{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2024,12,25]],"date-time":"2024-12-25T05:14:16Z","timestamp":1735103656923,"version":"3.32.0"},"reference-count":23,"publisher":"IEEE","license":[{"start":{"date-parts":[[2024,11,7]],"date-time":"2024-11-07T00:00:00Z","timestamp":1730937600000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2024,11,7]],"date-time":"2024-11-07T00:00:00Z","timestamp":1730937600000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-037"}],"funder":[{"DOI":"10.13039\/501100001809","name":"National Natural Science Foundation of China","doi-asserted-by":"publisher","award":["62076144"],"award-info":[{"award-number":["62076144"]}],"id":[{"id":"10.13039\/501100001809","id-type":"DOI","asserted-by":"publisher"}]}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":[],"published-print":{"date-parts":[[2024,11,7]]},"DOI":"10.1109\/iscslp63861.2024.10799993","type":"proceedings-article","created":{"date-parts":[[2024,12,23]],"date-time":"2024-12-23T19:11:17Z","timestamp":1734981077000},"page":"656-660","source":"Crossref","is-referenced-by-count":0,"title":["CMAST: Efficient Speech-Text Joint Training Method to Enhance Linguistic Features Learning of Speech Representations"],"prefix":"10.1109","author":[{"given":"Jingran","family":"Xie","sequence":"first","affiliation":[{"name":"Pengcheng Laboratory,Shenzhen"}]},{"given":"Changhe","family":"Song","sequence":"additional","affiliation":[{"name":"Pengcheng Laboratory,Shenzhen"}]},{"given":"Yang","family":"Xiang","sequence":"additional","affiliation":[{"name":"Pengcheng Laboratory,Shenzhen"}]},{"given":"Hui","family":"Wang","sequence":"additional","affiliation":[{"name":"Pengcheng Laboratory,Shenzhen"}]},{"given":"Xixin","family":"Wu","sequence":"additional","affiliation":[{"name":"The Chinese University of Hong Kong,Hong Kong SAR"}]},{"given":"Zhiyong","family":"Wu","sequence":"additional","affiliation":[{"name":"Shenzhen International Graduate School, Tsinghua University,Shenzhen"}]},{"given":"Helen","family":"Meng","sequence":"additional","affiliation":[{"name":"The Chinese University of Hong Kong,Hong Kong SAR"}]}],"member":"263","reference":[{"key":"ref1","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2019-1473"},{"key":"ref2","article-title":"Decoar 2.0: Deep contextualized acous-tic representations with vector quantization","author":"Ling","year":"2020","journal-title":"arXiv preprint"},{"key":"ref3","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":"ref4","doi-asserted-by":"publisher","DOI":"10.1109\/TASLP.2021.3122291"},{"key":"ref5","doi-asserted-by":"publisher","DOI":"10.1109\/TPAMI.2018.2798607"},{"key":"ref6","article-title":"Slam: A unified encoder for speech and language modeling via speech-text joint pretraining","author":"Bapna","year":"2021","journal-title":"arXiv preprint"},{"key":"ref7","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2022-10937"},{"key":"ref8","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2022.emnlp-main.108"},{"key":"ref9","first-page":"8748","article-title":"Learning transferable visual models from natural language supervision","volume-title":"International conference on machine learning","author":"Radford"},{"key":"ref10","first-page":"4904","article-title":"Scaling up visual and vision-language representation learning with noisy text supervision","volume-title":"International Conference on Machine Learning","author":"Jia"},{"key":"ref11","article-title":"Bert: Pretraining of deep bidirectional transformers for language understanding","author":"Devlin","year":"2018","journal-title":"arXiv preprint"},{"key":"ref12","doi-asserted-by":"publisher","DOI":"10.48550\/ARXIV.1706.03762"},{"key":"ref13","article-title":"Cross-lingual language model pretraining","volume":"32","author":"Conneau","year":"2019","journal-title":"Advances in neural information processing systems"},{"key":"ref14","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2015.7178964"},{"key":"ref15","article-title":"Decoupled weight decay regularization","author":"Loshchilov","year":"2017","journal-title":"arXiv preprint"},{"key":"ref16","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2021-1775"},{"key":"ref17","doi-asserted-by":"publisher","DOI":"10.1109\/JSTSP.2022.3188113"},{"key":"ref18","first-page":"1298","article-title":"Data2vec: A general framework for self-supervised learning in speech, vision and language","volume-title":"International Conference on Ma-chine Learning","author":"Baevski"},{"key":"ref19","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2022.naacl-main.376"},{"issue":"11","key":"ref20","article-title":"Visualizing data using t-sne","volume":"9","author":"Van Der Maaten","year":"2008","journal-title":"Journal of machine learning research"},{"key":"ref21","doi-asserted-by":"publisher","DOI":"10.1214\/aoms\/1177704472"},{"key":"ref22","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2021-1912"},{"key":"ref23","article-title":"Speechstew: Simply mix all available speech recognition data to train one large neural network","author":"Chan","year":"2021","journal-title":"arXiv preprint"}],"event":{"name":"2024 IEEE 14th International Symposium on Chinese Spoken Language Processing (ISCSLP)","start":{"date-parts":[[2024,11,7]]},"location":"Beijing, China","end":{"date-parts":[[2024,11,10]]}},"container-title":["2024 IEEE 14th International Symposium on Chinese Spoken Language Processing (ISCSLP)"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx8\/10799944\/10799969\/10799993.pdf?arnumber=10799993","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2024,12,24]],"date-time":"2024-12-24T06:42:35Z","timestamp":1735022555000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/10799993\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2024,11,7]]},"references-count":23,"URL":"https:\/\/doi.org\/10.1109\/iscslp63861.2024.10799993","relation":{},"subject":[],"published":{"date-parts":[[2024,11,7]]}}}