{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2025,9,19]],"date-time":"2025-09-19T09:24:31Z","timestamp":1758273871100,"version":"3.44.0"},"publisher-location":"New York, NY, USA","reference-count":16,"publisher":"ACM","license":[{"start":{"date-parts":[[2024,6,26]],"date-time":"2024-06-26T00:00:00Z","timestamp":1719360000000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/www.acm.org\/publications\/policies\/copyright_policy#Background"}],"funder":[{"name":"DOEd Grant","award":["P116Z220008"],"award-info":[{"award-number":["P116Z220008"]}]},{"name":"NSF Grant","award":["2306109"],"award-info":[{"award-number":["2306109"]}]}],"content-domain":{"domain":["dl.acm.org"],"crossmark-restriction":true},"short-container-title":[],"published-print":{"date-parts":[[2024,6,26]]},"DOI":"10.1145\/3652037.3663943","type":"proceedings-article","created":{"date-parts":[[2024,6,26]],"date-time":"2024-06-26T12:30:38Z","timestamp":1719405038000},"page":"375-381","update-policy":"https:\/\/doi.org\/10.1145\/crossmark-policy","source":"Crossref","is-referenced-by-count":1,"title":["A Cross-Domain Exploration of Audio and Textual Data for Multi-Modal Emotion Detection"],"prefix":"10.1145","author":[{"ORCID":"https:\/\/orcid.org\/0009-0000-4217-0209","authenticated-orcid":false,"given":"Mohd","family":"Ariful Haque","sequence":"first","affiliation":[{"name":"Clark Atlanta University, United States"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-0257-9725","authenticated-orcid":false,"given":"Roy","family":"George","sequence":"additional","affiliation":[{"name":"Clark Atlanta University, United States"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0009-0009-8288-0411","authenticated-orcid":false,"given":"Rakib","family":"Hossain Rifat","sequence":"additional","affiliation":[{"name":"BRAC University, Bangladesh"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0009-0006-2931-4320","authenticated-orcid":false,"given":"Md","family":"Shihab Uddin","sequence":"additional","affiliation":[{"name":"Comilla University, Bangladesh"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0009-0009-4675-7248","authenticated-orcid":false,"given":"Marufa","family":"Kamal","sequence":"additional","affiliation":[{"name":"BRAC University, Bangladesh"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-6867-2653","authenticated-orcid":false,"given":"Kishor","family":"Datta Gupta","sequence":"additional","affiliation":[{"name":"Clark Atlanta University, United States"}],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"320","published-online":{"date-parts":[[2024,6,26]]},"reference":[{"key":"e_1_3_2_1_1_1","doi-asserted-by":"publisher","DOI":"10.1016\/j.procs.2020.08.027"},{"key":"e_1_3_2_1_2_1","doi-asserted-by":"crossref","unstructured":"U\u011fur Ayvaz H\u00fcseyin G\u00fcr\u00fcler Faheem Khan Naveed Ahmed and Taegkeun Whangbo. 2022. Automatic Speaker Recognition Using Mel-Frequency Cepstral Coefficients Through Machine Learning. (2022).","DOI":"10.32604\/cmc.2022.023278"},{"key":"e_1_3_2_1_3_1","unstructured":"bdotloh. 2022. empathetic-dialogues-contexts. (2022). https:\/\/huggingface.co\/datasets\/bdotloh\/empathetic-dialogues-contexts"},{"key":"e_1_3_2_1_4_1","volume-title":"Text-Based Emotion Recognition Using Deep Learning Approach. Computational Intelligence and Neuroscience 2022","author":"Bharti Santosh\u00a0Kumar","year":"2022","unstructured":"Santosh\u00a0Kumar Bharti, S Varadhaganapathy, Rajeev\u00a0Kumar Gupta, Prashant\u00a0Kumar Shukla, Mohamed Bouye, Simon\u00a0Karanja Hingaa, and Amena Mahmoud. 2022. Text-Based Emotion Recognition Using Deep Learning Approach. Computational Intelligence and Neuroscience 2022 (2022)."},{"key":"e_1_3_2_1_5_1","unstructured":"Jochen Hartmann. 2022. Emotion English DistilRoBERTa-base. https:\/\/huggingface.co\/j-hartmann\/emotion-english-distilroberta-base\/."},{"key":"e_1_3_2_1_6_1","volume-title":"Bidirectional LSTM-CRF models for sequence tagging. arXiv preprint arXiv:1508.01991","author":"Huang Zhiheng","year":"2015","unstructured":"Zhiheng Huang, Wei Xu, and Kai Yu. 2015. Bidirectional LSTM-CRF models for sequence tagging. arXiv preprint arXiv:1508.01991 (2015)."},{"key":"e_1_3_2_1_7_1","doi-asserted-by":"publisher","DOI":"10.1016\/j.bspc.2020.101894"},{"key":"e_1_3_2_1_8_1","volume-title":"Surrey audio-visual expressed emotion (savee) database","author":"Jackson Philip","year":"2014","unstructured":"Philip Jackson and SJUoSG Haq. 2014. Surrey audio-visual expressed emotion (savee) database. University of Surrey: Guildford, UK (2014)."},{"key":"e_1_3_2_1_9_1","unstructured":"Kaggle. 2019. Emotions dataset for NLP. (2019). https:\/\/www.kaggle.com\/datasets\/praveengovi\/emotions-dataset-for-nlp"},{"key":"e_1_3_2_1_10_1","unstructured":"Kaggle. 2020. Emotion Detection from Text. (2020). https:\/\/www.kaggle.com\/datasets\/pashupatigupta\/emotion-detection-from-text"},{"key":"e_1_3_2_1_11_1","doi-asserted-by":"publisher","DOI":"10.1371\/journal.pone.0196391"},{"key":"e_1_3_2_1_12_1","volume-title":"Image and Audio Data. In 2021 5th International Conference on Computing Methodologies and Communication (ICCMC). IEEE, 1660\u20131667","author":"Mehta Munish","year":"2021","unstructured":"Munish Mehta, Kanhav Gupta, Shubhangi Tiwari, 2021. A Review on Sentiment Analysis of Text, Image and Audio Data. In 2021 5th International Conference on Computing Methodologies and Communication (ICCMC). IEEE, 1660\u20131667."},{"key":"e_1_3_2_1_13_1","doi-asserted-by":"publisher","DOI":"10.1109\/ICCIT57492.2022.10055173"},{"key":"e_1_3_2_1_14_1","first-page":"2020","article-title":"Toronto emotional speech set (TESS)","volume":"1","author":"Pichora-Fuller M\u00a0Kathleen","year":"2020","unstructured":"M\u00a0Kathleen Pichora-Fuller and Kate Dupuis. 2020. Toronto emotional speech set (TESS). Scholars Portal Dataverse 1 (2020), 2020.","journal-title":"Scholars Portal Dataverse"},{"key":"e_1_3_2_1_15_1","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2023.semeval-1.99"},{"key":"e_1_3_2_1_16_1","doi-asserted-by":"publisher","unstructured":"Elvis Saravia Hsien-Chi\u00a0Toby Liu Yen-Hao Huang Junlin Wu and Yi-Shin Chen. 2018. CARER: Contextualized Affect Representations for Emotion Recognition. In Proceedings of the 2018 Conference on Empirical Methods in Natural Language Processing Ellen Riloff David Chiang Julia Hockenmaier and Jun\u2019ichi Tsujii (Eds.). Association for Computational Linguistics Brussels Belgium 3687\u20133697. https:\/\/doi.org\/10.18653\/v1\/D18-1404","DOI":"10.18653\/v1\/D18-1404"}],"event":{"name":"PETRA '24: The PErvasive Technologies Related to Assistive Environments Conference","acronym":"PETRA '24","location":"Crete Greece"},"container-title":["Proceedings of the 17th International Conference on PErvasive Technologies Related to Assistive Environments"],"original-title":[],"link":[{"URL":"https:\/\/dl.acm.org\/doi\/10.1145\/3652037.3663943","content-type":"unspecified","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/dl.acm.org\/doi\/pdf\/10.1145\/3652037.3663943","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,8,22]],"date-time":"2025-08-22T15:42:05Z","timestamp":1755877325000},"score":1,"resource":{"primary":{"URL":"https:\/\/dl.acm.org\/doi\/10.1145\/3652037.3663943"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2024,6,26]]},"references-count":16,"alternative-id":["10.1145\/3652037.3663943","10.1145\/3652037"],"URL":"https:\/\/doi.org\/10.1145\/3652037.3663943","relation":{},"subject":[],"published":{"date-parts":[[2024,6,26]]},"assertion":[{"value":"2024-06-26","order":3,"name":"published","label":"Published","group":{"name":"publication_history","label":"Publication History"}}]}}