{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,1,2]],"date-time":"2026-01-02T07:39:00Z","timestamp":1767339540438,"version":"3.41.0"},"publisher-location":"New York, NY, USA","reference-count":31,"publisher":"ACM","license":[{"start":{"date-parts":[[2022,8,4]],"date-time":"2022-08-04T00:00:00Z","timestamp":1659571200000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/creativecommons.org\/licenses\/by\/4.0\/"}],"funder":[{"DOI":"10.13039\/100000001","name":"National Science Foundation","doi-asserted-by":"publisher","award":["DMS-2134248"],"award-info":[{"award-number":["DMS-2134248"]}],"id":[{"id":"10.13039\/100000001","id-type":"DOI","asserted-by":"publisher"}]},{"name":"Army Research Office Early Career Award","award":["ECCS-2037304"],"award-info":[{"award-number":["ECCS-2037304"]}]}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":[],"published-print":{"date-parts":[[2022,8,4]]},"DOI":"10.1145\/3556384.3556414","type":"proceedings-article","created":{"date-parts":[[2022,10,29]],"date-time":"2022-10-29T10:51:35Z","timestamp":1667040695000},"page":"197-202","source":"Crossref","is-referenced-by-count":7,"title":["Hierarchical Multi-modal Transformer for Automatic Detection of COVID-19"],"prefix":"10.1145","author":[{"given":"Shuyun","family":"Tang","sequence":"first","affiliation":[{"name":"Virufy AI Research, University of California, Berkeley, USA"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Xinying","family":"Hu","sequence":"additional","affiliation":[{"name":"Virufy AI Research, University of California, Berkeley, USA"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Les","family":"Atlas","sequence":"additional","affiliation":[{"name":"University of Washington, USA"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Amil","family":"Khanzada","sequence":"additional","affiliation":[{"name":"Virufy AI Research, University of California, Berkeley, USA"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Mert","family":"Pilanci","sequence":"additional","affiliation":[{"name":"Stanford University, USA"}],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"320","published-online":{"date-parts":[[2022,10,29]]},"reference":[{"key":"e_1_3_2_1_1_1","unstructured":"[n.d.]. World Health Organization. Coronavirus (COVID-19) Cases and Deaths. https:\/\/data.humdata.org\/dataset\/coronavirus-covid-19-cases-and-deaths  [n.d.]. World Health Organization. Coronavirus (COVID-19) Cases and Deaths. https:\/\/data.humdata.org\/dataset\/coronavirus-covid-19-cases-and-deaths"},{"key":"e_1_3_2_1_2_1","volume-title":"Cough Sound Analysis for Pneumonia and Asthma Classification in Pediatric Population. In 2015 6th International Conference on Intelligent Systems, Modelling and Simulation. 127\u2013131","author":"Amrulloh Yusuf","year":"2015","unstructured":"Yusuf Amrulloh , Udantha Abeyratne , Vinayak Swarnkar , and Rina Triasih . 2015 . Cough Sound Analysis for Pneumonia and Asthma Classification in Pediatric Population. In 2015 6th International Conference on Intelligent Systems, Modelling and Simulation. 127\u2013131 . https:\/\/doi.org\/10.1109\/ISMS.2015.41 10.1109\/ISMS.2015.41 Yusuf Amrulloh, Udantha Abeyratne, Vinayak Swarnkar, and Rina Triasih. 2015. Cough Sound Analysis for Pneumonia and Asthma Classification in Pediatric Population. In 2015 6th International Conference on Intelligent Systems, Modelling and Simulation. 127\u2013131. https:\/\/doi.org\/10.1109\/ISMS.2015.41"},{"key":"e_1_3_2_1_3_1","volume-title":"Virufy: Global Applicability of Crowdsourced and Clinical Datasets for AI Detection of COVID-19 from Cough. https:\/\/doi.org\/10.48550\/ARXIV.2011.13320","author":"Chaudhari Gunvant","year":"2020","unstructured":"Gunvant Chaudhari , Xinyi Jiang , Ahmed Fakhry , Asriel Han , Jaclyn Xiao , Sabrina Shen , and Amil Khanzada . 2020 . Virufy: Global Applicability of Crowdsourced and Clinical Datasets for AI Detection of COVID-19 from Cough. https:\/\/doi.org\/10.48550\/ARXIV.2011.13320 10.48550\/ARXIV.2011.13320 Gunvant Chaudhari, Xinyi Jiang, Ahmed Fakhry, Asriel Han, Jaclyn Xiao, Sabrina Shen, and Amil Khanzada. 2020. Virufy: Global Applicability of Crowdsourced and Clinical Datasets for AI Detection of COVID-19 from Cough. https:\/\/doi.org\/10.48550\/ARXIV.2011.13320"},{"key":"e_1_3_2_1_4_1","doi-asserted-by":"publisher","DOI":"10.1109\/TASSP.1980.1163420"},{"key":"e_1_3_2_1_5_1","unstructured":"Alexey Dosovitskiy Lucas Beyer Alexander Kolesnikov Dirk Weissenborn Xiaohua Zhai Thomas Unterthiner Mostafa Dehghani Matthias Minderer Georg Heigold Sylvain Gelly Jakob Uszkoreit and Neil Houlsby. 2020. An Image is Worth 16x16 Words: Transformers for Image Recognition at Scale. CoRR abs\/2010.11929(2020). arXiv:2010.11929https:\/\/arxiv.org\/abs\/2010.11929  Alexey Dosovitskiy Lucas Beyer Alexander Kolesnikov Dirk Weissenborn Xiaohua Zhai Thomas Unterthiner Mostafa Dehghani Matthias Minderer Georg Heigold Sylvain Gelly Jakob Uszkoreit and Neil Houlsby. 2020. An Image is Worth 16x16 Words: Transformers for Image Recognition at Scale. CoRR abs\/2010.11929(2020). arXiv:2010.11929https:\/\/arxiv.org\/abs\/2010.11929"},{"key":"e_1_3_2_1_6_1","volume-title":"Virufy: A Multi-Branch Deep Learning Network for Automated Detection of COVID-19. https:\/\/doi.org\/10.48550\/ARXIV.2103.01806","author":"Fakhry Ahmed","year":"2021","unstructured":"Ahmed Fakhry , Xinyi Jiang , Jaclyn Xiao , Gunvant Chaudhari , Asriel Han , and Amil Khanzada . 2021 . Virufy: A Multi-Branch Deep Learning Network for Automated Detection of COVID-19. https:\/\/doi.org\/10.48550\/ARXIV.2103.01806 10.48550\/ARXIV.2103.01806 Ahmed Fakhry, Xinyi Jiang, Jaclyn Xiao, Gunvant Chaudhari, Asriel Han, and Amil Khanzada. 2021. Virufy: A Multi-Branch Deep Learning Network for Automated Detection of COVID-19. https:\/\/doi.org\/10.48550\/ARXIV.2103.01806"},{"key":"e_1_3_2_1_7_1","first-page":"571","article-title":"AST","volume":"2021","author":"Gong Yuan","year":"2021","unstructured":"Yuan Gong , Yu-An Chung , and James Glass . 2021 . AST : Audio Spectrogram Transformer. In Proc. Interspeech 2021. 571 \u2013 575 . https:\/\/doi.org\/10.21437\/Interspeech.2021-698 10.21437\/Interspeech.2021-698 Yuan Gong, Yu-An Chung, and James Glass. 2021. AST: Audio Spectrogram Transformer. In Proc. Interspeech 2021. 571\u2013575. https:\/\/doi.org\/10.21437\/Interspeech.2021-698","journal-title":"Audio Spectrogram Transformer. In Proc. Interspeech"},{"key":"e_1_3_2_1_8_1","volume-title":"PSLA: Improving Audio Tagging with Pretraining, Sampling, Labeling, and Aggregation","author":"Gong Yuan","year":"2021","unstructured":"Yuan Gong , Yu-An Chung , and James Glass . 2021 . PSLA: Improving Audio Tagging with Pretraining, Sampling, Labeling, and Aggregation . IEEE\/ACM Transactions on Audio, Speech, and Language Processing ( 2021). https:\/\/doi.org\/10.1109\/TASLP.2021.3120633 10.1109\/TASLP.2021.3120633 Yuan Gong, Yu-An Chung, and James Glass. 2021. PSLA: Improving Audio Tagging with Pretraining, Sampling, Labeling, and Aggregation. IEEE\/ACM Transactions on Audio, Speech, and Language Processing (2021). https:\/\/doi.org\/10.1109\/TASLP.2021.3120633"},{"key":"#cr-split#-e_1_3_2_1_9_1.1","unstructured":"Esin\u00a0Darici Haritaoglu Nicholas Rasmussen Daniel C.\u00a0H. Tan Jennifer\u00a0Ranjani J. Jaclyn Xiao Gunvant Chaudhari Akanksha Rajput Praveen Govindan Christian Canham Wei Chen Minami Yamaura Laura Gomezjurado Aaron Broukhim Amil Khanzada and Mert Pilanci. 2022. Using Deep Learning with Large Aggregated Datasets for COVID-19 Classification from Cough. https:\/\/doi.org\/10.48550\/ARXIV.2201.01669 10.48550\/ARXIV.2201.01669"},{"key":"#cr-split#-e_1_3_2_1_9_1.2","unstructured":"Esin\u00a0Darici Haritaoglu Nicholas Rasmussen Daniel C.\u00a0H. Tan Jennifer\u00a0Ranjani J. Jaclyn Xiao Gunvant Chaudhari Akanksha Rajput Praveen Govindan Christian Canham Wei Chen Minami Yamaura Laura Gomezjurado Aaron Broukhim Amil Khanzada and Mert Pilanci. 2022. Using Deep Learning with Large Aggregated Datasets for COVID-19 Classification from Cough. https:\/\/doi.org\/10.48550\/ARXIV.2201.01669"},{"key":"e_1_3_2_1_10_1","volume-title":"Laurens van\u00a0der Maaten, and Kilian\u00a0Q. Weinberger","author":"Huang Gao","year":"2016","unstructured":"Gao Huang , Zhuang Liu , Laurens van\u00a0der Maaten, and Kilian\u00a0Q. Weinberger . 2016 . Densely Connected Convolutional Networks . https:\/\/doi.org\/10.48550\/ARXIV.1608.06993 10.48550\/ARXIV.1608.06993 Gao Huang, Zhuang Liu, Laurens van\u00a0der Maaten, and Kilian\u00a0Q. Weinberger. 2016. Densely Connected Convolutional Networks. https:\/\/doi.org\/10.48550\/ARXIV.1608.06993"},{"key":"e_1_3_2_1_11_1","volume-title":"Kingma and Jimmy Ba","author":"P.","year":"2014","unstructured":"Diederik\u00a0 P. Kingma and Jimmy Ba . 2014 . Adam : A Method for Stochastic Optimization . https:\/\/doi.org\/10.48550\/ARXIV.1412.6980 10.48550\/ARXIV.1412.6980 Diederik\u00a0P. Kingma and Jimmy Ba. 2014. Adam: A Method for Stochastic Optimization. https:\/\/doi.org\/10.48550\/ARXIV.1412.6980"},{"key":"e_1_3_2_1_12_1","doi-asserted-by":"publisher","DOI":"10.1006\/pulp.1996.0034"},{"key":"e_1_3_2_1_13_1","doi-asserted-by":"publisher","DOI":"10.1016\/j.media.2020.101794"},{"key":"e_1_3_2_1_14_1","unstructured":"Lara Orlandic Tomas Teijeiro and David Atienza. 2021. The COUGHVID crowdsourcing dataset a corpus for the study of large-scale cough analysis algorithms. https:\/\/www.nature.com\/articles\/s41597-021-00937-4  Lara Orlandic Tomas Teijeiro and David Atienza. 2021. The COUGHVID crowdsourcing dataset a corpus for the study of large-scale cough analysis algorithms. https:\/\/www.nature.com\/articles\/s41597-021-00937-4"},{"key":"#cr-split#-e_1_3_2_1_15_1.1","doi-asserted-by":"crossref","unstructured":"Zexu Pan Zhaojie Luo Jichen Yang and Haizhou Li. 2020. Multi-modal Attention for Speech Emotion Recognition. https:\/\/doi.org\/10.48550\/ARXIV.2009.04107 10.48550\/ARXIV.2009.04107","DOI":"10.21437\/Interspeech.2020-1653"},{"key":"#cr-split#-e_1_3_2_1_15_1.2","doi-asserted-by":"crossref","unstructured":"Zexu Pan Zhaojie Luo Jichen Yang and Haizhou Li. 2020. Multi-modal Attention for Speech Emotion Recognition. https:\/\/doi.org\/10.48550\/ARXIV.2009.04107","DOI":"10.21437\/Interspeech.2020-1653"},{"key":"e_1_3_2_1_16_1","volume-title":"A Cough-Based Algorithm for Automatic Diagnosis of Pertussis. PLOS ONE 11, 9 (09","author":"Xaviero\u00a0Adhi Pramono Renard","year":"2016","unstructured":"Renard Xaviero\u00a0Adhi Pramono , Syed\u00a0Anas Imtiaz , and Esther Rodriguez-Villegas . 2016. A Cough-Based Algorithm for Automatic Diagnosis of Pertussis. PLOS ONE 11, 9 (09 2016 ), 1\u201320. https:\/\/doi.org\/10.1371\/journal.pone.0162128 10.1371\/journal.pone.0162128 Renard Xaviero\u00a0Adhi Pramono, Syed\u00a0Anas Imtiaz, and Esther Rodriguez-Villegas. 2016. A Cough-Based Algorithm for Automatic Diagnosis of Pertussis. PLOS ONE 11, 9 (09 2016), 1\u201320. https:\/\/doi.org\/10.1371\/journal.pone.0162128"},{"key":"e_1_3_2_1_17_1","doi-asserted-by":"publisher","DOI":"10.4269\/ajtmh.20-0216"},{"key":"e_1_3_2_1_18_1","unstructured":"Elliot Saba. 2018. Techniques for cough sound analysis. http:\/\/hdl.handle.net\/1773\/43034  Elliot Saba. 2018. Techniques for cough sound analysis. http:\/\/hdl.handle.net\/1773\/43034"},{"key":"e_1_3_2_1_19_1","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2020-2768"},{"key":"#cr-split#-e_1_3_2_1_20_1.1","doi-asserted-by":"crossref","unstructured":"Christian Szegedy Sergey Ioffe Vincent Vanhoucke and Alex Alemi. 2016. Inception-v4 Inception-ResNet and the Impact of Residual Connections on Learning. https:\/\/doi.org\/10.48550\/ARXIV.1602.07261 10.48550\/ARXIV.1602.07261","DOI":"10.1609\/aaai.v31i1.11231"},{"key":"#cr-split#-e_1_3_2_1_20_1.2","doi-asserted-by":"crossref","unstructured":"Christian Szegedy Sergey Ioffe Vincent Vanhoucke and Alex Alemi. 2016. Inception-v4 Inception-ResNet and the Impact of Residual Connections on Learning. https:\/\/doi.org\/10.48550\/ARXIV.1602.07261","DOI":"10.1609\/aaai.v31i1.11231"},{"key":"#cr-split#-e_1_3_2_1_21_1.1","unstructured":"Shuyun Tang Zhaojie Luo Guoshun Nan Yuichiro Yoshikawa and Ishiguro Hiroshi. 2021. Fusion with Hierarchical Graphs for Mulitmodal Emotion Recognition. https:\/\/doi.org\/10.48550\/ARXIV.2109.07149 10.48550\/ARXIV.2109.07149"},{"key":"#cr-split#-e_1_3_2_1_21_1.2","unstructured":"Shuyun Tang Zhaojie Luo Guoshun Nan Yuichiro Yoshikawa and Ishiguro Hiroshi. 2021. Fusion with Hierarchical Graphs for Mulitmodal Emotion Recognition. https:\/\/doi.org\/10.48550\/ARXIV.2109.07149"},{"key":"e_1_3_2_1_22_1","unstructured":"Hugo Touvron Matthieu Cord Matthijs Douze Francisco Massa Alexandre Sablayrolles and Herv\u00e9 J\u00e9gou. 2020. Training data-efficient image transformers & distillation through attention. CoRR abs\/2012.12877(2020). arXiv:2012.12877https:\/\/arxiv.org\/abs\/2012.12877  Hugo Touvron Matthieu Cord Matthijs Douze Francisco Massa Alexandre Sablayrolles and Herv\u00e9 J\u00e9gou. 2020. Training data-efficient image transformers & distillation through attention. CoRR abs\/2012.12877(2020). arXiv:2012.12877https:\/\/arxiv.org\/abs\/2012.12877"},{"key":"e_1_3_2_1_23_1","volume-title":"\u00a0Lavista Ferres","author":"Trivedi Anusua","year":"2020","unstructured":"Anusua Trivedi , Anthony Ortiz , Jocelyn Desbiens , Caleb Robinson , Marian Blazes , Sunil Gupta , Rahul Dodhia , Pavan Bhatraju , W.\u00a0 Conrad Liles , Aaron Lee , and Juan M . \u00a0Lavista Ferres . 2020 . Effective Deep Learning Approaches for Predicting COVID-19 Outcomes from Chest Computed Tomography Volumes . medRxiv (2020). https:\/\/doi.org\/10.1101\/2020.10.15.20213462 arXiv:https:\/\/www.medrxiv.org\/content\/early\/2020\/10\/20\/2020.10.15.20213462.full.pdf 10.1101\/2020.10.15.20213462 Anusua Trivedi, Anthony Ortiz, Jocelyn Desbiens, Caleb Robinson, Marian Blazes, Sunil Gupta, Rahul Dodhia, Pavan Bhatraju, W.\u00a0Conrad Liles, Aaron Lee, and Juan M.\u00a0Lavista Ferres. 2020. Effective Deep Learning Approaches for Predicting COVID-19 Outcomes from Chest Computed Tomography Volumes. medRxiv (2020). https:\/\/doi.org\/10.1101\/2020.10.15.20213462 arXiv:https:\/\/www.medrxiv.org\/content\/early\/2020\/10\/20\/2020.10.15.20213462.full.pdf"},{"key":"#cr-split#-e_1_3_2_1_24_1.1","unstructured":"Ashish Vaswani Noam Shazeer Niki Parmar Jakob Uszkoreit Llion Jones Aidan\u00a0N. Gomez Lukasz Kaiser and Illia Polosukhin. 2017. Attention Is All You Need. https:\/\/doi.org\/10.48550\/ARXIV.1706.03762 10.48550\/ARXIV.1706.03762"},{"key":"#cr-split#-e_1_3_2_1_24_1.2","unstructured":"Ashish Vaswani Noam Shazeer Niki Parmar Jakob Uszkoreit Llion Jones Aidan\u00a0N. Gomez Lukasz Kaiser and Illia Polosukhin. 2017. Attention Is All You Need. https:\/\/doi.org\/10.48550\/ARXIV.1706.03762"},{"key":"#cr-split#-e_1_3_2_1_25_1.1","unstructured":"Zizhao Zhang Han Zhang Long Zhao Ting Chen Sercan\u00a0O. Arik and Tomas Pfister. 2021. Nested Hierarchical Transformer: Towards Accurate Data-Efficient and Interpretable Visual Understanding. https:\/\/doi.org\/10.48550\/ARXIV.2105.12723 10.48550\/ARXIV.2105.12723"},{"key":"#cr-split#-e_1_3_2_1_25_1.2","doi-asserted-by":"crossref","unstructured":"Zizhao Zhang Han Zhang Long Zhao Ting Chen Sercan\u00a0O. Arik and Tomas Pfister. 2021. Nested Hierarchical Transformer: Towards Accurate Data-Efficient and Interpretable Visual Understanding. https:\/\/doi.org\/10.48550\/ARXIV.2105.12723","DOI":"10.1609\/aaai.v36i3.20252"}],"event":{"name":"SPML 2022: 2022 5th International Conference on Signal Processing and Machine Learning","acronym":"SPML 2022","location":"Dalian China"},"container-title":["2022 5th International Conference on Signal Processing and Machine Learning"],"original-title":[],"link":[{"URL":"https:\/\/dl.acm.org\/doi\/10.1145\/3556384.3556414","content-type":"unspecified","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/dl.acm.org\/doi\/pdf\/10.1145\/3556384.3556414","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,6,17]],"date-time":"2025-06-17T19:00:32Z","timestamp":1750186832000},"score":1,"resource":{"primary":{"URL":"https:\/\/dl.acm.org\/doi\/10.1145\/3556384.3556414"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2022,8,4]]},"references-count":31,"alternative-id":["10.1145\/3556384.3556414","10.1145\/3556384"],"URL":"https:\/\/doi.org\/10.1145\/3556384.3556414","relation":{},"subject":[],"published":{"date-parts":[[2022,8,4]]}}}