{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2025,8,27]],"date-time":"2025-08-27T00:19:27Z","timestamp":1756253967562,"version":"3.44.0"},"publisher-location":"New York, NY, USA","reference-count":33,"publisher":"ACM","license":[{"start":{"date-parts":[[2023,12,6]],"date-time":"2023-12-06T00:00:00Z","timestamp":1701820800000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/www.acm.org\/publications\/policies\/copyright_policy#Background"}],"funder":[{"name":"JSPS KAKENHI","award":["JP19H05692"],"award-info":[{"award-number":["JP19H05692"]}]}],"content-domain":{"domain":["dl.acm.org"],"crossmark-restriction":true},"short-container-title":[],"published-print":{"date-parts":[[2023,12,6]]},"DOI":"10.1145\/3611380.3628557","type":"proceedings-article","created":{"date-parts":[[2023,12,30]],"date-time":"2023-12-30T12:03:31Z","timestamp":1703937811000},"page":"1-5","update-policy":"https:\/\/doi.org\/10.1145\/crossmark-policy","source":"Crossref","is-referenced-by-count":0,"title":["Speech Emotion Recognition using Threshold Fusion for Enhancing Audio Sensitivity"],"prefix":"10.1145","author":[{"ORCID":"https:\/\/orcid.org\/0000-0002-4173-6319","authenticated-orcid":false,"given":"Zhaojie","family":"Luo","sequence":"first","affiliation":[{"name":"SANKEN, Osaka University, JP"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0009-0007-0623-7673","authenticated-orcid":false,"given":"Stefan","family":"Christiansson","sequence":"additional","affiliation":[{"name":"KTH Royal Institute of Technology, SE"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-5056-4184","authenticated-orcid":false,"given":"Bence","family":"Lad\u00f3czki","sequence":"additional","affiliation":[{"name":"ELKH-BME Information Systems Research Group, Budapest University of Technology and Economics, HU"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-6052-600X","authenticated-orcid":false,"given":"Kazunori","family":"Komatani","sequence":"additional","affiliation":[{"name":"SANKEN, Osaka University, JP"}],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"320","published-online":{"date-parts":[[2023,12,30]]},"reference":[{"key":"e_1_3_2_1_1_1","doi-asserted-by":"publisher","DOI":"10.1145\/3292500.3330701"},{"key":"e_1_3_2_1_2_1","volume-title":"International conference on machine learning. PMLR, 199\u2013207","author":"Bardenet R\u00e9mi","year":"2013","unstructured":"R\u00e9mi Bardenet, M\u00e1ty\u00e1s Brendel, Bal\u00e1zs K\u00e9gl, and Michele Sebag. 2013. Collaborative hyperparameter tuning. In International conference on machine learning. PMLR, 199\u2013207."},{"key":"e_1_3_2_1_3_1","volume-title":"Algorithms for hyper-parameter optimization. Advances in neural information processing systems 24","author":"Bergstra James","year":"2011","unstructured":"James Bergstra, R\u00e9mi Bardenet, Yoshua Bengio, and Bal\u00e1zs K\u00e9gl. 2011. Algorithms for hyper-parameter optimization. Advances in neural information processing systems 24 (2011)."},{"key":"e_1_3_2_1_4_1","doi-asserted-by":"publisher","DOI":"10.1121\/1.400476"},{"key":"e_1_3_2_1_5_1","doi-asserted-by":"publisher","DOI":"10.1007\/s10579-008-9076-6"},{"key":"e_1_3_2_1_6_1","doi-asserted-by":"publisher","DOI":"10.1186\/s13636-016-0097-6"},{"key":"e_1_3_2_1_7_1","doi-asserted-by":"publisher","DOI":"10.1109\/TMM.2018.2856121"},{"key":"e_1_3_2_1_8_1","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2019.8682363"},{"key":"e_1_3_2_1_9_1","doi-asserted-by":"publisher","DOI":"10.1109\/79.911197"},{"key":"e_1_3_2_1_10_1","doi-asserted-by":"publisher","DOI":"10.1145\/1873951.1874246"},{"key":"e_1_3_2_1_11_1","doi-asserted-by":"publisher","DOI":"10.1016\/j.neunet.2005.03.006"},{"key":"e_1_3_2_1_12_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2014.223"},{"key":"e_1_3_2_1_13_1","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2019.8683679"},{"key":"e_1_3_2_1_14_1","volume-title":"2017 IEEE International Conference on Multimedia & Expo Workshops (ICMEW). IEEE, 657\u2013662","author":"Luo Zhaojie","year":"2017","unstructured":"Zhaojie Luo, Jinhui Chen, Tetsuya Takiguchi, and Yasuo Ariki. 2017. Facial expression recognition with deep age. In 2017 IEEE International Conference on Multimedia & Expo Workshops (ICMEW). IEEE, 657\u2013662."},{"key":"e_1_3_2_1_15_1","doi-asserted-by":"publisher","DOI":"10.1109\/TASLP.2022.3190715"},{"key":"e_1_3_2_1_16_1","doi-asserted-by":"publisher","DOI":"10.25080\/Majora-7b98e3ed-003"},{"key":"e_1_3_2_1_17_1","volume-title":"Decoding of inconsistent communications.Journal of personality and social psychology 6, 1","author":"Mehrabian Albert","year":"1967","unstructured":"Albert Mehrabian and Morton Wiener. 1967. Decoding of inconsistent communications.Journal of personality and social psychology 6, 1 (1967), 109."},{"key":"e_1_3_2_1_18_1","doi-asserted-by":"publisher","DOI":"10.1109\/ACII.2015.7344665"},{"key":"e_1_3_2_1_19_1","volume-title":"Ensemble methods for spoken emotion recognition in call-centres. Speech communication 49, 2","author":"Morrison Donn","year":"2007","unstructured":"Donn Morrison, Ruili Wang, and Liyanage\u00a0C De\u00a0Silva. 2007. Ensemble methods for spoken emotion recognition in call-centres. Speech communication 49, 2 (2007), 98\u2013112."},{"key":"e_1_3_2_1_20_1","volume-title":"Voice recognition algorithms using mel frequency cepstral coefficient (MFCC) and dynamic time warping (DTW) techniques. arXiv preprint arXiv:1003.4083","author":"Muda Lindasalwa","year":"2010","unstructured":"Lindasalwa Muda, Mumtaj Begam, and Irraivan Elamvazuthi. 2010. Voice recognition algorithms using mel frequency cepstral coefficient (MFCC) and dynamic time warping (DTW) techniques. arXiv preprint arXiv:1003.4083 (2010)."},{"key":"e_1_3_2_1_21_1","doi-asserted-by":"publisher","DOI":"10.1145\/3377930.3389817"},{"key":"e_1_3_2_1_22_1","volume-title":"Multi-modal attention for speech emotion recognition. arXiv preprint arXiv:2009.04107","author":"Pan Zexu","year":"2020","unstructured":"Zexu Pan, Zhaojie Luo, Jichen Yang, and Haizhou Li. 2020. Multi-modal attention for speech emotion recognition. arXiv preprint arXiv:2009.04107 (2020)."},{"key":"e_1_3_2_1_23_1","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/P17-1081"},{"key":"e_1_3_2_1_24_1","doi-asserted-by":"publisher","DOI":"10.1109\/ACCESS.2022.3219094"},{"key":"e_1_3_2_1_25_1","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2013-56"},{"key":"e_1_3_2_1_26_1","volume-title":"JSUT corpus: free large-scale Japanese speech corpus for end-to-end speech synthesis. arXiv preprint arXiv:1711.00354","author":"Sonobe Ryosuke","year":"2017","unstructured":"Ryosuke Sonobe, Shinnosuke Takamichi, and Hiroshi Saruwatari. 2017. JSUT corpus: free large-scale Japanese speech corpus for end-to-end speech synthesis. arXiv preprint arXiv:1711.00354 (2017)."},{"key":"e_1_3_2_1_27_1","first-page":"3","article-title":"Classification of human emotion from deap EEG signal using hybrid improved neural networks with cuckoo search","volume":"6","author":"Sreeshakthy M","year":"2016","unstructured":"M Sreeshakthy and J Preethi. 2016. Classification of human emotion from deap EEG signal using hybrid improved neural networks with cuckoo search. BRAIN. Broad Research in Artificial Intelligence and Neuroscience 6, 3-4 (2016), 60\u201373.","journal-title":"BRAIN. Broad Research in Artificial Intelligence and Neuroscience"},{"key":"e_1_3_2_1_28_1","volume-title":"Fusion with Hierarchical Graphs for Multimodal Emotion Recognition. In 2022 Asia-Pacific Signal and Information Processing Association Annual Summit and Conference (APSIPA ASC). IEEE, 1288\u20131296","author":"Tang Shuyun","year":"2022","unstructured":"Shuyun Tang, Zhaojie Luo, Guoshun Nan, Jun Baba, Yuichiro Yoshikawa, and Hiroshi Ishiguro. 2022. Fusion with Hierarchical Graphs for Multimodal Emotion Recognition. In 2022 Asia-Pacific Signal and Information Processing Association Annual Summit and Conference (APSIPA ASC). IEEE, 1288\u20131296."},{"key":"e_1_3_2_1_29_1","volume-title":"Efficient Estimation of Word Representations in Vector Space. arXiv preprint arXiv:1301.3781","author":"Jeffrey\u00a0Dean Tomas\u00a0Mikolov Greg Corrado","year":"2013","unstructured":"Greg Corrado Jeffrey\u00a0Dean Tomas\u00a0Mikolov, Kai\u00a0Chen. 2013. Efficient Estimation of Word Representations in Vector Space. arXiv preprint arXiv:1301.3781 (2013)."},{"key":"e_1_3_2_1_30_1","volume-title":"Multi-modal emotion recognition on iemocap dataset using deep learning. arXiv preprint arXiv:1804.05788","author":"Tripathi Samarth","year":"2018","unstructured":"Samarth Tripathi, Sarthak Tripathi, and Homayoon Beigi. 2018. Multi-modal emotion recognition on iemocap dataset using deep learning. arXiv preprint arXiv:1804.05788 (2018)."},{"key":"e_1_3_2_1_31_1","doi-asserted-by":"publisher","DOI":"10.1109\/ICME.2017.8019480"},{"key":"e_1_3_2_1_32_1","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP39728.2021.9413391"},{"key":"e_1_3_2_1_33_1","doi-asserted-by":"publisher","DOI":"10.1016\/j.specom.2021.11.006"}],"event":{"name":"MMAsia '23: ACM Multimedia Asia","sponsor":["SIGMM ACM Special Interest Group on Multimedia"],"location":"Tainan Taiwan","acronym":"MMAsia '23"},"container-title":["ACM Multimedia Asia Workshops"],"original-title":[],"link":[{"URL":"https:\/\/dl.acm.org\/doi\/10.1145\/3611380.3628557","content-type":"unspecified","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/dl.acm.org\/doi\/pdf\/10.1145\/3611380.3628557","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,8,26]],"date-time":"2025-08-26T19:09:51Z","timestamp":1756235391000},"score":1,"resource":{"primary":{"URL":"https:\/\/dl.acm.org\/doi\/10.1145\/3611380.3628557"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2023,12,6]]},"references-count":33,"alternative-id":["10.1145\/3611380.3628557","10.1145\/3611380"],"URL":"https:\/\/doi.org\/10.1145\/3611380.3628557","relation":{},"subject":[],"published":{"date-parts":[[2023,12,6]]},"assertion":[{"value":"2023-12-30","order":3,"name":"published","label":"Published","group":{"name":"publication_history","label":"Publication History"}}]}}