{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,3,25]],"date-time":"2026-03-25T06:12:06Z","timestamp":1774419126023,"version":"3.50.1"},"reference-count":33,"publisher":"IEEE","license":[{"start":{"date-parts":[[2025,4,6]],"date-time":"2025-04-06T00:00:00Z","timestamp":1743897600000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2025,4,6]],"date-time":"2025-04-06T00:00:00Z","timestamp":1743897600000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-037"}],"funder":[{"DOI":"10.13039\/501100012166","name":"National Key Research and Development Program of China","doi-asserted-by":"publisher","id":[{"id":"10.13039\/501100012166","id-type":"DOI","asserted-by":"publisher"}]},{"DOI":"10.13039\/501100002701","name":"Ministry of Education","doi-asserted-by":"publisher","id":[{"id":"10.13039\/501100002701","id-type":"DOI","asserted-by":"publisher"}]}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":[],"published-print":{"date-parts":[[2025,4,6]]},"DOI":"10.1109\/icassp49660.2025.10888294","type":"proceedings-article","created":{"date-parts":[[2025,3,12]],"date-time":"2025-03-12T17:15:19Z","timestamp":1741799719000},"page":"1-5","source":"Crossref","is-referenced-by-count":0,"title":["Adversarial Speech-Text Pre-Training for Speech Translation"],"prefix":"10.1109","author":[{"given":"Chenxuan","family":"Liu","sequence":"first","affiliation":[{"name":"NERC-SLIP,USTC,Hefei,China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Liping","family":"Chen","sequence":"additional","affiliation":[{"name":"NERC-SLIP,USTC,Hefei,China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Weitai","family":"Zhang","sequence":"additional","affiliation":[{"name":"NERC-SLIP,USTC,Hefei,China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Xiaoxi","family":"Li","sequence":"additional","affiliation":[{"name":"iFLYTEK Research,Hefei,China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Peiwang","family":"Tang","sequence":"additional","affiliation":[{"name":"iFLYTEK Research,Hefei,China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Mingjia","family":"Yu","sequence":"additional","affiliation":[{"name":"Coll. of Econ. & Mgmt.,CJLU,Hangzhou,China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Sreyan","family":"Ghosh","sequence":"additional","affiliation":[{"name":"University of Maryland,Dept. of Computer Science,College Park,USA"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Zhongyi","family":"Ye","sequence":"additional","affiliation":[{"name":"iFLYTEK Research,Hefei,China"}],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"263","reference":[{"key":"ref1","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/N16-1109"},{"key":"ref2","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2017-503"},{"key":"ref3","first-page":"26193","article-title":"Revisiting end-to-end speech-to-text translation from scratch","volume-title":"Proc. ICML","author":"Zhang"},{"key":"ref4","doi-asserted-by":"publisher","DOI":"10.1109\/ASRU46091.2019.9003774"},{"key":"ref5","first-page":"12449","article-title":"wav2vec 2.0: A framework for self-supervised learning of speech representations","volume-title":"Proc. NeurIPS","volume":"33","author":"Baevski"},{"key":"ref6","doi-asserted-by":"publisher","DOI":"10.1109\/JSTSP.2022.3188113"},{"key":"ref7","doi-asserted-by":"publisher","DOI":"10.1109\/TASLP.2021.3122291"},{"key":"ref8","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2022.acl-long.105"},{"key":"ref9","article-title":"SLAM: A unified encoder for speech and language modeling via speech-text joint pre-training","author":"Bapna","year":"2021"},{"key":"ref10","doi-asserted-by":"publisher","DOI":"10.1109\/TASLP.2024.3379877"},{"key":"ref11","article-title":"mSLAM: Massively multilingual joint pre-training for speech and text","author":"Bapna","year":"2022"},{"key":"ref12","doi-asserted-by":"publisher","DOI":"10.1145\/1143844.1143891"},{"key":"ref13","doi-asserted-by":"publisher","DOI":"10.1109\/JSTSP.2017.2763455"},{"key":"ref14","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2021.acl-long.204"},{"key":"ref15","article-title":"Generative adversarial nets","volume-title":"Proc. NeurIPS","volume":"27","author":"Goodfellow"},{"key":"ref16","doi-asserted-by":"publisher","DOI":"10.1016\/j.csl.2021.101308"},{"key":"ref17","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2024.findings-emnlp.263"},{"key":"ref18","article-title":"Qwen2-audio technical report","author":"Chu","year":"2024"},{"key":"ref19","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2024.findings-acl.416"},{"key":"ref20","doi-asserted-by":"publisher","DOI":"10.1016\/j.csl.2020.101155"},{"key":"ref21","article-title":"Common voice: A massively-multilingual speech corpus","volume-title":"ArXiv","volume":"abs\/1912.06670","author":"Ardila","year":"2019"},{"key":"ref22","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2023.acl-long.61"},{"key":"ref23","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP48485.2024.10446635"},{"key":"ref24","doi-asserted-by":"publisher","DOI":"10.5555\/3295222.3295349"},{"key":"ref25","doi-asserted-by":"publisher","DOI":"10.1162\/tacl_a_00300"},{"key":"ref26","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2016.90"},{"key":"ref27","article-title":"LoRA: Low-rank adaptation of large language models","volume-title":"Proc. ICLR","author":"Hu"},{"key":"ref28","article-title":"Efficient and effective text encoding for Chinese LLaMA and Alpaca","author":"Cui","year":"2023"},{"key":"ref29","article-title":"Multilingual translation with extensible multilingual pretraining and finetuning","author":"Tang","year":"2020"},{"key":"ref30","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2020.acl-demos.34"},{"key":"ref31","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v35i14.17508"},{"key":"ref32","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/W18-6319"},{"key":"ref33","first-page":"28492","article-title":"Robust speech recognition via large-scale weak supervision","volume-title":"Proc. ICML","author":"Radford"}],"event":{"name":"ICASSP 2025 - 2025 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)","location":"Hyderabad, India","start":{"date-parts":[[2025,4,6]]},"end":{"date-parts":[[2025,4,11]]}},"container-title":["ICASSP 2025 - 2025 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx8\/10887540\/10887541\/10888294.pdf?arnumber=10888294","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2026,3,25]],"date-time":"2026-03-25T05:20:40Z","timestamp":1774416040000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/10888294\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2025,4,6]]},"references-count":33,"URL":"https:\/\/doi.org\/10.1109\/icassp49660.2025.10888294","relation":{},"subject":[],"published":{"date-parts":[[2025,4,6]]}}}