{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2024,9,8]],"date-time":"2024-09-08T15:06:22Z","timestamp":1725807982569},"reference-count":36,"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\/icassp49357.2023.10095578","type":"proceedings-article","created":{"date-parts":[[2023,5,5]],"date-time":"2023-05-05T13:28:30Z","timestamp":1683293310000},"page":"1-5","source":"Crossref","is-referenced-by-count":3,"title":["Improving Speech-to-Speech Translation Through Unlabeled Text"],"prefix":"10.1109","author":[{"given":"Xuan-Phi","family":"Nguyen","sequence":"first","affiliation":[{"name":"Nanyang Technological University,Singapore"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Sravya","family":"Popuri","sequence":"additional","affiliation":[{"name":"Meta AI,USA"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Changhan","family":"Wang","sequence":"additional","affiliation":[{"name":"Meta AI,USA"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Yun","family":"Tang","sequence":"additional","affiliation":[{"name":"Meta AI,USA"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Ilia","family":"Kulikov","sequence":"additional","affiliation":[{"name":"Meta AI,USA"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Hongyu","family":"Gong","sequence":"additional","affiliation":[{"name":"Meta AI,USA"}],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"263","reference":[{"key":"ref13","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2022.naacl-main.63"},{"key":"ref35","article-title":"Ted-lium 3: twice as much data and corpus repartition for experiments on speaker adaptation","author":"hernandez","year":"2018","journal-title":"SPECOM"},{"key":"ref12","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2022-11032"},{"key":"ref34","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP40776.2020.9052942"},{"key":"ref15","article-title":"On generative spoken language modeling from raw audio","author":"lakhotia","year":"2021","journal-title":"ACL"},{"key":"ref14","article-title":"wav2vec 2.0: A framework for self-supervised learning of speech representations","author":"baevski","year":"2020","journal-title":"NeurIPS"},{"key":"ref36","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2021.acl-long.80"},{"key":"ref31","article-title":"The multilingual tedx corpus for speech recognition and translation","author":"elizabeth","year":"2021","journal-title":"InterSpeech"},{"key":"ref30","article-title":"Europarlst: A multilingual corpus for speech translation of parliamentary debates","author":"iranzo-s\u00e1nchez","year":"2020","journal-title":"ICASSP"},{"article-title":"Direct speech-to-speech translation with discrete units","year":"2021","author":"lee","key":"ref11"},{"article-title":"Common voice: A massively-multilingual speech corpus","year":"2019","author":"ardila","key":"ref33"},{"key":"ref10","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2019-1951"},{"key":"ref32","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2020-2826"},{"key":"ref2","article-title":"Attention is all you need","author":"vaswani","year":"2017","journal-title":"NeurIPS"},{"key":"ref1","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP40776.2020.9054295"},{"key":"ref17","doi-asserted-by":"publisher","DOI":"10.1162\/tacl_a_00343"},{"key":"ref16","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2021-475"},{"article-title":"Ccnet: Extracting high quality monolingual datasets from web crawl data","year":"2019","author":"wenzek","key":"ref19"},{"key":"ref18","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2019.8683343"},{"key":"ref24","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2020-3015"},{"key":"ref23","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2021-475"},{"article-title":"MUSAN: A Music, Speech, and Noise Corpus","year":"2015","author":"snyder","key":"ref26"},{"article-title":"Layer normalization","year":"2016","author":"ba","key":"ref25"},{"key":"ref20","article-title":"Cross-lingual language model pretraining","author":"conneau","year":"2019","journal-title":"NeurIPS"},{"key":"ref22","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2021-1912"},{"key":"ref21","doi-asserted-by":"publisher","DOI":"10.1109\/TASLP.2021.3122291"},{"key":"ref28","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/D18-1045"},{"key":"ref27","doi-asserted-by":"publisher","DOI":"10.1109\/TASL.2006.872621"},{"article-title":"Covost 2 and massively multilingual speech-to-text translation","year":"2020","author":"wang","key":"ref29"},{"key":"ref8","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.1997.599557"},{"key":"ref7","article-title":"Fastspeech: Fast, robust and controllable text to speech","author":"ren","year":"2019","journal-title":"NeurIPS"},{"key":"ref9","doi-asserted-by":"publisher","DOI":"10.1109\/TSA.2005.860774"},{"key":"ref4","article-title":"Contrastive clustering to mine pseudo parallel data for unsupervised translation","author":"nguyen","year":"2022","journal-title":"ICLRE"},{"key":"ref3","article-title":"Cross-lingual retrieval for iterative self-supervised training","author":"tran","year":"2020","journal-title":"NeurIPS"},{"key":"ref6","article-title":"Conditional variational autoencoder with adversarial learning for end-to-end text-to-speech","author":"kim","year":"2021","journal-title":"ICML"},{"article-title":"Towards speechto-text translation without speech recognition","year":"2017","author":"bansal","key":"ref5"}],"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\/10095578.pdf?arnumber=10095578","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2023,11,20]],"date-time":"2023-11-20T14:01:29Z","timestamp":1700488889000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/10095578\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2023,6,4]]},"references-count":36,"URL":"https:\/\/doi.org\/10.1109\/icassp49357.2023.10095578","relation":{},"subject":[],"published":{"date-parts":[[2023,6,4]]}}}