{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,4,22]],"date-time":"2026-04-22T18:58:08Z","timestamp":1776884288891,"version":"3.51.2"},"reference-count":21,"publisher":"IEEE","license":[{"start":{"date-parts":[[2024,4,14]],"date-time":"2024-04-14T00:00:00Z","timestamp":1713052800000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2024,4,14]],"date-time":"2024-04-14T00:00:00Z","timestamp":1713052800000},"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":[[2024,4,14]]},"DOI":"10.1109\/icassp48485.2024.10447797","type":"proceedings-article","created":{"date-parts":[[2024,3,18]],"date-time":"2024-03-18T18:56:31Z","timestamp":1710788191000},"page":"10196-10200","source":"Crossref","is-referenced-by-count":10,"title":["Learning Speech Representation from Contrastive Token-Acoustic Pretraining"],"prefix":"10.1109","author":[{"given":"Chunyu","family":"Qiang","sequence":"first","affiliation":[{"name":"Tianjin University,School of New Media and Communication,Tianjin,China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Hao","family":"Li","sequence":"additional","affiliation":[{"name":"Kuaishou Technology Co., Ltd,Beijing,China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Yixin","family":"Tian","sequence":"additional","affiliation":[{"name":"Kuaishou Technology Co., Ltd,Beijing,China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Ruibo","family":"Fu","sequence":"additional","affiliation":[{"name":"Chinese Academy of Sciences,Institute of Automation,Beijing,China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Tao","family":"Wang","sequence":"additional","affiliation":[{"name":"Chinese Academy of Sciences,Institute of Automation,Beijing,China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Longbiao","family":"Wang","sequence":"additional","affiliation":[{"name":"Tianjin University,School of New Media and Communication,Tianjin,China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Jianwu","family":"Dang","sequence":"additional","affiliation":[{"name":"Tianjin University,Tianjin Key Laboratory of Cognitive Computing and Application, College of Intelligence and Computing,Tianjin,China"}],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"263","reference":[{"key":"ref1","doi-asserted-by":"publisher","DOI":"10.1109\/JSTSP.2022.3207050"},{"key":"ref2","article-title":"wav2vec 2.0: A framework for self-supervised learning of speech representations","author":"Baevski","year":"2020","journal-title":"Advances in neural information processing systems"},{"key":"ref3","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2021-717"},{"key":"ref4","article-title":"vq-wav2vec: Self-supervised learning of discrete speech representations","author":"Baevski","year":"2019"},{"key":"ref5","doi-asserted-by":"publisher","DOI":"10.1109\/TASLP.2021.3122291"},{"key":"ref6","doi-asserted-by":"publisher","DOI":"10.1109\/ASRU51503.2021.9688253"},{"key":"ref7","doi-asserted-by":"publisher","DOI":"10.1162\/tacl_a_00618"},{"key":"ref8","doi-asserted-by":"publisher","DOI":"10.1109\/icassp48485.2024.10446203"},{"key":"ref9","doi-asserted-by":"publisher","DOI":"10.1109\/ICME.2016.7552917"},{"key":"ref10","first-page":"8748","article-title":"Learning transferable visual models from natural language supervision","volume-title":"International conference on machine learning","author":"Radford"},{"key":"ref11","article-title":"Florence: A new foundation model for computer vision","author":"Yuan","year":"2021"},{"key":"ref12","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":"ref13","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP43922.2022.9747669"},{"key":"ref14","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP43922.2022.9747631"},{"key":"ref15","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP49357.2023.10095889"},{"key":"ref16","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP49357.2023.10095840"},{"key":"ref17","article-title":"High fidelity neural audio compression","author":"D\u00e9fossez","year":"2022","journal-title":"ArXiv"},{"key":"ref18","first-page":"28492","article-title":"Robust speech recognition via large-scale weak supervision","volume-title":"International Conference on Machine Learning","author":"Radford"},{"key":"ref19","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2018.00745"},{"key":"ref20","article-title":"Adam: A method for stochastic optimization","author":"Kingma","year":"2014","journal-title":"CoRR"},{"key":"ref21","doi-asserted-by":"publisher","DOI":"10.21437\/interspeech.2021-755"}],"event":{"name":"ICASSP 2024 - 2024 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)","location":"Seoul, Korea, Republic of","start":{"date-parts":[[2024,4,14]]},"end":{"date-parts":[[2024,4,19]]}},"container-title":["ICASSP 2024 - 2024 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx7\/10445798\/10445803\/10447797.pdf?arnumber=10447797","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2024,8,2]],"date-time":"2024-08-02T06:11:50Z","timestamp":1722579110000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/10447797\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2024,4,14]]},"references-count":21,"URL":"https:\/\/doi.org\/10.1109\/icassp48485.2024.10447797","relation":{},"subject":[],"published":{"date-parts":[[2024,4,14]]}}}