O, Santamar\u00eda J, Fadhel MA, Al-Amidie M, Farhan L (2021) Review of deep learning: Concepts, CNN architectures, challenges, applications, future directions. J Big Data. 8:1\u201374","DOI":"10.1186\/s40537-021-00444-8"},{"key":"1088_CR21","doi-asserted-by":"publisher","first-page":"392","DOI":"10.1016\/j.neunet.2022.03.017","volume":"150","author":"P Kumar","year":"2022","unstructured":"Kumar P, Raman B (2022) A BERT based dual-channel explainable text emotion recognition system. Neural Netw 150:392\u2013407","journal-title":"Neural Netw"},{"key":"1088_CR22","doi-asserted-by":"publisher","first-page":"2560","DOI":"10.1016\/j.procs.2024.02.074","volume":"232","author":"A Chakhtouna","year":"2024","unstructured":"Chakhtouna A, Sekkate S, Adib A (2024) Unveiling embedded features in Wav2vec2 and Hubert msodels for speech emotion recognition. Procedia Comput Sci 232:2560\u20132569","journal-title":"Procedia Comput Sci"},{"key":"1088_CR23","doi-asserted-by":"crossref","unstructured":"Chakhtouna A, Sekkate S, Adib A (2024) Multi-features learning via attention-blstm for speech emotion recognition. In: 2024 International conference on Signal, Image, Video and Communications (ISIVC), pp 1\u20136","DOI":"10.1109\/ISIVC61350.2024.10577886"},{"key":"1088_CR24","doi-asserted-by":"crossref","unstructured":"Pepino L, Riera P, Ferrer L, Gravano A (2020) 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), pp. 6484\u20136488","DOI":"10.1109\/ICASSP40776.2020.9054709"},{"key":"1088_CR25","doi-asserted-by":"crossref","unstructured":"Li J, Wang S, Chao Y, Liu X, Meng H (2022) Context-aware multimodal fusion for emotion recognition. In: INTERSPEECH, pp 2013\u20132017","DOI":"10.21437\/Interspeech.2022-10592"},{"key":"1088_CR26","doi-asserted-by":"crossref","unstructured":"Pan B, Hirota K, Jia Z, Dai Y (2023) A review of multimodal emotion recognition from datasets, preprocessing, features, and fusion methods. Neurocomputing, 126866","DOI":"10.1016\/j.neucom.2023.126866"},{"issue":"5","key":"1088_CR27","doi-asserted-by":"publisher","first-page":"90","DOI":"10.1145\/3129340","volume":"61","author":"BW Schuller","year":"2018","unstructured":"Schuller BW (2018) Speech emotion recognition: two decades in a nutshell, benchmarks, and ongoing trends. Commun ACM 61(5):90\u201399","journal-title":"Commun ACM"},{"key":"1088_CR28","doi-asserted-by":"crossref","unstructured":"Kerkeni L, Serrestou Y, Mbarki M, Raoof K, Mahjoub MA, Cleder C (2019) Automatic speech emotion recognition using machine learning. IntechOpen","DOI":"10.5772\/intechopen.84856"},{"key":"1088_CR29","doi-asserted-by":"publisher","DOI":"10.1016\/j.eswa.2021.114683","volume":"173","author":"D Li","year":"2021","unstructured":"Li D, Liu J, Yang Z, Sun L, Wang Z (2021) Speech emotion recognition using recurrent neural networks with directional self-attention. Expert Syst Appl 173:114683","journal-title":"Expert Syst Appl"},{"key":"1088_CR30","doi-asserted-by":"crossref","unstructured":"Pepino, L., Riera, P., Ferrer, L.: Emotion recognition from speech using Wav2vec 2.0 embeddings. arXiv:2104.03502. (2021)","DOI":"10.21437\/Interspeech.2021-703"},{"issue":"2","key":"1088_CR31","doi-asserted-by":"publisher","first-page":"190","DOI":"10.1109\/TAFFC.2015.2457417","volume":"7","author":"F Eyben","year":"2015","unstructured":"Eyben F, Scherer KR, Schuller BW, Sundberg J, Andr\u00e9 E, Busso C, Devillers LY, Epps J, Laukka P, Narayanan SS et al (2015) The geneva minimalistic acoustic parameter set (gemaps) for voice research and affective computing. IEEE Trans Affect Comput 7(2):190\u2013202","journal-title":"IEEE Trans Affect Comput"},{"key":"1088_CR32","first-page":"12449","volume":"33","author":"A Baevski","year":"2020","unstructured":"Baevski A, Zhou Y, Mohamed A, Auli M (2020) wav2vec 2.0: A framework for self-supervised learning of speech representations. Advan Neural Inform Proc Syst 33:12449\u201312460","journal-title":"Advan Neural Inform Proc Syst"},{"issue":"4","key":"1088_CR33","doi-asserted-by":"publisher","first-page":"4897","DOI":"10.1007\/s11042-021-10553-4","volume":"81","author":"C Wang","year":"2022","unstructured":"Wang C, Ren Y, Zhang N, Cui F, Luo S (2022) Speech emotion recognition based on multi-feature and multi-lingual fusion. Multimed Tools Appl 81(4):4897\u20134907","journal-title":"Multimed Tools Appl"},{"key":"1088_CR34","doi-asserted-by":"crossref","unstructured":"Jin Q, Li C, Chen S, Wu H (2015) Speech emotion recognition with acoustic and lexical features. In: 2015 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP), pp 4749\u20134753","DOI":"10.1109\/ICASSP.2015.7178872"},{"key":"1088_CR35","doi-asserted-by":"crossref","unstructured":"Eyben F, W\u00f6llmer M, Schuller B (2010) Opensmile: the munich versatile and fast open-source audio feature extractor. In: Proceedings of the 18th ACM international conference on multimedia, pp 1459\u20131462","DOI":"10.1145\/1873951.1874246"},{"key":"1088_CR36","doi-asserted-by":"crossref","unstructured":"Yoon S, Dey S, Lee H, Jung K (2020) Attentive modality hopping mechanism for speech emotion recognition. In: ICASSP 2020 - 2020 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP), pp 3362\u20133366","DOI":"10.1109\/ICASSP40776.2020.9054229"},{"issue":"1","key":"1088_CR37","doi-asserted-by":"publisher","first-page":"71","DOI":"10.1007\/s11760-023-02707-8","volume":"18","author":"SS Hosseini","year":"2024","unstructured":"Hosseini SS, Yamaghani MR, Poorzaker Arabani S (2024) Multimodal modelling of human emotion using sound, image and text fusion. SIViP 18(1):71\u201379","journal-title":"SIViP"},{"key":"1088_CR38","unstructured":"Mikolov T, Chen K, Corrado G, Dean J (2013) Efficient estimation of word representations in vector space. arXiv:1301.3781"},{"key":"1088_CR39","doi-asserted-by":"publisher","first-page":"335","DOI":"10.1007\/s10579-008-9076-6","volume":"42","author":"C Busso","year":"2008","unstructured":"Busso C, Bulut M, Lee C-C, Kazemzadeh A, Mower E, Kim S, Chang JN, Lee S, Narayanan SS (2008) Iemocap: Interactive emotional dyadic motion capture database. Lang Resour Eval 42:335\u2013359","journal-title":"Lang Resour Eval"},{"key":"1088_CR40","doi-asserted-by":"crossref","unstructured":"Pedersen P (1965) The mel scale. J Music Theory 9(2):295\u2013308","DOI":"10.2307\/843164"},{"issue":"1","key":"1088_CR41","doi-asserted-by":"publisher","first-page":"11","DOI":"10.1108\/eb026526","volume":"28","author":"K Sparck Jones","year":"1972","unstructured":"Sparck Jones K (1972) A statistical interpretation of term specificity and its application in retrieval. Journal of documentation. 28(1):11\u201321","journal-title":"Journal of documentation."},{"key":"1088_CR42","unstructured":"Liu Y, Ott M, Goyal N, Du J, Joshi M, Chen D, Levy O, Lewis M, Zettlemoyer L, Stoyanov V (2019) Roberta: A robustly optimized bert pretraining approach. arXiv:1907.11692"},{"key":"1088_CR43","doi-asserted-by":"publisher","first-page":"264","DOI":"10.1162\/tacl_a_00313","volume":"8","author":"S Rothe","year":"2020","unstructured":"Rothe S, Narayan S, Severyn A (2020) Leveraging pre-trained checkpoints for sequence generation tasks. Trans Assoc Comput Linguistics 8:264\u2013280","journal-title":"Trans Assoc Comput Linguistics"},{"key":"1088_CR44","doi-asserted-by":"publisher","first-page":"64","DOI":"10.1162\/tacl_a_00300","volume":"8","author":"M Joshi","year":"2020","unstructured":"Joshi M, Chen D, Liu Y, Weld DS, Zettlemoyer L, Levy O (2020) Spanbert: Improving pre-training by representing and predicting spans. Transactions of the association for computational linguistics. 8:64\u201377","journal-title":"Transactions of the association for computational linguistics."},{"key":"1088_CR45","doi-asserted-by":"crossref","unstructured":"Girdhar R, El-Nouby A, Liu Z, Singh M, Alwala KV, Joulin A, Misra I (2023) Imagebind: One embedding space to bind them all. In: Proceedings of the IEEE\/CVF conference on computer vision and pattern recognition, pp 15180\u201315190","DOI":"10.1109\/CVPR52729.2023.01457"},{"key":"1088_CR46","doi-asserted-by":"crossref","unstructured":"Grauman K, Westbury A, Byrne E, Chavis Z, Furnari A, Girdhar R, Hamburger J, Jiang H, Liu M, Liu X et al (2022) Ego4d: Around the world in 3,000 hours of egocentric video. In: Proceedings of the IEEE\/CVF conference on computer vision and pattern recognition, pp 18995\u201319012","DOI":"10.1109\/CVPR52688.2022.01842"},{"key":"1088_CR47","doi-asserted-by":"crossref","unstructured":"Gemmeke JF, Ellis DPW, Freedman D, Jansen A, Lawrence W, Moore RC, Plakal M, Ritter M (2017) Audio set: An ontology and human-labeled dataset for audio events. In: 2017 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP), pp 776\u2013780","DOI":"10.1109\/ICASSP.2017.7952261"},{"key":"1088_CR48","doi-asserted-by":"crossref","unstructured":"Jia X, Zhu C, Li M, Tang W, Zhou W (2021) Llvip: A visible-infrared paired dataset for low-light vision. In: Proceedings of the IEEE\/CVF international conference on computer vision, pp 3496\u20133504","DOI":"10.1109\/ICCVW54120.2021.00389"},{"key":"1088_CR49","doi-asserted-by":"crossref","unstructured":"Song S, Lichtenberg SP, Xiao J (2015) Sun rgb-d: A rgb-d scene understanding benchmark suite. In: Proceedings of the IEEE conference on computer vision and pattern recognition, pp 567\u2013576","DOI":"10.1109\/CVPR.2015.7298655"},{"key":"1088_CR50","first-page":"273","volume":"20","author":"C Cortes","year":"1995","unstructured":"Cortes C, Vapnik V (1995) Support-vector networks. Machine learning. 20:273\u2013297","journal-title":"Support-vector networks. Machine learning."},{"issue":"5","key":"1088_CR51","doi-asserted-by":"publisher","first-page":"1207","DOI":"10.1162\/089976600300015565","volume":"12","author":"B Sch\u00f6lkopf","year":"2000","unstructured":"Sch\u00f6lkopf B, Smola AJ, Williamson RC, Bartlett PL (2000) New support vector algorithms. Neural Comput 12(5):1207\u20131245","journal-title":"Neural Comput"},{"key":"1088_CR52","doi-asserted-by":"publisher","first-page":"5","DOI":"10.1023\/A:1010933404324","volume":"45","author":"L Breiman","year":"2000","unstructured":"Breiman L (2000) Random forests. Mach Learn 45:5\u201332","journal-title":"Mach Learn"},{"issue":"1","key":"1088_CR53","doi-asserted-by":"publisher","first-page":"21","DOI":"10.1109\/TIT.1967.1053964","volume":"13","author":"T Cover","year":"1967","unstructured":"Cover T, Hart P (1967) Nearest neighbor pattern classification. IEEE Trans Inf Theory 13(1):21\u201327","journal-title":"IEEE Trans Inf Theory"},{"key":"1088_CR54","doi-asserted-by":"crossref","unstructured":"Lee CM, Narayanan SS, Pieraccini R (2002) Combining acoustic and language information for emotion recognition. In: 7th International Conference on Spoken Language Processing (ICSLP), pp 873\u2013876","DOI":"10.21437\/ICSLP.2002-296"},{"key":"1088_CR55","doi-asserted-by":"crossref","unstructured":"Chen M, Zhao X (2020) A multi-scale fusion framework for bimodal speech emotion recognition. In: Interspeech, pp 374\u2013378","DOI":"10.21437\/Interspeech.2020-3156"},{"key":"1088_CR56","doi-asserted-by":"crossref","unstructured":"Bhosale S, Chakraborty R, Kopparapu SK (2020) Deep encoded linguistic and acoustic cues for attention based end to end speech emotion recognition. In: ICASSP 2020 - 2020 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP), pp 7189\u20137193","DOI":"10.1109\/ICASSP40776.2020.9054621"},{"key":"1088_CR57","doi-asserted-by":"crossref","unstructured":"Xu H, Zhang H, Han K, Wang Y, Peng Y, Li X (2019) Learning alignment for multimodal emotion recognition from speech. arXiv:1909.05645","DOI":"10.21437\/Interspeech.2019-3247"},{"issue":"77","key":"1088_CR58","first-page":"1","volume":"18","author":"A Benavoli","year":"2017","unstructured":"Benavoli A, Corani G, Dem\u0161ar J, Zaffalon M (2017) Time for a change: A tutorial for comparing multiple classifiers through bayesian analysis. J Mach Learn Res 18(77):1\u201336","journal-title":"J Mach Learn Res"},{"key":"1088_CR59","doi-asserted-by":"crossref","unstructured":"Liu, J., Liu, Z., Wang, L., Guo, L., Dang, J.: Speech emotion recognition with local-global aware deep representation learning. In: ICASSP 2020 - 2020 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP), pp. 7174\u20137178 (2020)","DOI":"10.1109\/ICASSP40776.2020.9053192"},{"key":"1088_CR60","doi-asserted-by":"crossref","unstructured":"Mustaqeem, Kwon S (2021) Mlt-dnet: Speech emotion recognition using 1d dilated cnn based on multi-learning trick approach. Expert Syst Appl 167:114177","DOI":"10.1016\/j.eswa.2020.114177"},{"key":"1088_CR61","doi-asserted-by":"crossref","unstructured":"Meng H, Yan T, Yuan F, Wei H (2019) Speech emotion recognition from 3d log-mel spectrograms with deep learning network. IEEE access. 7:125868\u2013125881","DOI":"10.1109\/ACCESS.2019.2938007"},{"key":"1088_CR62","doi-asserted-by":"crossref","unstructured":"Neumann M, Vu NT (2017) Attentive convolutional neural network based speech emotion recognition: A study on the impact of input features, signal length, and acted speech. arXiv:1706.00612","DOI":"10.21437\/Interspeech.2017-917"},{"key":"1088_CR63","doi-asserted-by":"crossref","unstructured":"Yoon S, Byun S, Jung K (2018) Multimodal speech emotion recognition using audio and text. In: 2018 IEEE Spoken Language Technology Workshop (SLT), pp 112\u2013118","DOI":"10.1109\/SLT.2018.8639583"},{"key":"1088_CR64","doi-asserted-by":"crossref","unstructured":"Hazarika D, Poria S, Mihalcea R, Cambria E, Zimmermann R (2018) Icon: Interactive conversational memory network for multimodal emotion detection. In: Proceedings of the 2018 conference on empirical methods in natural language processing, pp 2594\u20132604","DOI":"10.18653\/v1\/D18-1280"}],"container-title":["Annals of Telecommunications"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/link.springer.com\/content\/pdf\/10.1007\/s12243-025-01088-y.pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/link.springer.com\/article\/10.1007\/s12243-025-01088-y\/fulltext.html","content-type":"text\/html","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/link.springer.com\/content\/pdf\/10.1007\/s12243-025-01088-y.pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,5,30]],"date-time":"2025-05-30T09:18:51Z","timestamp":1748596731000},"score":1,"resource":{"primary":{"URL":"https:\/\/link.springer.com\/10.1007\/s12243-025-01088-y"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2025,4,1]]},"references-count":64,"journal-issue":{"issue":"5-6","published-print":{"date-parts":[[2025,6]]}},"alternative-id":["1088"],"URL":"https:\/\/doi.org\/10.1007\/s12243-025-01088-y","relation":{},"ISSN":["0003-4347","1958-9395"],"issn-type":[{"value":"0003-4347","type":"print"},{"value":"1958-9395","type":"electronic"}],"subject":[],"published":{"date-parts":[[2025,4,1]]},"assertion":[{"value":"30 June 2024","order":1,"name":"received","label":"Received","group":{"name":"ArticleHistory","label":"Article History"}},{"value":"23 March 2025","order":2,"name":"accepted","label":"Accepted","group":{"name":"ArticleHistory","label":"Article History"}},{"value":"1 April 2025","order":3,"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 competing interest.","order":2,"name":"Ethics","group":{"name":"EthicsHeading","label":"Conflict of interest"}}]}}