{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,4,22]],"date-time":"2026-04-22T20:00:08Z","timestamp":1776888008698,"version":"3.51.2"},"reference-count":26,"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\/asru57964.2023.10389699","type":"proceedings-article","created":{"date-parts":[[2024,1,19]],"date-time":"2024-01-19T18:38:40Z","timestamp":1705689520000},"page":"1-8","source":"Crossref","is-referenced-by-count":6,"title":["Minisuperb: Lightweight Benchmark for Self-Supervised Speech Models"],"prefix":"10.1109","author":[{"given":"Yu-Hsiang","family":"Wang","sequence":"first","affiliation":[{"name":"National Taiwan University,College of Electrical Engineering and Computer Science,Taiwan"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Huang-Yu","family":"Chen","sequence":"additional","affiliation":[{"name":"National Taiwan University,College of Electrical Engineering and Computer Science,Taiwan"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Kai-Wei","family":"Chang","sequence":"additional","affiliation":[{"name":"National Taiwan University,College of Electrical Engineering and Computer Science,Taiwan"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Winston","family":"Hsu","sequence":"additional","affiliation":[{"name":"National Taiwan University,College of Electrical Engineering and Computer Science,Taiwan"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Hung-Yi","family":"Lee","sequence":"additional","affiliation":[{"name":"National Taiwan University,College of Electrical Engineering and Computer Science,Taiwan"}],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"263","reference":[{"key":"ref1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.01426"},{"key":"ref2","article-title":"Beit: BERT pre-training of image transformers","author":"Bao","journal-title":"ICLR. 2022"},{"key":"ref3","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/n18-1202"},{"key":"ref4","first-page":"4171","article-title":"BERT: pre-training of deep bidirectional transformers for language understanding","author":"Devlin","journal-title":"NAACL-HLT (1). 2019"},{"key":"ref5","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP40776.2020.9054458"},{"key":"ref6","doi-asserted-by":"publisher","DOI":"10.21437\/interspeech.2019-1873"},{"key":"ref7","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP40776.2020.9053176"},{"key":"ref8","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2019-2605"},{"key":"ref9","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2021-1775"},{"key":"ref10","doi-asserted-by":"publisher","DOI":"10.1109\/TASLP.2021.3122291"},{"key":"ref11","article-title":"wav2vec 2.0: A framework for self-supervised learning of speech representations","author":"Baevski","year":"2020","journal-title":"NeurIPS"},{"key":"ref12","article-title":"Representation learning with contrastive predictive coding","volume":"abs\/1807.03748","author":"van den Oord","year":"2018","journal-title":"CoRR"},{"key":"ref13","doi-asserted-by":"publisher","DOI":"10.1109\/JSTSP.2022.3207050"},{"key":"ref14","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2022.acl-long.580"},{"key":"ref15","doi-asserted-by":"publisher","DOI":"10.1109\/slt54892.2023.10022770"},{"key":"ref16","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP40776.2020.9052942"},{"key":"ref17","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2021.acl-long.80"},{"key":"ref18","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2021-1965"},{"key":"ref19","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2017-950"},{"key":"ref20","doi-asserted-by":"publisher","DOI":"10.1109\/ICSDA.2013.6709856"},{"key":"ref21","article-title":"Librimix: An open-source dataset for generalizable speech separation","author":"Cosentino","year":"2020"},{"key":"ref22","doi-asserted-by":"publisher","DOI":"10.1109\/IJCNN55064.2022.9891914"},{"key":"ref23","doi-asserted-by":"publisher","DOI":"10.1109\/TASLP.2021.3095662"},{"key":"ref24","doi-asserted-by":"publisher","DOI":"10.1109\/icassp40776.2020.9053176"},{"key":"ref25","first-page":"7414","article-title":"Unsupervised pre-training transfers well across languages","author":"Rivi\u00e8re","journal-title":"ICASSP. 2020"},{"key":"ref26","doi-asserted-by":"publisher","DOI":"10.1109\/JSTSP.2022.3188113"}],"event":{"name":"2023 IEEE Automatic Speech Recognition and Understanding Workshop (ASRU)","location":"Taipei, Taiwan","start":{"date-parts":[[2023,12,16]]},"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\/10389699.pdf?arnumber=10389699","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2024,1,23]],"date-time":"2024-01-23T16:27:44Z","timestamp":1706027264000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/10389699\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2023,12,16]]},"references-count":26,"URL":"https:\/\/doi.org\/10.1109\/asru57964.2023.10389699","relation":{},"subject":[],"published":{"date-parts":[[2023,12,16]]}}}