{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2025,9,11]],"date-time":"2025-09-11T19:15:07Z","timestamp":1757618107687,"version":"3.44.0"},"publisher-location":"Cham","reference-count":24,"publisher":"Springer Nature Switzerland","isbn-type":[{"type":"print","value":"9783031915802"},{"type":"electronic","value":"9783031915819"}],"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\/978-3-031-91581-9_24","type":"book-chapter","created":{"date-parts":[[2025,5,27]],"date-time":"2025-05-27T11:24:10Z","timestamp":1748345050000},"page":"335-348","update-policy":"https:\/\/doi.org\/10.1007\/springer_crossmark_policy","source":"Crossref","is-referenced-by-count":0,"title":["Better Spanish Emotion Recognition In-the-Wild: Bringing Attention to Deep Spectrum Voice Analysis"],"prefix":"10.1007","author":[{"given":"Elena","family":"Ortega-Beltr\u00e1n","sequence":"first","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Josep","family":"Cabacas-Maso","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-2504-6123","authenticated-orcid":false,"given":"Ismael","family":"Benito-Altamirano","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Carles","family":"Ventura","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"297","published-online":{"date-parts":[[2025,5,12]]},"reference":[{"issue":"3","key":"24_CR1","doi-asserted-by":"publisher","first-page":"2020","DOI":"10.1109\/TAFFC.2022.3143803","volume":"14","author":"H Abdollahi","year":"2022","unstructured":"Abdollahi, H., Mahoor, M.H., Zandie, R., Siewierski, J., Qualls, S.H.: Artificial emotional intelligence in socially assistive robots for older adults: A pilot study. IEEE Trans. Affect. Comput. 14(3), 2020\u20132032 (2022). https:\/\/doi.org\/10.1109\/TAFFC.2022.3143803","journal-title":"IEEE Trans. Affect. Comput."},{"key":"24_CR2","doi-asserted-by":"publisher","unstructured":"Amiriparian, S., et al.: Snore sound classification using image-based deep spectrum features. In: Interspeech 2017, pp. 3512\u20133516. ISCA (August 2017). https:\/\/doi.org\/10.21437\/Interspeech.2017-434","DOI":"10.21437\/Interspeech.2017-434"},{"key":"24_CR3","unstructured":"Amiriparian, S., Gerczuk, M., Ottl, S., Schuller, B.: Deepspectrum (2020). https:\/\/github.com\/DeepSpectrum\/DeepSpectrum. Accessed 30 July 2024"},{"key":"24_CR4","unstructured":"Barra\u00a0Chicote, R., et al.: Spanish expressive voices: corpus for emotion research in Spanish, pp. 60\u201370 (May 2008). http:\/\/www.lrec-conf.org\/proceedings\/lrec2008\/"},{"key":"24_CR5","doi-asserted-by":"publisher","unstructured":"Bestelmeyer, P.E.G., Kotz, S.A., Belin, P.: Effects of emotional valence and arousal on the voice perception network. Soc. Cogn. Affect. Neurosci. 12, 1351\u20131358 (2017). https:\/\/doi.org\/10.1093\/scan\/nsx059","DOI":"10.1093\/scan\/nsx059"},{"key":"24_CR6","doi-asserted-by":"crossref","unstructured":"Burkhardt, F., Paeschke, A., Rolfes, M., Sendlmeier, W.F., Weiss, B., et\u00a0al.: A database of German emotional speech. In: Interspeech, vol.\u00a05, pp. 1517\u20131520 (2005)","DOI":"10.21437\/Interspeech.2005-446"},{"key":"24_CR7","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, 335\u2013359 (2008)","journal-title":"Lang. Resour. Eval."},{"key":"24_CR8","doi-asserted-by":"crossref","unstructured":"Ekman, P.: Emotional and conversational nonverbal signals. In: Language, knowledge, and representation: Proceedings of the Sixth International Colloquium on Cognitive Science (ICCS-99), pp. 39\u201350. Springer (2004)","DOI":"10.1007\/978-1-4020-2783-3_3"},{"key":"24_CR9","doi-asserted-by":"publisher","unstructured":"Garcia-Cuesta, E., Salvador, A.B., P\u00e3ez, D.G.: EmoMatchSpanishDB: study of speech emotion recognition machine learning models in a new spanish elicited database 83(5), 13093\u20131311. https:\/\/doi.org\/10.1007\/s11042-023-15959-w, https:\/\/link.springer.com\/10.1007\/s11042-023-15959-w","DOI":"10.1007\/s11042-023-15959-w"},{"key":"24_CR10","unstructured":"G\u00f3rriz, M., Antony, J., McGuinness, K., Gir\u00f3-i Nieto, X., O\u2019Connor, N.E.: Assessing knee oa severity with cnn attention-based end-to-end architectures. In: International Conference on Medical Imaging with Deep Learning, pp. 197\u2013214 (2019)"},{"key":"24_CR11","unstructured":"Hortal, E., Brechard\u00a0Alarcia, R.: Gantron: emotional speech synthesis with generative adversarial networks (October 2021)"},{"key":"24_CR12","doi-asserted-by":"crossref","unstructured":"Jaafar, N., Lachiri, Z.: Stress recognition from speech by combining image-based deep spectrum and text-based features. In: 2022 IEEE Information Technologies & Smart Industrial Systems (ITSIS), pp.\u00a01\u20136. IEEE (2022)","DOI":"10.1109\/ITSIS56166.2022.10118402"},{"key":"24_CR13","doi-asserted-by":"publisher","unstructured":"Kerkeni, L., Serrestou, Y., Mbarki, M., Raoof, K., Mahjoub, M.A.: Speech emotion recognition: methods and cases study:. In: Proceedings of the 10th International Conference on Agents and Artificial Intelligence, pp. 175\u2013182. SCITEPRESS - Science and Technology Publications. https:\/\/doi.org\/10.5220\/0006611601750182, http:\/\/www.scitepress.org\/DigitalLibrary\/Link.aspx?doi=10.5220\/0006611601750182","DOI":"10.5220\/0006611601750182"},{"issue":"1","key":"24_CR14","volume":"2014","author":"CH Lin","year":"2014","unstructured":"Lin, C.H., Liao, W.K., Hsieh, W.C., Liao, W.J., Wang, J.C.: Emotion identification using extremely low frequency components of speech feature contours. Sci. World J. 2014(1), 757121 (2014)","journal-title":"Sci. World J."},{"key":"24_CR15","doi-asserted-by":"publisher","unstructured":"Martin, O., Kotsia, I., Macq, B., Pitas, I.: The enterfaceamp;146;05 audio-visual emotion database, p.\u00a08. IEEE (2006). https:\/\/doi.org\/10.1109\/ICDEW.2006.145","DOI":"10.1109\/ICDEW.2006.145"},{"issue":"2","key":"24_CR16","doi-asserted-by":"publisher","first-page":"527","DOI":"10.1111\/padr.12386","volume":"47","author":"SH Preston","year":"2021","unstructured":"Preston, S.H., Vierboom, Y.C.: The changing age distribution of the united states. Popul. Dev. Rev. 47(2), 527\u2013539 (2021)","journal-title":"Popul. Dev. Rev."},{"key":"24_CR17","doi-asserted-by":"crossref","unstructured":"Ringeval, F., Sonderegger, A., Sauer, J., Lalanne, D.: Introducing the recola multimodal corpus of remote collaborative and affective interactions. In: 2013 10th IEEE International Conference and Workshops on Automatic Face and Gesture Recognition (FG), pp.\u00a01\u20138. IEEE (2013)","DOI":"10.1109\/FG.2013.6553805"},{"key":"24_CR18","doi-asserted-by":"crossref","unstructured":"Schuller, B.W., et\u00a0al.: The acm multimedia 2023 computational paralinguistics challenge: emotion share & requests. In: Proceedings of the 31st ACM International Conference on Multimedia, pp. 9635\u20139639 (2023)","DOI":"10.1145\/3581783.3612835"},{"key":"24_CR19","doi-asserted-by":"crossref","unstructured":"\u0160\u00eddlo, L., \u0160procha, B., Dur\u010dek, P.: A retrospective and prospective view of current and future population ageing in the european union 28 countries. Morav. Geogr. Rep. 28(3), 187\u2013207 (2020)","DOI":"10.2478\/mgr-2020-0014"},{"key":"24_CR20","unstructured":"Simonyan, K., Zisserman, A.: Very deep convolutional networks for large-scale image recognition. arXiv preprint arXiv:1409.1556 (2014)"},{"key":"24_CR21","doi-asserted-by":"crossref","unstructured":"Vary, P., Martin, R.: Digital Speech Transmission and Enhancement. IEEE Press, Wiley, Hoboken (2023). https:\/\/books.google.es\/books?id=3rDiEAAAQBAJ","DOI":"10.1002\/9781119060970"},{"key":"24_CR22","doi-asserted-by":"publisher","unstructured":"Wu, S., Falk, T.H., Chan, W.Y.: Automatic speech emotion recognition using modulation spectral features 53(5), 768\u2013785. https:\/\/doi.org\/10.1016\/j.specom.2010.08.013, https:\/\/linkinghub.elsevier.com\/retrieve\/pii\/S0167639310001470","DOI":"10.1016\/j.specom.2010.08.013"},{"key":"24_CR23","doi-asserted-by":"publisher","DOI":"10.1016\/j.arr.2022.101633","volume":"78","author":"C Yu","year":"2022","unstructured":"Yu, C., Sommerlad, A., Sakure, L., Livingston, G.: Socially assistive robots for people with dementia: systematic review and meta-analysis of feasibility, acceptability and the effect on cognition, neuropsychiatric symptoms and quality of life. Ageing Res. Rev. 78, 101633 (2022)","journal-title":"Ageing Res. Rev."},{"key":"24_CR24","doi-asserted-by":"publisher","unstructured":"Zadeh, A.B., Cao, Y., Hessner, S., Liang, P.P., Poria, S., Morency, L.P.: Cmu-moseas: a multimodal language dataset for Spanish, Portuguese, German and French, pp. 1801\u20131812. Association for Computational Linguistics (2020). https:\/\/doi.org\/10.18653\/v1\/2020.emnlp-main.141","DOI":"10.18653\/v1\/2020.emnlp-main.141"}],"container-title":["Lecture Notes in Computer Science","Computer Vision \u2013 ECCV 2024 Workshops"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/link.springer.com\/content\/pdf\/10.1007\/978-3-031-91581-9_24","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,9,6]],"date-time":"2025-09-06T16:16:30Z","timestamp":1757175390000},"score":1,"resource":{"primary":{"URL":"https:\/\/link.springer.com\/10.1007\/978-3-031-91581-9_24"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2025]]},"ISBN":["9783031915802","9783031915819"],"references-count":24,"URL":"https:\/\/doi.org\/10.1007\/978-3-031-91581-9_24","relation":{},"ISSN":["0302-9743","1611-3349"],"issn-type":[{"type":"print","value":"0302-9743"},{"type":"electronic","value":"1611-3349"}],"subject":[],"published":{"date-parts":[[2025]]},"assertion":[{"value":"12 May 2025","order":1,"name":"first_online","label":"First Online","group":{"name":"ChapterHistory","label":"Chapter History"}},{"value":"ECCV","order":1,"name":"conference_acronym","label":"Conference Acronym","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"European Conference on Computer Vision","order":2,"name":"conference_name","label":"Conference Name","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"Milan","order":3,"name":"conference_city","label":"Conference City","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"Italy","order":4,"name":"conference_country","label":"Conference Country","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"2024","order":5,"name":"conference_year","label":"Conference Year","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"29 September 2024","order":7,"name":"conference_start_date","label":"Conference Start Date","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"4 October 2024","order":8,"name":"conference_end_date","label":"Conference End Date","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"18","order":9,"name":"conference_number","label":"Conference Number","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"eccv2024","order":10,"name":"conference_id","label":"Conference ID","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"https:\/\/eccv2024.ecva.net\/","order":11,"name":"conference_url","label":"Conference URL","group":{"name":"ConferenceInfo","label":"Conference Information"}}]}}