{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2025,11,29]],"date-time":"2025-11-29T07:16:16Z","timestamp":1764400576931,"version":"3.46.0"},"reference-count":32,"publisher":"IEEE","license":[{"start":{"date-parts":[[2025,10,22]],"date-time":"2025-10-22T00:00:00Z","timestamp":1761091200000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2025,10,22]],"date-time":"2025-10-22T00:00:00Z","timestamp":1761091200000},"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":[[2025,10,22]]},"DOI":"10.1109\/apsipaasc65261.2025.11249353","type":"proceedings-article","created":{"date-parts":[[2025,11,28]],"date-time":"2025-11-28T18:40:26Z","timestamp":1764355226000},"page":"909-914","source":"Crossref","is-referenced-by-count":0,"title":["Semi-Supervised End-to-End Speech-to-Text Translation with Joint Text-to-Text and Speech-to-Text Decoding"],"prefix":"10.1109","author":[{"given":"Tomohiro","family":"Tanaka","sequence":"first","affiliation":[{"name":"NTT, Inc.,Japan"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Ryo","family":"Masumura","sequence":"additional","affiliation":[{"name":"NTT, Inc.,Japan"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Naoki","family":"Makishima","sequence":"additional","affiliation":[{"name":"NTT, Inc.,Japan"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Mana","family":"Ihori","sequence":"additional","affiliation":[{"name":"NTT, Inc.,Japan"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Shota","family":"Orihashi","sequence":"additional","affiliation":[{"name":"NTT, Inc.,Japan"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Satoshi","family":"Suzuki","sequence":"additional","affiliation":[{"name":"NTT, Inc.,Japan"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Taiga","family":"Yamane","sequence":"additional","affiliation":[{"name":"NTT, Inc.,Japan"}],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"263","reference":[{"key":"ref1","article-title":"Harnessing indirect training data for end-toend automatic speech translation: Tricks of the trade","volume-title":"Proc. of International Conference on Spoken Language Translation (IWSLT)","author":"Pino","year":"2019"},{"key":"ref2","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2019.8683343"},{"key":"ref3","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2017-503"},{"key":"ref4","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2018.8461690"},{"key":"ref5","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/N19-1006"},{"key":"ref6","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP40776.2020.9053847"},{"key":"ref7","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2019-2582"},{"key":"ref8","doi-asserted-by":"publisher","DOI":"10.1109\/icassp48485.2024.10445811"},{"key":"ref9","doi-asserted-by":"publisher","DOI":"10.1109\/asru46091.2019.9004003"},{"key":"ref10","doi-asserted-by":"publisher","DOI":"10.1109\/ASRU46091.2019.9003832"},{"key":"ref11","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2023.findings-acl.447"},{"key":"ref12","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2020-2938"},{"key":"ref13","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2023.findings-acl.483"},{"key":"ref14","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v32i1.11248"},{"key":"ref15","article-title":"Revisiting selftraining for neural sequence generation","volume-title":"Proc. of International Conference on Learning Representations (ICLR)","author":"He","year":"2020"},{"key":"ref16","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2021.acl-long.221"},{"key":"ref17","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2020-1800"},{"key":"ref18","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2020-1470"},{"key":"ref19","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP40776.2020.9054295"},{"key":"ref20","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2021-740"},{"key":"ref21","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2022-10011"},{"key":"ref22","article-title":"On using monolingual corpora in neural machine translation","author":"G\u00fcl\u00e7ehre","year":"2015","journal-title":"CoRR"},{"key":"ref23","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2016.308"},{"key":"ref24","first-page":"1171","article-title":"Scheduled sampling for sequence prediction with recurrent neural networks","volume-title":"In Proc. of Annual Conference on Neural Information Processing Systems (NeurIPS)","author":"Bengio","year":"2015"},{"key":"ref25","article-title":"Aligning pre-trained models for spoken language translation","volume":"abs\/2411.18294","author":"Sedl\u00e1cek","year":"2024","journal-title":"CoRR"},{"key":"ref26","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/W18-6319"},{"key":"ref27","doi-asserted-by":"publisher","DOI":"10.1016\/j.csl.2020.101155"},{"key":"ref28","first-page":"6704","article-title":"JParaCrawl v3.0: A large-scale English-Japanese parallel corpus","volume-title":"In Proc. of Language Resources and Evaluation Conference (LREC)","author":"Morishita","year":"2022"},{"key":"ref29","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2019-2680"},{"key":"ref30","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/D18-2012"},{"key":"ref31","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2021.acl-long.68"},{"key":"ref32","article-title":"On the variance of the adaptive learning rate and beyond","volume-title":"Proc. of International Conference on Learning Representations (ICLR)","author":"Liu","year":"2020"}],"event":{"name":"2025 Asia Pacific Signal and Information Processing Association Annual Summit and Conference (APSIPA ASC)","start":{"date-parts":[[2025,10,22]]},"location":"Singapore, Singapore","end":{"date-parts":[[2025,10,24]]}},"container-title":["2025 Asia Pacific Signal and Information Processing Association Annual Summit and Conference (APSIPA ASC)"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx8\/11248853\/11248968\/11249353.pdf?arnumber=11249353","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,11,29]],"date-time":"2025-11-29T07:12:52Z","timestamp":1764400372000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/11249353\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2025,10,22]]},"references-count":32,"URL":"https:\/\/doi.org\/10.1109\/apsipaasc65261.2025.11249353","relation":{},"subject":[],"published":{"date-parts":[[2025,10,22]]}}}