{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,3,28]],"date-time":"2026-03-28T13:41:35Z","timestamp":1774705295498,"version":"3.50.1"},"reference-count":32,"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"}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":[],"published-print":{"date-parts":[[2022,5,23]]},"DOI":"10.1109\/icassp43922.2022.9747671","type":"proceedings-article","created":{"date-parts":[[2022,4,27]],"date-time":"2022-04-27T19:50:34Z","timestamp":1651089034000},"page":"6882-6886","source":"Crossref","is-referenced-by-count":12,"title":["Language Adaptive Cross-Lingual Speech Representation Learning with Sparse Sharing Sub-Networks"],"prefix":"10.1109","author":[{"given":"Yizhou","family":"Lu","sequence":"first","affiliation":[{"name":"ByteDance AI Lab,Speech & Audio Team"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Mingkun","family":"Huang","sequence":"additional","affiliation":[{"name":"ByteDance AI Lab,Speech & Audio Team"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Xinghua","family":"Qu","sequence":"additional","affiliation":[{"name":"ByteDance AI Lab,Speech & Audio Team"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Pengfei","family":"Wei","sequence":"additional","affiliation":[{"name":"ByteDance AI Lab,Speech & Audio Team"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Zejun","family":"Ma","sequence":"additional","affiliation":[{"name":"ByteDance AI Lab,Speech & Audio Team"}],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"263","reference":[{"key":"ref32","doi-asserted-by":"publisher","DOI":"10.1145\/1143844.1143891"},{"key":"ref31","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP40776.2020.9054548"},{"key":"ref30","article-title":"Common voice: A massively-multilingual speech corpus","author":"ardila","year":"2019","journal-title":"arXiv preprint arXiv 1912 06670"},{"key":"ref10","article-title":"Unsupervised crosslingual representation learning for speech recognition","author":"conneau","year":"2020","journal-title":"arXiv preprint arXiv 2006 13823"},{"key":"ref11","article-title":"Unispeech: Unified speech representation learning with labeled and unlabeled data","author":"wang","year":"2021","journal-title":"arXiv preprint arXiv 2101 06286"},{"key":"ref12","doi-asserted-by":"crossref","first-page":"41","DOI":"10.1023\/A:1007379606734","article-title":"Multitask learning","volume":"28","author":"caruana","year":"1997","journal-title":"Machine Learning"},{"key":"ref13","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2020-2485"},{"key":"ref14","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2020-2831"},{"key":"ref15","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2021-216"},{"key":"ref16","doi-asserted-by":"publisher","DOI":"10.1109\/ASRU51503.2021.9687871"},{"key":"ref17","article-title":"Multilingual speech translation with efficient finetuning of pretrained models","author":"li","year":"2020","journal-title":"arXiv preprint arXiv 2010 12136"},{"key":"ref18","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v34i05.6424"},{"key":"ref19","doi-asserted-by":"crossref","DOI":"10.1609\/aaai.v35i15.17574","article-title":"Finding sparse structures for domain specific neural machine translation","author":"liang","year":"2021","journal-title":"AAAI"},{"key":"ref28","article-title":"Categorical reparameterization with gumbel-softmax","author":"jang","year":"2016","journal-title":"arXiv preprint arXiv 1611 01144"},{"key":"ref4","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2019-1873"},{"key":"ref27","article-title":"Attention is all you need","author":"vaswani","year":"2017","journal-title":"NeurIPS"},{"key":"ref3","article-title":"Representation learning with contrastive predictive coding","author":"van den oord","year":"2018","journal-title":"arXiv preprint arXiv 1807 03748"},{"key":"ref6","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP40776.2020.9054458"},{"key":"ref5","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2019-1473"},{"key":"ref29","article-title":"Cross-lingual language model pretraining","author":"conneau","year":"2019","journal-title":"NeurIPS"},{"key":"ref8","article-title":"wav2vec 2.0: A framework for self-supervised learning of speech representations","author":"baevski","year":"2020","journal-title":"NeurIPS"},{"key":"ref7","article-title":"Deep contextualized acoustic representations for semisupervised speech recognition","author":"ling","year":"2020","journal-title":"ICASSP"},{"key":"ref2","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2018.8462105"},{"key":"ref9","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP40776.2020.9053541"},{"key":"ref1","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2017-405"},{"key":"ref20","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2021.acl-long.25"},{"key":"ref22","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2019-2858"},{"key":"ref21","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2021.acl-long.445"},{"key":"ref24","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2019.01152"},{"key":"ref23","article-title":"The lottery ticket hypothesis: Finding sparse, trainable neural networks","author":"frankle","year":"2018","journal-title":"ICLRE"},{"key":"ref26","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2018.8461972"},{"key":"ref25","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2021-1075"}],"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\/09747671.pdf?arnumber=9747671","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2023,11,20]],"date-time":"2023-11-20T19:14:38Z","timestamp":1700507678000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/9747671\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2022,5,23]]},"references-count":32,"URL":"https:\/\/doi.org\/10.1109\/icassp43922.2022.9747671","relation":{},"subject":[],"published":{"date-parts":[[2022,5,23]]}}}