{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,3,7]],"date-time":"2026-03-07T18:32:08Z","timestamp":1772908328232,"version":"3.50.1"},"publisher-location":"New York, NY, USA","reference-count":27,"publisher":"ACM","license":[{"start":{"date-parts":[[2024,5,24]],"date-time":"2024-05-24T00:00:00Z","timestamp":1716508800000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/creativecommons.org\/licenses\/by\/4.0\/"}],"content-domain":{"domain":["dl.acm.org"],"crossmark-restriction":true},"short-container-title":[],"published-print":{"date-parts":[[2024,5,24]]},"DOI":"10.1145\/3674029.3674045","type":"proceedings-article","created":{"date-parts":[[2024,9,11]],"date-time":"2024-09-11T12:25:22Z","timestamp":1726057522000},"page":"95-100","update-policy":"https:\/\/doi.org\/10.1145\/crossmark-policy","source":"Crossref","is-referenced-by-count":5,"title":["Enhancing Speech Emotion Recognition Using Deep Convolutional Neural Networks"],"prefix":"10.1145","author":[{"ORCID":"https:\/\/orcid.org\/0000-0002-1823-1304","authenticated-orcid":false,"given":"M M Manjurul","family":"Islam","sequence":"first","affiliation":[{"name":"Intelligent System Research Centre, Ulster University, UK"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-7136-6339","authenticated-orcid":false,"given":"Md Alamgir","family":"Kabir","sequence":"additional","affiliation":[{"name":"Artificial Intelligence and Intelligent Systems Research Group, Malardalen University, Sweden"}]},{"ORCID":"https:\/\/orcid.org\/0009-0003-1481-593X","authenticated-orcid":false,"given":"Alamin","family":"Sheikh","sequence":"additional","affiliation":[{"name":"American International University-Bangladesh, Bangladesh"}]},{"ORCID":"https:\/\/orcid.org\/0009-0007-1515-8731","authenticated-orcid":false,"given":"Muhammad","family":"Saiduzzaman","sequence":"additional","affiliation":[{"name":"American International University-Bangladesh, Bangladesh"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-6640-1868","authenticated-orcid":false,"given":"Abdelakram","family":"Hafid","sequence":"additional","affiliation":[{"name":"School of Innovation,Design and Engineering, Malardalen University, Sweden"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-7186-6210","authenticated-orcid":false,"given":"Saad","family":"Abdullah","sequence":"additional","affiliation":[{"name":"School of Innovation,Design and Engineering, Malardalen University, Sweden"}]}],"member":"320","published-online":{"date-parts":[[2024,9,11]]},"reference":[{"key":"e_1_3_2_1_1_1","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP43922.2022.9746679"},{"key":"e_1_3_2_1_2_1","doi-asserted-by":"publisher","DOI":"10.1109\/ISCAS.2010.5537589"},{"key":"e_1_3_2_1_3_1","doi-asserted-by":"publisher","DOI":"10.3390\/s20185212"},{"key":"e_1_3_2_1_4_1","doi-asserted-by":"publisher","DOI":"10.1109\/TCE.2021.3056421"},{"key":"e_1_3_2_1_5_1","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP49357.2023.10095036"},{"key":"e_1_3_2_1_6_1","doi-asserted-by":"publisher","DOI":"10.1109\/ICCVW54120.2021.00393"},{"key":"e_1_3_2_1_7_1","unstructured":"K Dupuis and KP Fuller. 2010. Toronto emotional speech set (TESS) Collection."},{"key":"e_1_3_2_1_8_1","volume-title":"Few-shot learning in emotion recognition of spontaneous speech using a siamese neural network with adaptive sample pair formation","author":"Feng Kexin","year":"2021","unstructured":"Kexin Feng and Theodora Chaspari. 2021. Few-shot learning in emotion recognition of spontaneous speech using a siamese neural network with adaptive sample pair formation. IEEE Transactions on Affective Computing (2021)."},{"key":"e_1_3_2_1_9_1","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2017.7953109"},{"key":"e_1_3_2_1_10_1","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2017.7952580"},{"key":"e_1_3_2_1_11_1","doi-asserted-by":"publisher","DOI":"10.1109\/ACCESS.2019.2927384"},{"key":"e_1_3_2_1_12_1","doi-asserted-by":"publisher","DOI":"10.3390\/s19122730"},{"key":"e_1_3_2_1_13_1","doi-asserted-by":"publisher","DOI":"10.1109\/ACCESS.2019.2936124"},{"key":"e_1_3_2_1_14_1","doi-asserted-by":"publisher","DOI":"10.1007\/s40747-021-00295-z"},{"key":"e_1_3_2_1_15_1","doi-asserted-by":"publisher","DOI":"10.1109\/ACCESS.2019.2938007"},{"key":"e_1_3_2_1_16_1","doi-asserted-by":"publisher","DOI":"10.3390\/s20010183"},{"key":"e_1_3_2_1_17_1","doi-asserted-by":"publisher","DOI":"10.3390\/math8122133"},{"key":"e_1_3_2_1_18_1","volume-title":"The Proceedings of the Multiconference on\" Computational Engineering in Systems Applications\", Vol.\u00a02. IEEE, 2169\u20132172","author":"Pan YC","year":"2006","unstructured":"YC Pan, MX Xu, LQ Liu, and PF Jia. 2006. Emotion-detecting based model selection for emotional speech recognition. In The Proceedings of the Multiconference on\" Computational Engineering in Systems Applications\", Vol.\u00a02. IEEE, 2169\u20132172."},{"key":"e_1_3_2_1_19_1","doi-asserted-by":"publisher","DOI":"10.1109\/ASRU51503.2021.9687971"},{"key":"e_1_3_2_1_20_1","volume-title":"Proceedings of the 3rd International Conference on Informatics, Electronics & Vision (ICIEV), Dhaka, Bangladesh. 23\u201324","author":"Sarker K","year":"2014","unstructured":"K Sarker and KR Alam. 2014. Emotion recognition from human speech: Emphasizing on relevant feature selection and majority voting technique. In Proceedings of the 3rd International Conference on Informatics, Electronics & Vision (ICIEV), Dhaka, Bangladesh. 23\u201324."},{"key":"e_1_3_2_1_21_1","volume-title":"Emotion recognition in audio and video using deep neural networks. arXiv preprint arXiv:2006.08129","author":"Singh Mandeep","year":"2020","unstructured":"Mandeep Singh and Yuan Fang. 2020. Emotion recognition in audio and video using deep neural networks. arXiv preprint arXiv:2006.08129 (2020)."},{"key":"e_1_3_2_1_22_1","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-63830-6_21"},{"key":"e_1_3_2_1_23_1","doi-asserted-by":"publisher","DOI":"10.1007\/s10772-018-9491-z"},{"key":"e_1_3_2_1_24_1","volume-title":"DeepEMO: deep learning for speech emotion recognition. arXiv preprint arXiv:2109.04081","author":"Togootogtokh Enkhtogtokh","year":"2021","unstructured":"Enkhtogtokh Togootogtokh and Christian Klasen. 2021. DeepEMO: deep learning for speech emotion recognition. arXiv preprint arXiv:2109.04081 (2021)."},{"key":"e_1_3_2_1_25_1","doi-asserted-by":"publisher","DOI":"10.3390\/s22041414"},{"key":"e_1_3_2_1_26_1","doi-asserted-by":"publisher","DOI":"10.12720\/jait.14.4.694-700"},{"key":"e_1_3_2_1_27_1","volume-title":"A transfer learning method for speech emotion recognition from automatic speech recognition. arXiv preprint arXiv:2008.02863","author":"Zhou Sitong","year":"2020","unstructured":"Sitong Zhou and Homayoon Beigi. 2020. A transfer learning method for speech emotion recognition from automatic speech recognition. arXiv preprint arXiv:2008.02863 (2020)."}],"event":{"name":"ICMLT 2024: 2024 9th International Conference on Machine Learning Technologies","location":"Oslo Norway","acronym":"ICMLT 2024"},"container-title":["2024 9th International Conference on Machine Learning Technologies (ICMLT)"],"original-title":[],"link":[{"URL":"https:\/\/dl.acm.org\/doi\/10.1145\/3674029.3674045","content-type":"unspecified","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/dl.acm.org\/doi\/pdf\/10.1145\/3674029.3674045","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,8,29]],"date-time":"2025-08-29T17:03:26Z","timestamp":1756487006000},"score":1,"resource":{"primary":{"URL":"https:\/\/dl.acm.org\/doi\/10.1145\/3674029.3674045"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2024,5,24]]},"references-count":27,"alternative-id":["10.1145\/3674029.3674045","10.1145\/3674029"],"URL":"https:\/\/doi.org\/10.1145\/3674029.3674045","relation":{},"subject":[],"published":{"date-parts":[[2024,5,24]]},"assertion":[{"value":"2024-09-11","order":3,"name":"published","label":"Published","group":{"name":"publication_history","label":"Publication History"}}]}}