{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,8,12]],"date-time":"2026-08-12T16:23:49Z","timestamp":1786551829698,"version":"build-2736575974"},"publisher-location":"New York, NY, USA","reference-count":29,"publisher":"ACM","license":[{"start":{"date-parts":[[2020,10,25]],"date-time":"2020-10-25T00:00:00Z","timestamp":1603584000000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/www.acm.org\/publications\/policies\/copyright_policy#Background"}],"content-domain":{"domain":["dl.acm.org"],"crossmark-restriction":true},"short-container-title":[],"published-print":{"date-parts":[[2020,10,25]]},"DOI":"10.1145\/3395035.3425255","type":"proceedings-article","created":{"date-parts":[[2020,12,28]],"date-time":"2020-12-28T05:36:37Z","timestamp":1609133797000},"page":"12-16","update-policy":"https:\/\/doi.org\/10.1145\/crossmark-policy","source":"Crossref","is-referenced-by-count":19,"title":["Speech Emotion Recognition among Elderly Individuals using Multimodal Fusion and Transfer Learning"],"prefix":"10.1145","author":[{"given":"George","family":"Boateng","sequence":"first","affiliation":[{"name":"ETH Z\u00fcrich, Zurich, Switzerland"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Tobias","family":"Kowatsch","sequence":"additional","affiliation":[{"name":"ETH Z\u00fcrich & University of St.Gallen, St.Gallen, Switzerland"}],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"320","published-online":{"date-parts":[[2020,12,27]]},"reference":[{"key":"e_1_3_2_1_1_1","unstructured":"[n.d.]. imbalanced-learn. https:\/\/imbalanced-learn.readthedocs.io\/en\/stable\/index.html. Accessed: 2020-05-1.  [n.d.]. imbalanced-learn. https:\/\/imbalanced-learn.readthedocs.io\/en\/stable\/index.html. Accessed: 2020-05-1."},{"key":"e_1_3_2_1_2_1","unstructured":"[n.d.]. Open Sourcing German BERT. https:\/\/deepset.ai\/german-bert. Accessed: 2020-05-1.  [n.d.]. Open Sourcing German BERT. https:\/\/deepset.ai\/german-bert. Accessed: 2020-05-1."},{"key":"e_1_3_2_1_3_1","volume-title":"IEMOCAP: Interactive emotional dyadic motion capture database. Language resources and evaluation","author":"Busso Carlos","year":"2008"},{"key":"e_1_3_2_1_4_1","doi-asserted-by":"crossref","unstructured":"Sandeep Nallan Chakravarthula Haoqi Li Shao-Yen Tseng Maija Reblin and Panayiotis Georgiou. 2019. Predicting Behavior in Cancer-Afflicted Patient and Spouse Interactions using Speech and Language. (2019).  Sandeep Nallan Chakravarthula Haoqi Li Shao-Yen Tseng Maija Reblin and Panayiotis Georgiou. 2019. Predicting Behavior in Cancer-Afflicted Patient and Spouse Interactions using Speech and Language. (2019).","DOI":"10.21437\/Interspeech.2019-1888"},{"key":"e_1_3_2_1_5_1","volume-title":"Keras: The python deep learning library","author":"Chollet Francc","year":"2018"},{"key":"e_1_3_2_1_6_1","volume-title":"Bert: Pre-training of deep bidirectional transformers for language understanding. arXiv preprint arXiv:1810.04805","author":"Devlin Jacob","year":"2018"},{"key":"e_1_3_2_1_7_1","doi-asserted-by":"publisher","DOI":"10.3389\/fcomp.2020.00009"},{"key":"e_1_3_2_1_8_1","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2017.7952261"},{"key":"e_1_3_2_1_9_1","volume-title":"Jort F Gemmeke, Aren Jansen, R Channing Moore, Manoj Plakal, Devin Platt, Rif A Saurous, Bryan Seybold, et al.","author":"Hershey Shawn","year":"2017"},{"key":"e_1_3_2_1_10_1","doi-asserted-by":"publisher","DOI":"10.1162\/neco.1997.9.8.1735"},{"key":"e_1_3_2_1_11_1","volume-title":"Mobilenets: Efficient convolutional neural networks for mobile vision applications. arXiv preprint arXiv:1704.04861","author":"Howard Andrew G","year":"2017"},{"key":"e_1_3_2_1_12_1","volume-title":"Universal language model fine-tuning for text classification. arXiv preprint arXiv:1801.06146","author":"Howard Jeremy","year":"2018"},{"key":"e_1_3_2_1_13_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2014.223"},{"key":"e_1_3_2_1_14_1","doi-asserted-by":"publisher","DOI":"10.1145\/2818346.2830593"},{"key":"e_1_3_2_1_15_1","volume-title":"20th Annual Conference of the International Speech Communication Association","author":"Onu Charles C.","year":"2019"},{"key":"e_1_3_2_1_16_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2014.222"},{"key":"e_1_3_2_1_17_1","doi-asserted-by":"publisher","DOI":"10.1109\/RADIOELEK.2019.8733432"},{"key":"e_1_3_2_1_18_1","unstructured":"Adam Paszke Sam Gross Francisco Massa Adam Lerer James Bradbury Gregory Chanan Trevor Killeen Zeming Lin Natalia Gimelshein Luca Antiga etal 2019. PyTorch: An imperative style high-performance deep learning library. In Advances in Neural Information Processing Systems. 8024--8035.  Adam Paszke Sam Gross Francisco Massa Adam Lerer James Bradbury Gregory Chanan Trevor Killeen Zeming Lin Natalia Gimelshein Luca Antiga et al. 2019. PyTorch: An imperative style high-performance deep learning library. In Advances in Neural Information Processing Systems. 8024--8035."},{"key":"e_1_3_2_1_19_1","doi-asserted-by":"publisher","DOI":"10.5555\/1953048.2078195"},{"key":"e_1_3_2_1_20_1","doi-asserted-by":"publisher","DOI":"10.1016\/j.inffus.2017.02.003"},{"key":"e_1_3_2_1_21_1","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/D19-1410"},{"key":"e_1_3_2_1_22_1","volume-title":"Making Monolingual Sentence Embeddings Multilingual using Knowledge Distillation. arXiv preprint arXiv:2004.09813 (04","author":"Reimers Nils","year":"2020"},{"key":"e_1_3_2_1_23_1","volume-title":"Preliminary proceedings of the 15th Conference on Natural Language Processing (KONVENS","author":"Risch Julian","year":"2019"},{"key":"e_1_3_2_1_24_1","doi-asserted-by":"publisher","DOI":"10.1016\/j.futures.2016.07.002"},{"key":"e_1_3_2_1_25_1","volume-title":"Asian Conference on Pattern Recognition. Springer, 435--448","author":"Sahoo Sourav","year":"2019"},{"key":"e_1_3_2_1_26_1","volume-title":"The INTERSPEECH 2020 Computational Paralinguistics Challenge: Elderly Emotion, Breathing & Masks. In Proceedings of Interspeech","author":"Schuller Bjorn W.","year":"2020"},{"key":"e_1_3_2_1_27_1","doi-asserted-by":"publisher","DOI":"10.5555\/2627435.2670313"},{"key":"e_1_3_2_1_28_1","doi-asserted-by":"publisher","DOI":"10.1109\/ICOSP.2006.345752"},{"key":"e_1_3_2_1_29_1","unstructured":"Zixiaofan Yang and Julia Hirschberg. 2018. Predicting Arousal and Valence from Waveforms and Spectrograms Using Deep Neural Networks.. In Interspeech. 3092--3096.  Zixiaofan Yang and Julia Hirschberg. 2018. Predicting Arousal and Valence from Waveforms and Spectrograms Using Deep Neural Networks.. In Interspeech. 3092--3096."}],"event":{"name":"ICMI '20: INTERNATIONAL CONFERENCE ON MULTIMODAL INTERACTION","location":"Virtual Event Netherlands","acronym":"ICMI '20","sponsor":["SIGCHI ACM Special Interest Group on Computer-Human Interaction"]},"container-title":["Companion Publication of the 2020 International Conference on Multimodal Interaction"],"original-title":[],"link":[{"URL":"https:\/\/dl.acm.org\/doi\/10.1145\/3395035.3425255","content-type":"unspecified","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/dl.acm.org\/doi\/pdf\/10.1145\/3395035.3425255","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,6,17]],"date-time":"2025-06-17T20:48:01Z","timestamp":1750193281000},"score":1,"resource":{"primary":{"URL":"https:\/\/dl.acm.org\/doi\/10.1145\/3395035.3425255"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2020,10,25]]},"references-count":29,"alternative-id":["10.1145\/3395035.3425255","10.1145\/3395035"],"URL":"https:\/\/doi.org\/10.1145\/3395035.3425255","relation":{},"subject":[],"published":{"date-parts":[[2020,10,25]]},"assertion":[{"value":"2020-12-27","order":2,"name":"published","label":"Published","group":{"name":"publication_history","label":"Publication History"}}]}}