{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,4,22]],"date-time":"2026-04-22T19:18:19Z","timestamp":1776885499040,"version":"3.51.2"},"reference-count":33,"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"}]},{"DOI":"10.13039\/501100020785","name":"Shenzhen Research Institute of Big Data","doi-asserted-by":"publisher","id":[{"id":"10.13039\/501100020785","id-type":"DOI","asserted-by":"publisher"}]},{"DOI":"10.13039\/501100004853","name":"Chinese University of Hong Kong","doi-asserted-by":"publisher","id":[{"id":"10.13039\/501100004853","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\/icassp49357.2023.10096923","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":8,"title":["Token2vec: A Joint Self-Supervised Pre-Training Framework Using Unpaired Speech and Text"],"prefix":"10.1109","author":[{"given":"Xianghu","family":"Yue","sequence":"first","affiliation":[{"name":"National University of Singapore,Department of Electrical and Computer Engineering,Singapore"}]},{"given":"Junyi","family":"Ao","sequence":"additional","affiliation":[{"name":"Shenzhen Research Institute of Big Data,Shenzhen,China"}]},{"given":"Xiaoxue","family":"Gao","sequence":"additional","affiliation":[{"name":"National University of Singapore,Department of Electrical and Computer Engineering,Singapore"}]},{"given":"Haizhou","family":"Li","sequence":"additional","affiliation":[{"name":"National University of Singapore,Department of Electrical and Computer Engineering,Singapore"}]}],"member":"263","reference":[{"key":"ref13","first-page":"4411","article-title":"Xtreme: A massively multilingual multi-task benchmark for evaluating cross-lingual generalisation","author":"hu","year":"2020","journal-title":"ICML"},{"key":"ref12","article-title":"SuperGLUE: A stickier benchmark for general-purpose language understanding systems","author":"wang","year":"2019","journal-title":"NeurIPS"},{"key":"ref15","article-title":"SLAM: A unified encoder for speech and language modeling via speechtext joint pre-training","author":"bapna","year":"2021"},{"key":"ref14","first-page":"4171","article-title":"Bert: Pre-training of deep bidirectional transformers for language understanding","author":"devlin","year":"2019","journal-title":"NAACL"},{"key":"ref31","article-title":"Librilight: A benchmark for asr with limited or no supervision","author":"kahn","year":"2020","journal-title":"ICASSP"},{"key":"ref30","first-page":"6000","article-title":"Attention is all you need","author":"vaswani","year":"2018","journal-title":"NIPS"},{"key":"ref11","article-title":"GLUE: A multi-task benchmark and analysis platform for natural language understanding","author":"wang","year":"2019","journal-title":"ICLRE"},{"key":"ref33","article-title":"Adam: A method for stochastic optimization","author":"kingma","year":"2015","journal-title":"ICLRE"},{"key":"ref10","doi-asserted-by":"publisher","DOI":"10.1162\/tacl_a_00300"},{"key":"ref32","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/N19-4009"},{"key":"ref2","doi-asserted-by":"publisher","DOI":"10.1109\/TASLP.2021.3122291"},{"key":"ref1","article-title":"wav2vec 2.0: A framework for self-supervised learning of speech representations","author":"baevski","year":"2020","journal-title":"NeurIPS"},{"key":"ref17","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2021.naacl-main.152"},{"key":"ref16","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP39728.2021.9413359"},{"key":"ref19","article-title":"mSLAM: Massively multilingual joint pre-training for speech and text","author":"bapna","year":"2022"},{"key":"ref18","doi-asserted-by":"publisher","DOI":"10.1109\/JSTSP.2022.3192714"},{"key":"ref24","first-page":"1336","article-title":"Generative spoken language modeling from raw audio","author":"lakhotia","year":"2021","journal-title":"TACL"},{"key":"ref23","article-title":"vqwav2vec: Self-supervised learning of discrete speech representations","author":"baevski","year":"2020","journal-title":"ICLRE"},{"key":"ref26","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2022.acl-long.235"},{"key":"ref25","article-title":"AudioLM: a language modeling approach to audio generation","author":"borsos","year":"2022"},{"key":"ref20","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2022-10937"},{"key":"ref22","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP40776.2020.9054224"},{"key":"ref21","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2015.7178964"},{"key":"ref28","first-page":"791","article-title":"Genreconditioned acoustic models for automatic lyrics transcription of polyphonic music","author":"gao","year":"2022","journal-title":"ICASSP"},{"key":"ref27","first-page":"2280","article-title":"Automatic lyrics transcription of polyphonic music with lyricschord multi-task learning","volume":"30","author":"gao","year":"2022","journal-title":"IEEE TASLP"},{"key":"ref29","article-title":"SpeechLM: Enhanced speech pre-training with unpaired textual data","author":"zhang","year":"2022"},{"key":"ref8","article-title":"Roberta: A robustly optimized bert pretraining approach","author":"liu","year":"2019"},{"key":"ref7","article-title":"Improving language understanding by generative pre-training","author":"radford","year":"2018"},{"key":"ref9","first-page":"5753","article-title":"Xlnet: generalized autoregressive pretraining for language understanding","author":"yang","year":"2019","journal-title":"Proc 33th Conf Neural Inf Process Syst"},{"key":"ref4","doi-asserted-by":"publisher","DOI":"10.1109\/JSTSP.2022.3188113"},{"key":"ref3","first-page":"1298","article-title":"data2vec: A general framework for self-supervised learning in speech, vision and language","author":"baevski","year":"2022","journal-title":"ICML"},{"key":"ref6","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2021-1775"},{"key":"ref5","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2022-936"}],"event":{"name":"ICASSP 2023 - 2023 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)","location":"Rhodes Island, Greece","start":{"date-parts":[[2023,6,4]]},"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\/10096923.pdf?arnumber=10096923","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2023,11,13]],"date-time":"2023-11-13T19:03:17Z","timestamp":1699902197000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/10096923\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2023,6,4]]},"references-count":33,"URL":"https:\/\/doi.org\/10.1109\/icassp49357.2023.10096923","relation":{},"subject":[],"published":{"date-parts":[[2023,6,4]]}}}