{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2024,10,30]],"date-time":"2024-10-30T00:58:55Z","timestamp":1730249935712,"version":"3.28.0"},"reference-count":27,"publisher":"IEEE","license":[{"start":{"date-parts":[[2024,7,15]],"date-time":"2024-07-15T00:00:00Z","timestamp":1721001600000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2024,7,15]],"date-time":"2024-07-15T00:00:00Z","timestamp":1721001600000},"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":[[2024,7,15]]},"DOI":"10.1109\/icme57554.2024.10687681","type":"proceedings-article","created":{"date-parts":[[2024,9,30]],"date-time":"2024-09-30T17:24:16Z","timestamp":1727717056000},"page":"1-6","source":"Crossref","is-referenced-by-count":0,"title":["SSHR: Leveraging Self-supervised Hierarchical Representations for Multilingual Automatic Speech Recognition"],"prefix":"10.1109","author":[{"given":"Hongfei","family":"Xue","sequence":"first","affiliation":[{"name":"Northwestern Polytechnical University,School of Software,Xi’an,China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Qijie","family":"Shao","sequence":"additional","affiliation":[{"name":"Northwestern Polytechnical University,School of Computer Science,Xi’an,China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Kaixun","family":"Huang","sequence":"additional","affiliation":[{"name":"Northwestern Polytechnical University,School of Software,Xi’an,China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Peikun","family":"Chen","sequence":"additional","affiliation":[{"name":"Northwestern Polytechnical University,School of Computer Science,Xi’an,China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Jie","family":"Liu","sequence":"additional","affiliation":[{"name":"HuaWei Cloud HuaWei,Xi’an,China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Lei","family":"Xie","sequence":"additional","affiliation":[{"name":"Northwestern Polytechnical University,School of Computer Science,Xi’an,China"}],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"263","reference":[{"issue":"97","key":"ref1","first-page":"1","article-title":"Scaling speech technology to 1,000+ languages","volume":"25","author":"Pratap","year":"2024","journal-title":"Journal of Machine Learning Research"},{"key":"ref2","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2020-2831"},{"key":"ref3","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP43922.2022.9746038"},{"key":"ref4","doi-asserted-by":"publisher","DOI":"10.1109\/ASRU51503.2021.9687871"},{"key":"ref5","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2018.8461972"},{"key":"ref6","first-page":"28492","article-title":"Robust Speech Recognition via Large-Scale Weak Supervision","volume":"202","author":"Radford","year":"2023","journal-title":"ICML"},{"key":"ref7","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2021-329"},{"key":"ref8","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2022-10006"},{"key":"ref9","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2019-2858"},{"key":"ref10","first-page":"10937","article-title":"UniSpeech: Unified Speech Representation Learning with Labeled and Unlabeled Data","author":"Wang","year":"2021","journal-title":"ICML"},{"key":"ref11","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2022-143"},{"article-title":"Google usm: Scaling automatic speech recognition beyond 100 languages","year":"2023","author":"Zhang","key":"ref12"},{"key":"ref13","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2023-746"},{"key":"ref14","doi-asserted-by":"publisher","DOI":"10.1109\/ASRU51503.2021.9688093"},{"key":"ref15","doi-asserted-by":"publisher","DOI":"10.1109\/TASLP.2021.3122291"},{"key":"ref16","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP43922.2022.9747667"},{"key":"ref17","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP49357.2023.10095326"},{"key":"ref18","doi-asserted-by":"crossref","first-page":"369","DOI":"10.1145\/1143844.1143891","article-title":"Connec-tionist temporal classification: labelling unsegmented sequence data with recurrent neural networks","volume":"148","author":"Graves","year":"2006","journal-title":"ICML"},{"key":"ref19","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2023-1316"},{"key":"ref20","first-page":"4218","article-title":"Common Voice: A Massively-Multilingual Speech Corpus","author":"Ardila","year":"2020","journal-title":"LREC"},{"key":"ref21","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2022-11249"},{"key":"ref22","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP39728.2021.9414594"},{"key":"ref23","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2021-911"},{"key":"ref24","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP49357.2023.10094820"},{"key":"ref25","first-page":"12449","article-title":"wav2vec 2.0: A Framework for Self-Supervised Learning of Speech Representations","author":"Baevski","year":"2020","journal-title":"NeurIPS"},{"key":"ref26","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/N19-4009"},{"key":"ref27","article-title":"Adam: A Method for Stochastic Optimization","author":"Kingma","year":"2015","journal-title":"ICLR"}],"event":{"name":"2024 IEEE International Conference on Multimedia and Expo (ICME)","start":{"date-parts":[[2024,7,15]]},"location":"Niagara Falls, ON, Canada","end":{"date-parts":[[2024,7,19]]}},"container-title":["2024 IEEE International Conference on Multimedia and Expo (ICME)"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx8\/10685847\/10687354\/10687681.pdf?arnumber=10687681","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2024,10,1]],"date-time":"2024-10-01T06:17:24Z","timestamp":1727763444000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/10687681\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2024,7,15]]},"references-count":27,"URL":"https:\/\/doi.org\/10.1109\/icme57554.2024.10687681","relation":{},"subject":[],"published":{"date-parts":[[2024,7,15]]}}}