{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2025,2,21]],"date-time":"2025-02-21T01:36:45Z","timestamp":1740101805540,"version":"3.37.3"},"reference-count":18,"publisher":"IEEE","license":[{"start":{"date-parts":[[2023,6,4]],"date-time":"2023-06-04T00:00:00Z","timestamp":1685836800000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2023,6,4]],"date-time":"2023-06-04T00:00:00Z","timestamp":1685836800000},"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","id":[{"id":"10.13039\/501100001809","id-type":"DOI","asserted-by":"publisher"}]}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":[],"published-print":{"date-parts":[[2023,6,4]]},"DOI":"10.1109\/icassp49357.2023.10095130","type":"proceedings-article","created":{"date-parts":[[2023,5,5]],"date-time":"2023-05-05T17:28:30Z","timestamp":1683307710000},"page":"1-5","source":"Crossref","is-referenced-by-count":2,"title":["Front-End Adapter: Adapting Front-End Input of Speech Based Self-Supervised Learning for Speech Recognition"],"prefix":"10.1109","author":[{"given":"Xie","family":"Chen","sequence":"first","affiliation":[{"name":"Shanghai Jiao Tong University,MoE Key Lab of Artificial Intelligence, AI Institute X-Lance Lab,Department of Computer Science and Engineering,Shanghai,China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Ziyang","family":"Ma","sequence":"additional","affiliation":[{"name":"Shanghai Jiao Tong University,MoE Key Lab of Artificial Intelligence, AI Institute X-Lance Lab,Department of Computer Science and Engineering,Shanghai,China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Changli","family":"Tang","sequence":"additional","affiliation":[{"name":"Tsinghua University,Department of Electronic Engineering,Beijing,China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Yujin","family":"Wang","sequence":"additional","affiliation":[{"name":"Tsinghua University,Department of Electronic Engineering,Beijing,China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Zhisheng","family":"Zheng","sequence":"additional","affiliation":[{"name":"Shanghai Jiao Tong University,MoE Key Lab of Artificial Intelligence, AI Institute X-Lance Lab,Department of Computer Science and Engineering,Shanghai,China"}],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"263","reference":[{"article-title":"VQ-wav2vec: Self-supervised learning of discrete speech representations","year":"2019","author":"baevski","key":"ref13"},{"key":"ref12","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2019-1873"},{"key":"ref15","first-page":"21271","article-title":"Bootstrap your own latent-a new approach to self-supervised learning","volume":"33","author":"grill","year":"2020","journal-title":"Advances in neural information processing systems"},{"article-title":"Representation learning with contrastive predictive coding","year":"2018","author":"van den oord","key":"ref14"},{"key":"ref11","doi-asserted-by":"publisher","DOI":"10.1145\/1143844.1143891"},{"key":"ref10","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/N19-4009"},{"key":"ref2","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2015.167"},{"article-title":"BERT: Pre-training of deep bidirectional Transformers for language understanding","year":"2018","author":"devlin","key":"ref1"},{"key":"ref17","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2021-1965"},{"key":"ref16","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2015.7178964"},{"key":"ref18","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2019-2680"},{"article-title":"BigSSL: Exploring the frontier of large-scale semi-supervised learning for automatic speech recognition","year":"2021","author":"zhang","key":"ref8"},{"key":"ref7","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2021-1775"},{"article-title":"Mt4ssl: Boosting self-supervised speech representation learning by integrating multiple targets","year":"2022","author":"ma","key":"ref9"},{"key":"ref4","doi-asserted-by":"publisher","DOI":"10.1109\/TASLP.2021.3122291"},{"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":"Proc NIPS"},{"article-title":"Data2vec: A general framework for self-supervised learning in speech, vision and language","year":"2022","author":"baevski","key":"ref6"},{"article-title":"WavLM: Large-scale self-supervised pre-training for full stack speech processing","year":"2021","author":"chen","key":"ref5"}],"event":{"name":"ICASSP 2023 - 2023 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)","start":{"date-parts":[[2023,6,4]]},"location":"Rhodes Island, Greece","end":{"date-parts":[[2023,6,10]]}},"container-title":["ICASSP 2023 - 2023 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx7\/10094559\/10094560\/10095130.pdf?arnumber=10095130","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2023,11,20]],"date-time":"2023-11-20T19:02:22Z","timestamp":1700506942000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/10095130\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2023,6,4]]},"references-count":18,"URL":"https:\/\/doi.org\/10.1109\/icassp49357.2023.10095130","relation":{},"subject":[],"published":{"date-parts":[[2023,6,4]]}}}