{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,4,22]],"date-time":"2026-04-22T19:46:39Z","timestamp":1776887199220,"version":"3.51.2"},"reference-count":46,"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"}],"funder":[{"DOI":"10.13039\/100000001","name":"National Science Foundation","doi-asserted-by":"publisher","id":[{"id":"10.13039\/100000001","id-type":"DOI","asserted-by":"publisher"}]}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":[],"published-print":{"date-parts":[[2024,4,14]]},"DOI":"10.1109\/icassp48485.2024.10447929","type":"proceedings-article","created":{"date-parts":[[2024,3,18]],"date-time":"2024-03-18T18:56:31Z","timestamp":1710788191000},"page":"11481-11485","source":"Crossref","is-referenced-by-count":30,"title":["Exploring Speech Recognition, Translation, and Understanding with Discrete Speech Units: A Comparative Study"],"prefix":"10.1109","author":[{"given":"Xuankai","family":"Chang","sequence":"first","affiliation":[{"name":"Carnegie Mellon University"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Brian","family":"Yan","sequence":"additional","affiliation":[{"name":"Carnegie Mellon University"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Kwanghee","family":"Choi","sequence":"additional","affiliation":[{"name":"Carnegie Mellon University"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Jee-Weon","family":"Jung","sequence":"additional","affiliation":[{"name":"Carnegie Mellon University"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Yichen","family":"Lu","sequence":"additional","affiliation":[{"name":"Carnegie Mellon University"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Soumi","family":"Maiti","sequence":"additional","affiliation":[{"name":"Carnegie Mellon University"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Roshan","family":"Sharma","sequence":"additional","affiliation":[{"name":"Carnegie Mellon University"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Jiatong","family":"Shi","sequence":"additional","affiliation":[{"name":"Carnegie Mellon University"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Jinchuan","family":"Tian","sequence":"additional","affiliation":[{"name":"Carnegie Mellon University"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Shinji","family":"Watanabe","sequence":"additional","affiliation":[{"name":"Carnegie Mellon University"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Yuya","family":"Fujita","sequence":"additional","affiliation":[{"name":"Yahoo Japan Corporation"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Takashi","family":"Maekaku","sequence":"additional","affiliation":[{"name":"Yahoo Japan Corporation"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Pengcheng","family":"Guo","sequence":"additional","affiliation":[{"name":"Northwestern Polytechnical University"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Yao-Fei","family":"Cheng","sequence":"additional","affiliation":[{"name":"University of Washington"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Pavel","family":"Denisov","sequence":"additional","affiliation":[{"name":"University of Stuttgart"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Kohei","family":"Saijo","sequence":"additional","affiliation":[{"name":"Waseda University"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Hsiu-Hsuan","family":"Wang","sequence":"additional","affiliation":[{"name":"National Taiwan University"}],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"263","reference":[{"key":"ref1","doi-asserted-by":"publisher","DOI":"10.1109\/MSP.2012.2205597"},{"key":"ref2","doi-asserted-by":"publisher","DOI":"10.1109\/TASLP.2016.2602884"},{"key":"ref3","doi-asserted-by":"publisher","DOI":"10.1145\/1143844.1143891"},{"key":"ref4","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-642-24797-2"},{"key":"ref5","first-page":"577","article-title":"Attention-based models for speech recognition","volume":"2015","author":"Chorowski","year":"2015","journal-title":"NeurIPS"},{"key":"ref6","doi-asserted-by":"publisher","DOI":"10.48550\/ARXIV.1706.03762"},{"key":"ref7","doi-asserted-by":"publisher","DOI":"10.21437\/interspeech.2020-3015"},{"key":"ref8","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP39728.2021.9414858"},{"key":"ref9","doi-asserted-by":"publisher","DOI":"10.1109\/SLT54892.2023.10022656"},{"key":"ref10","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2019-1873"},{"key":"ref11","article-title":"Vq-wav2vec: Self-supervised learning of discrete speech representations","volume-title":"Proc. ICLR","author":"Baevski"},{"key":"ref12","first-page":"12 449","article-title":"Wav2vec 2.0: A framework for self-supervised learning of speech representations","volume":"33","author":"Baevski","year":"2020","journal-title":"NeurIPS"},{"key":"ref13","doi-asserted-by":"publisher","DOI":"10.1109\/TASLP.2021.3122291"},{"key":"ref14","doi-asserted-by":"publisher","DOI":"10.1109\/JSTSP.2022.3188113"},{"key":"ref15","first-page":"28 492","article-title":"Robust speech recognition via large-scale weak supervision","volume-title":"Proc. ICML","author":"Radford"},{"key":"ref16","doi-asserted-by":"publisher","DOI":"10.21437\/interspeech.2015-1"},{"key":"ref17","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2023-2051"},{"key":"ref18","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP40776.2020.9054224"},{"key":"ref19","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2023.findings-acl.447"},{"key":"ref20","author":"Kim","year":"2023","journal-title":"Many-to-many spoken language translation via unified speech and text representation learning with unit-to-unit translation"},{"key":"ref21","author":"Hayashi","year":"2020","journal-title":"Discretalk: Text-to-speech as a machine translation problem"},{"key":"ref22","author":"Shi","year":"2021","journal-title":"Discretization and re-synthesis: An alternative method to solve the cocktail party problem"},{"key":"ref23","doi-asserted-by":"publisher","DOI":"10.1109\/TASLP.2023.3288409"},{"key":"ref24","author":"Wang","year":"2023","journal-title":"Neural codec language models are zero-shot text to speech synthesizers"},{"key":"ref25","author":"Rubenstein","year":"2023","journal-title":"Audiopalm: A large language model that can speak and listen"},{"key":"ref26","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP49357.2023.10096149"},{"key":"ref27","author":"D\u00e9fossez","year":"2022","journal-title":"High fidelity neural audio compression"},{"key":"ref28","doi-asserted-by":"publisher","DOI":"10.21437\/interspeech.2018-1456"},{"key":"ref29","article-title":"Neural discrete representation learning","volume":"30","author":"Van Den Oord","year":"2017","journal-title":"NeurIPS"},{"key":"ref30","doi-asserted-by":"publisher","DOI":"10.1109\/TASLP.2021.3129994"},{"key":"ref31","author":"Barrault","year":"2023","journal-title":"Seamlessm4t-massively multilingual & multi-modal machine translation"},{"key":"ref32","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2015.7178964"},{"key":"ref33","article-title":"The 4th chime speech separation and recognition challenge","author":"Vincent","year":"2016"},{"key":"ref34","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.1992.225858"},{"key":"ref35","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2021-1965"},{"key":"ref36","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-319-99579-3_21"},{"key":"ref37","article-title":"How2: A large-scale dataset for multimodal language understanding","author":"Sanabria","year":"2018","journal-title":"NeurIPS"},{"key":"ref38","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2021-1860"},{"key":"ref39","first-page":"2012","article-title":"Must-c: A multilingual speech translation corpus","volume-title":"Proc. NAACL","author":"Gangi"},{"key":"ref40","doi-asserted-by":"publisher","DOI":"10.1109\/ICSDA.2017.8384449"},{"key":"ref41","first-page":"4218","article-title":"Common voice: A massively-multilingual speech corpus","volume-title":"English, in Proceedings of the Twelfth Language Resources and Evaluation Conference","author":"Ardila"},{"key":"ref42","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2023-1316"},{"key":"ref43","doi-asserted-by":"publisher","DOI":"10.1109\/ASRU57964.2023.10389676"},{"key":"ref44","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2023.eacl-main.119"},{"key":"ref45","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2023.acl-demo.38"},{"key":"ref46","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2020.emnlp-main.588"}],"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\/10447929.pdf?arnumber=10447929","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2024,8,2]],"date-time":"2024-08-02T04:35:38Z","timestamp":1722573338000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/10447929\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2024,4,14]]},"references-count":46,"URL":"https:\/\/doi.org\/10.1109\/icassp48485.2024.10447929","relation":{},"subject":[],"published":{"date-parts":[[2024,4,14]]}}}