{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,2,5]],"date-time":"2026-02-05T11:35:41Z","timestamp":1770291341337,"version":"3.49.0"},"publisher-location":"New York, NY, USA","reference-count":22,"publisher":"ACM","license":[{"start":{"date-parts":[[2024,10,27]],"date-time":"2024-10-27T00:00:00Z","timestamp":1729987200000},"content-version":"vor","delay-in-days":367,"URL":"http:\/\/www.acm.org\/publications\/policies\/copyright_policy#Background"}],"funder":[{"DOI":"10.13039\/100000001","name":"National Science Foundation","doi-asserted-by":"publisher","award":["1834701, 2038853"],"award-info":[{"award-number":["1834701, 2038853"]}],"id":[{"id":"10.13039\/100000001","id-type":"DOI","asserted-by":"publisher"}]}],"content-domain":{"domain":["dl.acm.org"],"crossmark-restriction":true},"short-container-title":[],"published-print":{"date-parts":[[2023,10,26]]},"DOI":"10.1145\/3581783.3612855","type":"proceedings-article","created":{"date-parts":[[2023,10,27]],"date-time":"2023-10-27T07:27:40Z","timestamp":1698391660000},"page":"9511-9515","update-policy":"https:\/\/doi.org\/10.1145\/crossmark-policy","source":"Crossref","is-referenced-by-count":3,"title":["Effect of Attention and Self-Supervised Speech Embeddings on Non-Semantic Speech Tasks"],"prefix":"10.1145","author":[{"ORCID":"https:\/\/orcid.org\/0000-0002-3534-9136","authenticated-orcid":false,"given":"Payal","family":"Mohapatra","sequence":"first","affiliation":[{"name":"Northwestern University, Evanston, IL, USA"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0009-0003-5324-8667","authenticated-orcid":false,"given":"Akash","family":"Pandey","sequence":"additional","affiliation":[{"name":"Northwestern University, Evanston, IL, USA"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0009-0007-1602-5359","authenticated-orcid":false,"given":"Yueyuan","family":"Sui","sequence":"additional","affiliation":[{"name":"Northwestern University, Evanston, IL, USA"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-7700-4099","authenticated-orcid":false,"given":"Qi","family":"Zhu","sequence":"additional","affiliation":[{"name":"Northwestern University, Evanston, IL, USA"}],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"320","published-online":{"date-parts":[[2023,10,27]]},"reference":[{"key":"e_1_3_2_2_1_1","doi-asserted-by":"publisher","DOI":"10.1016\/j.procs.2020.08.027"},{"key":"e_1_3_2_2_2_1","volume-title":"wav2vec 2.0: A framework for self-supervised learning of speech representations. Advances in neural information processing systems","author":"Baevski Alexei","year":"2020","unstructured":"Alexei Baevski, Yuhao Zhou, Abdelrahman Mohamed, and Michael Auli. 2020. wav2vec 2.0: A framework for self-supervised learning of speech representations. Advances in neural information processing systems, Vol. 33 (2020), 12449--12460."},{"key":"e_1_3_2_2_3_1","volume-title":"IEMOCAP: Interactive emotional dyadic motion capture database. Language resources and evaluation","author":"Busso Carlos","year":"2008","unstructured":"Carlos Busso, Murtaza Bulut, Chi-Chun Lee, Abe Kazemzadeh, Emily Mower, Samuel Kim, Jeannette N Chang, Sungbok Lee, and Shrikanth S Narayanan. 2008. IEMOCAP: Interactive emotional dyadic motion capture database. Language resources and evaluation, Vol. 42 (2008), 335--359."},{"key":"e_1_3_2_2_4_1","first-page":"4508","article-title":"Speech emotion recognition with multi-task learning","volume":"2021","author":"Cai Xingyu","year":"2021","unstructured":"Xingyu Cai, Jiahong Yuan, Renjie Zheng, Liang Huang, and Kenneth Church. 2021. Speech emotion recognition with multi-task learning.. In Interspeech, Vol. 2021. 4508--4512.","journal-title":"Interspeech"},{"key":"e_1_3_2_2_5_1","doi-asserted-by":"publisher","DOI":"10.1037\/amp0000399"},{"key":"e_1_3_2_2_6_1","doi-asserted-by":"publisher","DOI":"10.1016\/j.tics.2020.11.004"},{"key":"e_1_3_2_2_7_1","doi-asserted-by":"publisher","DOI":"10.1109\/SPIN.2017.8049931"},{"key":"e_1_3_2_2_8_1","doi-asserted-by":"publisher","DOI":"10.1109\/TASLP.2021.3122291"},{"key":"e_1_3_2_2_9_1","volume-title":"Faiqa Hanif, and Ghulam Mujtaba.","author":"Jahangir Rashid","year":"2021","unstructured":"Rashid Jahangir, Ying Wah Teh, Faiqa Hanif, and Ghulam Mujtaba. 2021. Deep learning approaches for speech emotion recognition: State of the art and research challenges. Multimedia Tools and Applications (2021), 1--68."},{"key":"e_1_3_2_2_10_1","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP49357.2023.10094673"},{"key":"e_1_3_2_2_11_1","doi-asserted-by":"publisher","DOI":"10.1016\/j.procs.2015.10.020"},{"key":"e_1_3_2_2_12_1","doi-asserted-by":"publisher","DOI":"10.1109\/WiSPNET.2017.8300161"},{"key":"e_1_3_2_2_13_1","volume-title":"Efficient Stuttering Event Detection Using Siamese Networks. In ICASSP 2023--2023 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP). IEEE, 1--5.","author":"Mohapatra Payal","year":"2023","unstructured":"Payal Mohapatra, Bashima Islam, Md Tamzeed Islam, Ruochen Jiao, and Qi Zhu. 2023. Efficient Stuttering Event Detection Using Siamese Networks. In ICASSP 2023--2023 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP). IEEE, 1--5."},{"key":"e_1_3_2_2_14_1","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP43922.2022.9747870"},{"key":"e_1_3_2_2_15_1","doi-asserted-by":"publisher","DOI":"10.1109\/RADIOELEK.2019.8733432"},{"key":"e_1_3_2_2_16_1","doi-asserted-by":"crossref","unstructured":"Bj\u00f6rn W Schuller Anton Batliner Shahin Amiriparian Alexander Barnhill Maurice Gerczuk Andreas Triantafyllopoulos Alice Baird Panagiotis Tzirakis Chris Gagne Alan S Cowen et al. 2023. The ACM Multimedia 2023 Computational Paralinguistics Challenge: Emotion Share & Requests. arXiv preprint arXiv:2304.14882 (2023).","DOI":"10.1145\/3581783.3612835"},{"key":"e_1_3_2_2_17_1","doi-asserted-by":"publisher","DOI":"10.3390\/ijerph20065140"},{"key":"e_1_3_2_2_18_1","doi-asserted-by":"publisher","DOI":"10.2307\/1412159"},{"key":"e_1_3_2_2_19_1","doi-asserted-by":"publisher","DOI":"10.1109\/JPROC.2023.3250266"},{"key":"e_1_3_2_2_20_1","volume-title":"Advances in Neural Information Processing Systems","author":"Vaswani Ashish","year":"2017","unstructured":"Ashish Vaswani, Noam Shazeer, Niki Parmar, Jakob Uszkoreit, Llion Jones, Aidan N Gomez, ?ukasz Kaiser, and Illia Polosukhin. 2017. Attention is All you Need. In Advances in Neural Information Processing Systems, I. Guyon, U. Von Luxburg, S. Bengio, H. Wallach, R. Fergus, S. Vishwanathan, and R. Garnett (Eds.), Vol. 30. Curran Associates, Inc. https:\/\/proceedings.neurips.cc\/paper_files\/paper\/2017\/file\/3f5ee243547dee91fbd053c1c4a845aa-Paper.pdf"},{"key":"e_1_3_2_2_21_1","volume-title":"Dawn of the transformer era in speech emotion recognition: closing the valence gap","author":"Wagner Johannes","year":"2023","unstructured":"Johannes Wagner, Andreas Triantafyllopoulos, Hagen Wierstorf, Maximilian Schmitt, Felix Burkhardt, Florian Eyben, and Bj\u00f6rn W Schuller. 2023. Dawn of the transformer era in speech emotion recognition: closing the valence gap. IEEE Transactions on Pattern Analysis and Machine Intelligence (2023)."},{"key":"e_1_3_2_2_22_1","doi-asserted-by":"publisher","DOI":"10.1109\/ICSC56153.2023.00032"}],"event":{"name":"MM '23: The 31st ACM International Conference on Multimedia","location":"Ottawa ON Canada","acronym":"MM '23","sponsor":["SIGMM ACM Special Interest Group on Multimedia"]},"container-title":["Proceedings of the 31st ACM International Conference on Multimedia"],"original-title":[],"link":[{"URL":"https:\/\/dl.acm.org\/doi\/10.1145\/3581783.3612855","content-type":"unspecified","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/dl.acm.org\/doi\/pdf\/10.1145\/3581783.3612855","content-type":"application\/pdf","content-version":"vor","intended-application":"syndication"},{"URL":"https:\/\/dl.acm.org\/doi\/pdf\/10.1145\/3581783.3612855","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,8,22]],"date-time":"2025-08-22T00:13:30Z","timestamp":1755821610000},"score":1,"resource":{"primary":{"URL":"https:\/\/dl.acm.org\/doi\/10.1145\/3581783.3612855"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2023,10,26]]},"references-count":22,"alternative-id":["10.1145\/3581783.3612855","10.1145\/3581783"],"URL":"https:\/\/doi.org\/10.1145\/3581783.3612855","relation":{},"subject":[],"published":{"date-parts":[[2023,10,26]]},"assertion":[{"value":"2023-10-27","order":3,"name":"published","label":"Published","group":{"name":"publication_history","label":"Publication History"}}]}}