{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2024,9,7]],"date-time":"2024-09-07T10:50:09Z","timestamp":1725706209099},"reference-count":34,"publisher":"IEEE","license":[{"start":{"date-parts":[[2023,12,16]],"date-time":"2023-12-16T00:00:00Z","timestamp":1702684800000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2023,12,16]],"date-time":"2023-12-16T00:00:00Z","timestamp":1702684800000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-037"}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":[],"published-print":{"date-parts":[[2023,12,16]]},"DOI":"10.1109\/asru57964.2023.10389789","type":"proceedings-article","created":{"date-parts":[[2024,1,19]],"date-time":"2024-01-19T18:38:40Z","timestamp":1705689520000},"page":"1-7","source":"Crossref","is-referenced-by-count":0,"title":["Detecting Speech Abnormalities With a Perceiver-Based Sequence Classifier that Leverages a Universal Speech Model"],"prefix":"10.1109","author":[{"given":"Hagen","family":"Soltau","sequence":"first","affiliation":[{"name":"Google DeepMind"}]},{"given":"Izhak","family":"Shafran","sequence":"additional","affiliation":[{"name":"Google DeepMind"}]},{"given":"Alex","family":"Ottenwess","sequence":"additional","affiliation":[{"name":"Google"}]},{"given":"Joseph R. Jr","family":"Duffy","sequence":"additional","affiliation":[{"name":"Mayo Clinic"}]},{"given":"Rene L.","family":"Utianski","sequence":"additional","affiliation":[{"name":"Mayo Clinic"}]},{"given":"Leland R.","family":"Barnard","sequence":"additional","affiliation":[{"name":"Mayo Clinic"}]},{"given":"John L.","family":"Stricker","sequence":"additional","affiliation":[{"name":"Mayo Clinic"}]},{"given":"Daniela","family":"Wiepert","sequence":"additional","affiliation":[{"name":"Mayo Clinic"}]},{"given":"David T.","family":"Jones","sequence":"additional","affiliation":[{"name":"Mayo Clinic"}]},{"given":"Hugo","family":"Botha","sequence":"additional","affiliation":[{"name":"Mayo Clinic"}]}],"member":"263","reference":[{"key":"ref1","doi-asserted-by":"publisher","DOI":"10.1016\/S1474-4422(17)30299-5"},{"key":"ref2","doi-asserted-by":"publisher","DOI":"10.1016\/j.jns.2006.03.003"},{"key":"ref3","doi-asserted-by":"publisher","DOI":"10.1007\/s00415-021-10585-8"},{"article-title":"Google USM: Scaling automatic speech recognition beyond 100 languages","year":"2023","author":"Zhang","key":"ref4"},{"key":"ref5","article-title":"Perceiver: General perception with iterative attention","author":"Jaegle","year":"2021","journal-title":"in ICML"},{"key":"ref6","doi-asserted-by":"publisher","DOI":"10.1016\/j.bspc.2020.102350"},{"key":"ref7","doi-asserted-by":"publisher","DOI":"10.3390\/s22031137"},{"key":"ref8","doi-asserted-by":"publisher","DOI":"10.1002\/dad2.12393"},{"key":"ref9","doi-asserted-by":"publisher","DOI":"10.1089\/tmj.2018.0271"},{"key":"ref10","doi-asserted-by":"publisher","DOI":"10.1016\/j.csl.2013.12.001"},{"key":"ref11","doi-asserted-by":"publisher","DOI":"10.1109\/MLSP.2014.6958856"},{"key":"ref12","doi-asserted-by":"publisher","DOI":"10.1002\/aur.2721"},{"key":"ref13","article-title":"Emotional Speech Recognition with Pre-trained Deep Visual Models","author":"Ragheb","year":"2022","journal-title":"arXiv:2204.03561"},{"key":"ref14","doi-asserted-by":"publisher","DOI":"10.1016\/j.bbe.2022.04.002"},{"key":"ref15","doi-asserted-by":"publisher","DOI":"10.1145\/3469089"},{"key":"ref16","article-title":"Data2vec: A general framework for self-supervised learning in speech, vision and language","author":"Baevski","year":"2022","journal-title":"ICML"},{"key":"ref17","doi-asserted-by":"publisher","DOI":"10.3390\/brainsci13010028"},{"key":"ref18","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2008-480"},{"key":"ref19","doi-asserted-by":"publisher","DOI":"10.1007\/s10579-011-9145-0"},{"key":"ref20","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP49357.2023.10095981"},{"key":"ref21","doi-asserted-by":"publisher","DOI":"10.1121\/1.5100272"},{"article-title":"BERT: Pre-training of deep bidirectional transformers for language understanding","volume-title":"in Proc. NAACL\/HLT","author":"Devlin","key":"ref22"},{"key":"ref23","article-title":"Improving language understanding by generative pre-training","volume-title":"Technical Report","author":"Radford","year":"2018"},{"key":"ref24","doi-asserted-by":"publisher","DOI":"10.1109\/TASL.2010.2064307"},{"key":"ref25","doi-asserted-by":"publisher","DOI":"10.1162\/neco.1997.9.8.1735"},{"article-title":"Set transformer: A framework for attention-based permutation-invariant neural networks","year":"2019","author":"Lee","key":"ref26"},{"key":"ref27","article-title":"Proposal-based few-shot sound event detection for speech and environmental sounds with perceivers","author":"Wolters","year":"2021","journal-title":"arXiv"},{"key":"ref28","article-title":"Motor speech disorders: Substrates, differential diagnosis, and management","author":"Duffy","year":"2019","journal-title":"Elsevier Health Sciences"},{"key":"ref29","doi-asserted-by":"publisher","DOI":"10.1109\/MeMeA.2016.7533761"},{"key":"ref30","doi-asserted-by":"publisher","DOI":"10.1109\/ACCESS.2017.2762475"},{"key":"ref31","doi-asserted-by":"publisher","DOI":"10.21437\/interspeech.2020-3015"},{"key":"ref32","article-title":"Self-supervised learning with random-projection quantizer for speech recognition","author":"Chiu","year":"2022","journal-title":"arXiv"},{"key":"ref33","doi-asserted-by":"publisher","DOI":"10.1145\/1143844.1143891"},{"key":"ref34","article-title":"Attention is all you need","author":"Vaswani","year":"2017","journal-title":"Advances in neural information processing systems"}],"event":{"name":"2023 IEEE Automatic Speech Recognition and Understanding Workshop (ASRU)","start":{"date-parts":[[2023,12,16]]},"location":"Taipei, Taiwan","end":{"date-parts":[[2023,12,20]]}},"container-title":["2023 IEEE Automatic Speech Recognition and Understanding Workshop (ASRU)"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx7\/10388490\/10389614\/10389789.pdf?arnumber=10389789","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2024,1,23]],"date-time":"2024-01-23T16:36:43Z","timestamp":1706027803000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/10389789\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2023,12,16]]},"references-count":34,"URL":"https:\/\/doi.org\/10.1109\/asru57964.2023.10389789","relation":{},"subject":[],"published":{"date-parts":[[2023,12,16]]}}}