{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2025,9,8]],"date-time":"2025-09-08T06:06:38Z","timestamp":1757311598158,"version":"3.40.3"},"publisher-location":"Cham","reference-count":13,"publisher":"Springer Nature Switzerland","isbn-type":[{"type":"print","value":"9783031779145"},{"type":"electronic","value":"9783031779152"}],"license":[{"start":{"date-parts":[[2024,11,29]],"date-time":"2024-11-29T00:00:00Z","timestamp":1732838400000},"content-version":"tdm","delay-in-days":0,"URL":"https:\/\/www.springernature.com\/gp\/researchers\/text-and-data-mining"},{"start":{"date-parts":[[2024,11,29]],"date-time":"2024-11-29T00:00:00Z","timestamp":1732838400000},"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\/978-3-031-77915-2_24","type":"book-chapter","created":{"date-parts":[[2024,11,28]],"date-time":"2024-11-28T11:54:20Z","timestamp":1732794860000},"page":"320-326","update-policy":"https:\/\/doi.org\/10.1007\/springer_crossmark_policy","source":"Crossref","is-referenced-by-count":1,"title":["Audio-Visual Emotion Recognition Using Deep Learning Methods"],"prefix":"10.1007","author":[{"given":"Mukhambet","family":"Tolegenov","sequence":"first","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-5263-596X","authenticated-orcid":false,"given":"Lakshmi Babu","family":"Saheer","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-2697-8288","authenticated-orcid":false,"given":"Mahdi Maktabdar","family":"Oghaz","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"297","published-online":{"date-parts":[[2024,11,29]]},"reference":[{"key":"24_CR1","doi-asserted-by":"publisher","unstructured":"Breuer, R., Kimmel, R.: A Deep Learning Perspective on the Origin of Facial Expressions. arXiv.org. https:\/\/doi.org\/10.48550\/arxiv.1705.01842 (2017)","DOI":"10.48550\/arxiv.1705.01842"},{"issue":"22","key":"24_CR2","doi-asserted-by":"publisher","first-page":"7530","DOI":"10.3390\/s21227530","volume":"21","author":"S Chen","year":"2021","unstructured":"Chen, S., Zhang, M., Yang, X., Zhao, Z., Zou, T., Sun, X.: The impact of attention mechanisms on speech emotion recognition. Sensors 21(22), 7530 (2021). https:\/\/doi.org\/10.3390\/s21227530","journal-title":"Sensors"},{"issue":"2","key":"24_CR3","doi-asserted-by":"publisher","first-page":"133","DOI":"10.1007\/s10919-019-00293-3","volume":"43","author":"D Keltner","year":"2019","unstructured":"Keltner, D., Sauter, D., Tracy, J., Cowen, A.: Emotional expression: advances in basic emotion theory. J. Nonverbal Behav. 43(2), 133\u2013160 (2019). https:\/\/doi.org\/10.1007\/s10919-019-00293-3","journal-title":"J. Nonverbal Behav."},{"key":"24_CR4","doi-asserted-by":"crossref","unstructured":"Khan, W., Qudous, H., Farhan, A.: Speech emotion recognition using feature fusion: a hybrid approach to deep learning. Multimedia Tools Appl. 1\u201328 (2024)","DOI":"10.1007\/s11042-024-18316-7"},{"key":"24_CR5","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, 1440 (2023)","journal-title":"Entropy"},{"issue":"5","key":"24_CR6","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"},{"issue":"2","key":"24_CR7","doi-asserted-by":"publisher","first-page":"715","DOI":"10.1109\/TCDS.2021.3071170","volume":"14","author":"W Liu","year":"2022","unstructured":"Liu, W., Qiu, J.-L., Zheng, W.-L., Lu, B.-L.: Comparing recognition performance and robustness of multimodal deep learning models for multimodal emotion recognition. IEEE Trans. Cogn. Dev. Syst. 14(2), 715\u2013729 (2022). https:\/\/doi.org\/10.1109\/TCDS.2021.3071170","journal-title":"IEEE Trans. Cogn. Dev. Syst."},{"issue":"22","key":"24_CR8","doi-asserted-by":"publisher","first-page":"7665","DOI":"10.3390\/s21227665","volume":"21","author":"C Luna-Jim\u00e9nez","year":"2021","unstructured":"Luna-Jim\u00e9nez, C., Griol, D., Callejas, Z., Kleinlein, R., Montero, J.M., Fern\u00e1ndez-Mart\u00ednez, F.: Multimodal emotion recognition on RAVDESS dataset using transfer learning. Sensors 21(22), 7665 (2021). https:\/\/doi.org\/10.3390\/s21227665","journal-title":"Sensors"},{"key":"24_CR9","doi-asserted-by":"publisher","DOI":"10.1016\/j.knosys.2022.108580","volume":"244","author":"AI Middya","year":"2022","unstructured":"Middya, A.I., Nag, B., Roy, S.: Deep learning based multimodal emotion recognition using model-level fusion of audio-visual modalities. Knowl.-Based Syst. 244, 108580 (2022). https:\/\/doi.org\/10.1016\/j.knosys.2022.108580","journal-title":"Knowl.-Based Syst."},{"key":"24_CR10","doi-asserted-by":"publisher","DOI":"10.1016\/j.bspc.2022.103970","volume":"78","author":"M Sharafi","year":"2022","unstructured":"Sharafi, M., Yazdchi, M., Rasti, R., Nasimi, F.: A novel spatio-temporal convolutional neural framework for multimodal emotion recognition. Biomed. Signal Process. Control 78, 103970 (2022). https:\/\/doi.org\/10.1016\/j.bspc.2022.103970","journal-title":"Biomed. Signal Process. Control"},{"issue":"6","key":"24_CR11","doi-asserted-by":"publisher","first-page":"5140","DOI":"10.3390\/ijerph20065140","volume":"20","author":"J Singh","year":"2023","unstructured":"Singh, J., Saheer, L.B., Faust, O.: Speech emotion recognition using attention model. Int. J. Environ. Res. Public Health 20(6), 5140 (2023). https:\/\/doi.org\/10.3390\/ijerph20065140","journal-title":"Int. J. Environ. Res. Public Health"},{"key":"24_CR12","doi-asserted-by":"publisher","first-page":"784514","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\u2013784514 (2021). https:\/\/doi.org\/10.3389\/fnbot.2021.784514","journal-title":"Front. Neurorobotics"},{"issue":"10","key":"24_CR13","doi-asserted-by":"publisher","first-page":"3030","DOI":"10.1109\/TCSVT.2017.2719043","volume":"28","author":"S Zhang","year":"2018","unstructured":"Zhang, S., Zhang, S., Huang, T., Gao, W., Tian, Q.: Learning affective features with a hybrid deep model for audio-visual emotion recognition. IEEE Trans. Circuits Syst. Video Technol. 28(10), 3030\u20133043 (2018). https:\/\/doi.org\/10.1109\/TCSVT.2017.2719043","journal-title":"IEEE Trans. Circuits Syst. Video Technol."}],"container-title":["Lecture Notes in Computer Science","Artificial Intelligence XLI"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/link.springer.com\/content\/pdf\/10.1007\/978-3-031-77915-2_24","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2024,11,28]],"date-time":"2024-11-28T12:11:56Z","timestamp":1732795916000},"score":1,"resource":{"primary":{"URL":"https:\/\/link.springer.com\/10.1007\/978-3-031-77915-2_24"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2024,11,29]]},"ISBN":["9783031779145","9783031779152"],"references-count":13,"URL":"https:\/\/doi.org\/10.1007\/978-3-031-77915-2_24","relation":{},"ISSN":["0302-9743","1611-3349"],"issn-type":[{"type":"print","value":"0302-9743"},{"type":"electronic","value":"1611-3349"}],"subject":[],"published":{"date-parts":[[2024,11,29]]},"assertion":[{"value":"29 November 2024","order":1,"name":"first_online","label":"First Online","group":{"name":"ChapterHistory","label":"Chapter History"}},{"value":"SGAI","order":1,"name":"conference_acronym","label":"Conference Acronym","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"International Conference on Innovative Techniques and Applications of Artificial Intelligence","order":2,"name":"conference_name","label":"Conference Name","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"Cambridge","order":3,"name":"conference_city","label":"Conference City","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"United Kingdom","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":"17 December 2024","order":7,"name":"conference_start_date","label":"Conference Start Date","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"19 December 2024","order":8,"name":"conference_end_date","label":"Conference End Date","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"44","order":9,"name":"conference_number","label":"Conference Number","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"sgai2024","order":10,"name":"conference_id","label":"Conference ID","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"http:\/\/bcs-sgai.org\/ai2024\/","order":11,"name":"conference_url","label":"Conference URL","group":{"name":"ConferenceInfo","label":"Conference Information"}}]}}