{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,5,20]],"date-time":"2026-05-20T04:39:28Z","timestamp":1779251968706,"version":"3.51.4"},"reference-count":56,"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\/100002465","name":"Delta","doi-asserted-by":"publisher","id":[{"id":"10.13039\/100002465","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\/icassp48485.2024.10447926","type":"proceedings-article","created":{"date-parts":[[2024,3,18]],"date-time":"2024-03-18T18:56:31Z","timestamp":1710788191000},"page":"11941-11945","source":"Crossref","is-referenced-by-count":6,"title":["Cross-Modal Multi-Tasking for Speech-to-Text Translation via Hard Parameter Sharing"],"prefix":"10.1109","author":[{"given":"Brian","family":"Yan","sequence":"first","affiliation":[{"name":"Carnegie Mellon University,US"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Xuankai","family":"Chang","sequence":"additional","affiliation":[{"name":"Carnegie Mellon University,US"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Antonios","family":"Anastasopoulos","sequence":"additional","affiliation":[{"name":"George Mason University,US"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Yuya","family":"Fujita","sequence":"additional","affiliation":[{"name":"Yahoo Japan Corporation,JP"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Shinji","family":"Watanabe","sequence":"additional","affiliation":[{"name":"Carnegie Mellon University,US"}],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"263","reference":[{"key":"ref1","article-title":"Harnessing indirect training data for end-to-end automatic speech translation: Tricks of the trade","volume-title":"Proc. IWSLT","author":"Pino"},{"key":"ref2","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2021.naacl-main.150"},{"key":"ref3","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2022-10938"},{"key":"ref4","article-title":"An overview of multi-task learning in deep neural networks","author":"Ruder","year":"2017"},{"key":"ref5","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2022.acl-long.393"},{"key":"ref6","article-title":"Mslam: Massively multilingual joint pre-training for speech and text","author":"Bapna","year":"2022"},{"key":"ref7","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2022.acl-long.105"},{"key":"ref8","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2022.naacl-main.376"},{"key":"ref9","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2022.acl-long.486"},{"key":"ref10","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2022-10937"},{"key":"ref11","article-title":"M 3 st: Mix at three levels for speech translation","volume-title":"Proc. ICASSP","author":"Cheng"},{"key":"ref12","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2023.acl-long.216"},{"key":"ref13","doi-asserted-by":"publisher","DOI":"10.1109\/ASRU57964.2023.10389705"},{"key":"ref14","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2023-2051"},{"key":"ref15","article-title":"Audiopalm: A large language model that can speak and listen","author":"Rubenstein","year":"2023"},{"key":"ref16","article-title":"Discretalk: Text-to-speech as a machine translation problem","author":"Hayashi","year":"2020"},{"key":"ref17","article-title":"On generative spoken language modeling from raw audio","author":"Lakhotia","year":"2021","journal-title":"TACL"},{"key":"ref18","article-title":"Neural codec language models are zero-shot text to speech synthesizers","author":"Wang","year":"2023"},{"key":"ref19","article-title":"Textually pretrained speech language models","author":"Hassid","year":"2023"},{"key":"ref20","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2022.acl-long.235"},{"key":"ref21","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP49357.2023.10096797"},{"key":"ref22","doi-asserted-by":"publisher","DOI":"10.1109\/JSTSP.2022.3188113"},{"key":"ref23","article-title":"Must-c: A multilingual speech translation corpus","volume-title":"Proc. NAACL","author":"Gangi"},{"key":"ref24","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/W16-2301"},{"key":"ref25","doi-asserted-by":"publisher","DOI":"10.1162\/tacl_a_00343"},{"key":"ref26","article-title":"Multilingual translation with extensible multilingual pretraining and finetuning","author":"Tang","year":"2020"},{"key":"ref27","article-title":"Neural discrete representation learning","volume-title":"Proc. Neurips","author":"Van Den Oord"},{"key":"ref28","article-title":"Soundstream: An end-to-end neural audio codec","author":"Zeghidour","year":"2021","journal-title":"TASLP"},{"key":"ref29","article-title":"High fidelity neural audio compression","author":"D\u00e9fossez","year":"2022"},{"key":"ref30","doi-asserted-by":"publisher","DOI":"10.1109\/TASLP.2021.3122291"},{"key":"ref31","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP49357.2023.10096149"},{"key":"ref32","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/D18-2012"},{"key":"ref33","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2020.acl-main.170"},{"key":"ref34","doi-asserted-by":"publisher","DOI":"10.1109\/taslp.2023.3328283"},{"key":"ref35","doi-asserted-by":"publisher","DOI":"10.1613\/jair.1.12007"},{"key":"ref36","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2019-2680"},{"key":"ref37","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2018-2456"},{"key":"ref38","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP43922.2022.9747862"},{"key":"ref39","article-title":"Neural machine translation by jointly learning to align and translate","volume-title":"Proc. ICLR","author":"Bahdanau"},{"key":"ref40","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2016.7472621"},{"key":"ref41","doi-asserted-by":"publisher","DOI":"10.1145\/1143844.1143891"},{"key":"ref42","article-title":"Sequence Transduction with Recurrent Neural Networks","volume-title":"Proc. ICML","author":"Graves"},{"key":"ref43","doi-asserted-by":"publisher","DOI":"10.1109\/JSTSP.2017.2763455"},{"key":"ref44","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2023.eacl-main.119"},{"key":"ref45","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2020.acl-demos.34"},{"key":"ref46","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2021.eacl-main.57"},{"key":"ref47","article-title":"Revisiting end-to-end speech-to-text translation from scratch","volume-title":"Proc. ICML","author":"Zhang"},{"key":"ref48","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2023.acl-demo.38"},{"key":"ref49","doi-asserted-by":"publisher","DOI":"10.1109\/SLT54892.2023.10022656"},{"key":"ref50","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2021.acl-long.68"},{"key":"ref51","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2023.iwslt-1.20"},{"key":"ref52","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/W18-6319"},{"key":"ref53","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2022.iwslt-1.14"},{"key":"ref54","article-title":"The yitrans end-to-end speech translation system for iwslt 2022 offline shared task","volume-title":"Proc. IWSLT","author":"Zhang"},{"key":"ref55","doi-asserted-by":"publisher","DOI":"10.1186\/s40537-017-0089-0"},{"key":"ref56","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2023.acl-long.872"}],"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\/10447926.pdf?arnumber=10447926","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2024,8,2]],"date-time":"2024-08-02T04:35:34Z","timestamp":1722573334000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/10447926\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2024,4,14]]},"references-count":56,"URL":"https:\/\/doi.org\/10.1109\/icassp48485.2024.10447926","relation":{},"subject":[],"published":{"date-parts":[[2024,4,14]]}}}