{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,8,18]],"date-time":"2026-08-18T14:37:53Z","timestamp":1787063873096,"version":"build-2736575974"},"reference-count":26,"publisher":"IEEE","license":[{"start":{"date-parts":[[2022,5,23]],"date-time":"2022-05-23T00:00:00Z","timestamp":1653264000000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2022,5,23]],"date-time":"2022-05-23T00:00:00Z","timestamp":1653264000000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-037"}],"funder":[{"DOI":"10.13039\/100006785","name":"Google","doi-asserted-by":"publisher","id":[{"id":"10.13039\/100006785","id-type":"DOI","asserted-by":"publisher"}]}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":[],"published-print":{"date-parts":[[2022,5,23]]},"DOI":"10.1109\/icassp43922.2022.9747357","type":"proceedings-article","created":{"date-parts":[[2022,4,27]],"date-time":"2022-04-27T15:50:34Z","timestamp":1651074634000},"page":"8202-8206","source":"Crossref","is-referenced-by-count":12,"title":["Analyzing The Robustness of Unsupervised Speech Recognition"],"prefix":"10.1109","author":[{"given":"Guan-Ting","family":"Lin","sequence":"first","affiliation":[{"name":"National Taiwan University,Taiwan"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Chan-Jan","family":"Hsu","sequence":"additional","affiliation":[{"name":"National Taiwan University,Taiwan"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Da-Rong","family":"Liu","sequence":"additional","affiliation":[{"name":"National Taiwan University,Taiwan"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Hung-Yi","family":"Lee","sequence":"additional","affiliation":[{"name":"National Taiwan University,Taiwan"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Yu","family":"Tsao","sequence":"additional","affiliation":[{"name":"Academia Sinica,Taiwan"}],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"263","reference":[{"key":"ref10","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2018.8461704"},{"key":"ref11","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2015.7178964"},{"key":"ref12","first-page":"740","article-title":"Microsoft coco: Common objects in context","author":"lin","year":"2014","journal-title":"European Conference on Computer Vision"},{"key":"ref13","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/P18-1238"},{"key":"ref14","article-title":"End-to-end asr: from supervised to semi-supervised learning with modern architectures","author":"synnaeve","year":"2019"},{"key":"ref15","article-title":"Pointer sentinel mixture models","author":"merity","year":"2016"},{"key":"ref16","article-title":"Switchboard-1 release 2 ldc97s62","author":"godfrey","year":"1993","journal-title":"Web Download"},{"key":"ref17","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-319-99579-3_21"},{"key":"ref18","first-page":"12449","article-title":"wav2vec 2.0: A framework for self-supervised learning of speech representations","volume":"33","author":"baevski","year":"2020","journal-title":"Advances in neural information processing systems"},{"key":"ref19","first-page":"5998","article-title":"Attention is all you need","author":"vaswani","year":"2017","journal-title":"Advances in neural information processing systems"},{"key":"ref4","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP40776.2020.9053571"},{"key":"ref3","article-title":"Unsupervised automatic speech recognition: A review","author":"aldarmaki","year":"2021"},{"key":"ref6","article-title":"Completely unsupervised speech recognition by a generative adversarial network harmonized with iteratively refined hidden markov models","author":"chen","year":"2019","journal-title":"Proc INTERSPEECH"},{"key":"ref5","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2018-1800"},{"key":"ref8","first-page":"173","article-title":"Deep speech 2: End-to-end speech recognition in english and mandarin","author":"amodei","year":"2016","journal-title":"International Conference on Machine Learning"},{"key":"ref7","article-title":"Generative adversarial networks","author":"goodfellow","year":"2014"},{"key":"ref2","article-title":"Unsupervised speech recognition via segmental empirical output distribution matching","author":"yeh","year":"2019","journal-title":"Proc ICLR"},{"key":"ref9","article-title":"Pushing the limits of semi-supervised learning for automatic speech recognition","author":"zhang","year":"2020"},{"key":"ref1","article-title":"Unsupervised speech recognition","author":"baevski","year":"2021"},{"key":"ref20","article-title":"g2pe","author":"park","year":"2019"},{"key":"ref22","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP40776.2020.9052942"},{"key":"ref21","doi-asserted-by":"publisher","DOI":"10.1016\/j.csl.2019.06.005"},{"key":"ref24","article-title":"Fisher english training speech part 1 and 2 speech ldc200{4,5}s13","author":"cieria","year":"2005","journal-title":"Web Download Philadelphia Linguistic Data Consortium 2004"},{"key":"ref23","first-page":"4218","article-title":"Common voice: A massively-multilingual speech corpus","author":"ardila","year":"2020","journal-title":"Proceedings of the 12th Language Resources and Evaluation Conference"},{"key":"ref26","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2021-236"},{"key":"ref25","article-title":"Fisher english training speech part 1 and 2 speech ldc200 transcripts {4,5} t19","author":"cieria","year":"2005","journal-title":"Web Download Philadelphia Linguistic Data Consortium 2004"}],"event":{"name":"ICASSP 2022 - 2022 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)","location":"Singapore, Singapore","start":{"date-parts":[[2022,5,23]]},"end":{"date-parts":[[2022,5,27]]}},"container-title":["ICASSP 2022 - 2022 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx7\/9745891\/9746004\/09747357.pdf?arnumber=9747357","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2022,8,15]],"date-time":"2022-08-15T16:06:15Z","timestamp":1660579575000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/9747357\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2022,5,23]]},"references-count":26,"URL":"https:\/\/doi.org\/10.1109\/icassp43922.2022.9747357","relation":{},"subject":[],"published":{"date-parts":[[2022,5,23]]}}}