{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,3,4]],"date-time":"2026-03-04T17:35:01Z","timestamp":1772645701018,"version":"3.50.1"},"reference-count":43,"publisher":"IEEE","license":[{"start":{"date-parts":[[2021,12,13]],"date-time":"2021-12-13T00:00:00Z","timestamp":1639353600000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2021,12,13]],"date-time":"2021-12-13T00:00:00Z","timestamp":1639353600000},"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":[[2021,12,13]]},"DOI":"10.1109\/asru51503.2021.9688061","type":"proceedings-article","created":{"date-parts":[[2022,2,3]],"date-time":"2022-02-03T20:31:00Z","timestamp":1643920260000},"page":"169-176","source":"Crossref","is-referenced-by-count":3,"title":["Comparison of Self-Supervised Speech Pre-Training Methods on Flemish Dutch"],"prefix":"10.1109","author":[{"given":"Jakob","family":"Poncelet","sequence":"first","affiliation":[{"name":"KU Leuven, ESAT-PSI,Department Electrical Engineering,Leuven,Belgium,B-3001"}]},{"given":"Hugo","family":"Van hamme","sequence":"additional","affiliation":[{"name":"KU Leuven, ESAT-PSI,Department Electrical Engineering,Leuven,Belgium,B-3001"}]}],"member":"263","reference":[{"key":"ref39","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP40776.2020.9052942"},{"key":"ref38","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2015.7178964"},{"key":"ref33","author":"liu","year":"2020","journal-title":"S3PRL The self-supervised speech pre-training and representation learning toolkit"},{"key":"ref32","author":"ashish","year":"2017","journal-title":"Attention is all you need"},{"key":"ref31","article-title":"The Kaldi speech recognition toolkit","author":"povey","year":"2011","journal-title":"2011 IEEE Workshop on Automatic Speech Recognition & Understanding"},{"key":"ref30","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP39728.2021.9414776"},{"key":"ref37","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2018-1417"},{"key":"ref36","article-title":"The Spoken Dutch Corpus: Overview and first evaluation","volume":"2","author":"oostdijk","year":"2000","journal-title":"Proceedings of LREC-2000 Athens"},{"key":"ref35","first-page":"333","article-title":"Automatic generation of phonetic transcriptions for large speech corpora","volume":"1","author":"demuynck","year":"0","journal-title":"Proceedings International Conference on Spoken Language Processing"},{"key":"ref34","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/N19-4009"},{"key":"ref10","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2020-1228"},{"key":"ref40","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2020-2826"},{"key":"ref11","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2020.acl-main.213"},{"key":"ref12","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP40776.2020.9054458"},{"key":"ref13","doi-asserted-by":"publisher","DOI":"10.1109\/SLT48900.2021.9383575"},{"key":"ref14","author":"devlin","year":"2019","journal-title":"BERT Pre-training of deep bidirectional transformers for language understanding"},{"key":"ref15","author":"van den oord","year":"2019","journal-title":"Representation learning with contrastive predictive coding"},{"key":"ref16","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2019-1873"},{"key":"ref17","author":"baevski","year":"2020","journal-title":"vq-wav2vec Self-supervised learning of discrete speech representations"},{"key":"ref18","author":"baevski","year":"2020","journal-title":"Effectiveness of self-supervised pre-training for speech recognition"},{"key":"ref19","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2020.findings-emnlp.106"},{"key":"ref28","doi-asserted-by":"publisher","DOI":"10.1515\/mult.2010.019"},{"key":"ref4","author":"baevski","year":"2021","journal-title":"Unsupervised speech recognition"},{"key":"ref27","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP40776.2020.9053176"},{"key":"ref3","author":"zhang","year":"2020","journal-title":"Pushing the Limits of Semi-Supervised Learning for Automatic Speech Recognition"},{"key":"ref6","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP40776.2020.9054548"},{"key":"ref29","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2021-236"},{"key":"ref5","author":"conneau","year":"2020","journal-title":"Unsupervised cross-lingual representation learning for speech recognition"},{"key":"ref8","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2019-1473"},{"key":"ref7","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP39728.2021.9414321"},{"key":"ref2","author":"xu","year":"2020","journal-title":"Self-training and pre-training are complementary for speech recognition"},{"key":"ref9","author":"chung","year":"2020","journal-title":"Generative pretraining for speech with autoregressive predictive coding"},{"key":"ref1","author":"baevski","year":"2020","journal-title":"wav2vec 2 0 A framework for self-supervised learning of speech representations"},{"key":"ref20","doi-asserted-by":"publisher","DOI":"10.1109\/TASLP.2019.2938863"},{"key":"ref22","author":"liu","year":"2020","journal-title":"Tera Self-supervised learning of transformer encoder representation for speech"},{"key":"ref21","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2020-3084"},{"key":"ref42","first-page":"16","article-title":"Speech recognition and keyword spotting for low-resource languages: Babel project research at cued","author":"gales","year":"0","journal-title":"SLTU"},{"key":"ref24","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP40776.2020.9053569"},{"key":"ref41","author":"rosana","year":"2020","journal-title":"Common voice A massively-multilingual speech corpus"},{"key":"ref23","author":"liu","year":"2020","journal-title":"Non-autoregressive predictive coding for learning speech representations from local dependencies"},{"key":"ref26","author":"jiang","year":"2020","journal-title":"Speech SIM-CLR Combining contrastive and reconstruction objective for self-supervised speech representation learning"},{"key":"ref43","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2021.acl-long.80"},{"key":"ref25","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2019-2605"}],"event":{"name":"2021 IEEE Automatic Speech Recognition and Understanding Workshop (ASRU)","location":"Cartagena, Colombia","start":{"date-parts":[[2021,12,13]]},"end":{"date-parts":[[2021,12,17]]}},"container-title":["2021 IEEE Automatic Speech Recognition and Understanding Workshop (ASRU)"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx7\/9687821\/9687855\/09688061.pdf?arnumber=9688061","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2022,5,16]],"date-time":"2022-05-16T20:41:54Z","timestamp":1652733714000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/9688061\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2021,12,13]]},"references-count":43,"URL":"https:\/\/doi.org\/10.1109\/asru51503.2021.9688061","relation":{},"subject":[],"published":{"date-parts":[[2021,12,13]]}}}