{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,1,6]],"date-time":"2026-01-06T13:36:28Z","timestamp":1767706588826,"version":"3.28.0"},"reference-count":40,"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"}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":[],"published-print":{"date-parts":[[2023,6,4]]},"DOI":"10.1109\/icassp49357.2023.10096827","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":5,"title":["Bridging Speech and Textual Pre-Trained Models With Unsupervised ASR"],"prefix":"10.1109","author":[{"given":"Jiatong","family":"Shi","sequence":"first","affiliation":[{"name":"Carnegie Mellon University"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Chan-Jan","family":"Hsu","sequence":"additional","affiliation":[{"name":"National Taiwan University"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Holam","family":"Chung","sequence":"additional","affiliation":[{"name":"National Taiwan University"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Dongji","family":"Gao","sequence":"additional","affiliation":[{"name":"Johns Hopkins University"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Paola","family":"Garcia","sequence":"additional","affiliation":[{"name":"Johns Hopkins University"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Shinji","family":"Watanabe","sequence":"additional","affiliation":[{"name":"Carnegie Mellon University"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Ann","family":"Lee","sequence":"additional","affiliation":[{"name":"Meta AI"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Hung-Yi","family":"Lee","sequence":"additional","affiliation":[{"name":"National Taiwan University"}],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"263","reference":[{"key":"ref13","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2022-10702"},{"key":"ref35","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/D18-1241"},{"article-title":"mSLAM: Massively multilingual joint pre-training for speech and text","year":"2022","author":"bapna","key":"ref12"},{"key":"ref34","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/W17-2623"},{"key":"ref15","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2022-10610"},{"key":"ref37","doi-asserted-by":"publisher","DOI":"10.1162\/tacl_a_00461"},{"article-title":"Do we still need automatic speech recognition for spoken language understanding?","year":"2021","author":"borgholt","key":"ref14"},{"key":"ref36","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP40776.2020.9052942"},{"key":"ref31","doi-asserted-by":"publisher","DOI":"10.1007\/s10579-008-9076-6"},{"key":"ref30","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2020.acl-demos.34"},{"article-title":"SLAM: A unified encoder for speech and language modeling via speech-text joint pretraining","year":"2021","author":"bapna","key":"ref11"},{"key":"ref33","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/D16-1264"},{"key":"ref10","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2020.emnlp-main.588"},{"key":"ref32","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2021-2027"},{"key":"ref2","article-title":"wav2vec 2.0: A framework for self-supervised learning of speech representations","volume":"33","author":"baevski","year":"2020","journal-title":"NeurIPS"},{"key":"ref1","article-title":"BERT: Pre-training of deep bidirectional transformers for language understanding","author":"devlin","year":"2019","journal-title":"NAACL"},{"key":"ref17","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP43922.2022.9747674"},{"key":"ref39","doi-asserted-by":"publisher","DOI":"10.1109\/JSTSP.2017.2763455"},{"key":"ref16","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2020-3094"},{"key":"ref38","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP39728.2021.9414858"},{"key":"ref19","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2021.naacl-main.152"},{"key":"ref18","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2022-10890"},{"article-title":"Towards end-to-end unsupervised speech recognition","year":"2022","author":"liu","key":"ref24"},{"article-title":"T5lephone: Bridging speech and text self-supervised models for spoken language understanding via phoneme level t5","year":"2022","author":"hsu","key":"ref23"},{"key":"ref26","article-title":"Unsupervised speech recognition via segmental empirical output distribution matching","author":"yeh","year":"2018","journal-title":"ICLRE"},{"key":"ref25","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2019-2068"},{"key":"ref20","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP40776.2020.9053281"},{"key":"ref22","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2022-612"},{"key":"ref21","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP39728.2021.9414922"},{"key":"ref28","article-title":"Unsupervised speech recognition","author":"baevski","year":"2021","journal-title":"NeurIPS"},{"key":"ref27","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP40776.2020.9053571"},{"key":"ref29","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2022.acl-long.580"},{"article-title":"Effectiveness of self-supervised pre-training for speech recognition","year":"2019","author":"baevski","key":"ref8"},{"key":"ref7","article-title":"Self-supervised learning of visual features through embedding images into text top-iec spaces","author":"gomez","year":"2017","journal-title":"CVPR"},{"key":"ref9","doi-asserted-by":"publisher","DOI":"10.1109\/ASRU51503.2021.9688137"},{"key":"ref4","article-title":"Show, attend and tell: Neural image caption generation with visual attention","author":"xu","year":"2015","journal-title":"ICML"},{"key":"ref3","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2021-1775"},{"key":"ref6","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP43922.2022.9746818"},{"key":"ref5","volume":"1","author":"yu","year":"2016","journal-title":"Automatic Speech Recognition"},{"key":"ref40","doi-asserted-by":"publisher","DOI":"10.1145\/2792745.2792775"}],"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\/10096827.pdf?arnumber=10096827","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2023,11,20]],"date-time":"2023-11-20T18:58:23Z","timestamp":1700506703000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/10096827\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2023,6,4]]},"references-count":40,"URL":"https:\/\/doi.org\/10.1109\/icassp49357.2023.10096827","relation":{},"subject":[],"published":{"date-parts":[[2023,6,4]]}}}