{"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":1779251968692,"version":"3.51.4"},"reference-count":56,"publisher":"IEEE","license":[{"start":{"date-parts":[[2021,6,6]],"date-time":"2021-06-06T00:00:00Z","timestamp":1622937600000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2021,6,6]],"date-time":"2021-06-06T00:00:00Z","timestamp":1622937600000},"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":[[2021,6,6]]},"DOI":"10.1109\/icassp39728.2021.9415093","type":"proceedings-article","created":{"date-parts":[[2021,5,13]],"date-time":"2021-05-13T15:53:45Z","timestamp":1620921225000},"page":"7503-7507","source":"Crossref","is-referenced-by-count":10,"title":["ORTHROS: non-autoregressive end-to-end speech translation With dual-decoder"],"prefix":"10.1109","author":[{"given":"Hirofumi","family":"Inaguma","sequence":"first","affiliation":[{"name":"Kyoto University,Japan"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Yosuke","family":"Higuchi","sequence":"additional","affiliation":[{"name":"Waseda University,Japan"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Kevin","family":"Duh","sequence":"additional","affiliation":[{"name":"Johns Hopkins University,USA"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Tatsuya","family":"Kawahara","sequence":"additional","affiliation":[{"name":"Kyoto University,Japan"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Shinji","family":"Watanabe","sequence":"additional","affiliation":[{"name":"Johns Hopkins University,USA"}],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"263","reference":[{"key":"ref39","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2020.acl-main.36"},{"key":"ref38","first-page":"5026","article-title":"Spike-triggered non-autoregressive Trans-former for end-to-end speech recognition","author":"tian","year":"2020","journal-title":"Proc of Inter-speech"},{"key":"ref33","article-title":"Listen and fill in the missing letters: Non-autoregressive Transformer for speech recognition","author":"chen","year":"2019","journal-title":"arXiv preprint arXiv 1911 12945"},{"key":"ref32","first-page":"3171","article-title":"FastSpeech: Fast, robust and controllable text to speech","author":"ren","year":"2019","journal-title":"Proc of NeurIPS"},{"key":"ref31","first-page":"3918","article-title":"Parallel wavenet: Fast high-fidelity speech synthesis","author":"oord","year":"2018","journal-title":"Proc of ICML"},{"key":"ref30","first-page":"5998","article-title":"Attention is all you need","author":"vaswani","year":"2017","journal-title":"Proc of NeurIPS"},{"key":"ref37","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2020-1600"},{"key":"ref36","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2020-1619"},{"key":"ref35","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2020-2404"},{"key":"ref34","article-title":"Imputer: Sequence modelling via imputation and dynamic programming","author":"chan","year":"2020","journal-title":"arXiv preprint arXiv 2002 05155"},{"key":"ref28","article-title":"Non-autoregressive machine translation with latent alignments","author":"saharia","year":"2020","journal-title":"arXiv preprint arXiv 2004 06774"},{"key":"ref27","article-title":"Aligned cross entropy for non-autoregressive machine translation","author":"ghazvininejad","year":"2020","journal-title":"Proc of ICML"},{"key":"ref29","article-title":"Semi-autoregressive training improves mask-predict decoding","author":"ghazvininejad","year":"2020","journal-title":"arXiv preprint arXiv 2001 04786"},{"key":"ref2","article-title":"Listen and translate: A proof of concept for end-to-end speech-to-text translation","author":"b\u00e9rard","year":"2016","journal-title":"Proc of NeurIPS 2016 End-to-end Learning for Speech and Audio Processing Workshop"},{"key":"ref1","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.1999.758176"},{"key":"ref20","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/D18-1149"},{"key":"ref22","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/D18-1336"},{"key":"ref21","first-page":"2390","article-title":"Fast decoding in sequence models using discrete latent variables","author":"kaiser","year":"2018","journal-title":"Proc of ICML"},{"key":"ref24","first-page":"11181","article-title":"Levenshtein Transformer","author":"gu","year":"2019","journal-title":"Proc of NeurIPS"},{"key":"ref23","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/D19-1633"},{"key":"ref26","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/D19-1437"},{"key":"ref25","first-page":"5976","article-title":"Insertion Transformer: Flexible sequence generation via insertion operations","author":"stern","year":"2019","journal-title":"Proc of ICML"},{"key":"ref50","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2019-2680"},{"key":"ref51","doi-asserted-by":"publisher","DOI":"10.3115\/1557769.1557821"},{"key":"ref56","first-page":"4171","article-title":"BERT: Pre-training of deep bidirectional Transformers for language understanding","author":"devlin","year":"2019","journal-title":"Proc of NAACL-HLT"},{"key":"ref55","doi-asserted-by":"publisher","DOI":"10.1109\/JSTSP.2017.2763455"},{"key":"ref54","article-title":"Adam: A method for stochastic optimization","author":"kingma","year":"2015","journal-title":"Proc of ICLR"},{"key":"ref53","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/P18-1007"},{"key":"ref52","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/P16-1162"},{"key":"ref10","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2020-2938"},{"key":"ref11","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/P19-1179"},{"key":"ref40","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/D16-1139"},{"key":"ref12","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2020.acl-main.217"},{"key":"ref13","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2018.8461690"},{"key":"ref14","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/N19-1006"},{"key":"ref15","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP40776.2020.9054759"},{"key":"ref16","doi-asserted-by":"crossref","first-page":"2625","DOI":"10.21437\/Interspeech.2017-503","article-title":"Sequence-to-sequence models can directly translate foreign speech","author":"weiss","year":"2017","journal-title":"Proc of Interspeech"},{"key":"ref17","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2019-2582"},{"key":"ref18","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2016-154"},{"key":"ref19","article-title":"Non-autoregressive neural machine translation","author":"gu","year":"2018","journal-title":"Proc of ICLR"},{"key":"ref4","first-page":"7180","article-title":"Leveraging weakly supervised data to improve end-to-end speech-to-text translation","year":"2019","journal-title":"Proc of ICASSP"},{"key":"ref3","doi-asserted-by":"publisher","DOI":"10.1109\/ASRU.2017.8268972"},{"key":"ref6","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v34i05.6452"},{"key":"ref5","first-page":"arxiv","article-title":"Harnessing indirect training data for end-to-end automatic speech translation: Tricks of the trade","author":"pino","year":"2019","journal-title":"ArXiv"},{"key":"ref8","doi-asserted-by":"publisher","DOI":"10.1109\/ASRU46091.2019.9003832"},{"key":"ref7","first-page":"3728","article-title":"Curriculum pre-training for end-to-end speech translation","author":"wang","year":"2020","journal-title":"Proc of ACL"},{"key":"ref49","first-page":"3586","article-title":"Audio augmentation for speech recognition","author":"ko","year":"2015","journal-title":"Proc of Interspeech"},{"key":"ref9","doi-asserted-by":"publisher","DOI":"10.1109\/ASRU46091.2019.9004003"},{"key":"ref46","first-page":"302","article-title":"ESPnet-ST: All-in-one speech translation toolkit","author":"inaguma","year":"2020","journal-title":"Proc of ACL System Demonstrations"},{"key":"ref45","article-title":"Augmenting Librispeech with French translations: A multimodal corpus for direct speech trans-lation evaluation","author":"kocabiyikoglu","year":"2018","journal-title":"Proc of LREC"},{"key":"ref48","article-title":"The kaldi speech recognition toolkit","author":"povey","year":"2011","journal-title":"Proc of ASRU"},{"key":"ref47","first-page":"311","article-title":"Bleu: a method for automatic evaluation of machine translation","author":"papineni","year":"2002","journal-title":"Proc of ACL"},{"key":"ref42","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2020.acl-main.15"},{"key":"ref41","article-title":"Understanding knowledge distillation in non-autoregressive machine translation","author":"zhou","year":"2019","journal-title":"Proc of ICLR"},{"key":"ref44","article-title":"Improved speech-to-text translation with the Fisher and Callhome Spanish–English speech translation corpus","author":"post","year":"2013","journal-title":"Proc of IWSLT"},{"key":"ref43","first-page":"2012","article-title":"MuST-C: a Multilingual Speech Translation Corpus","author":"gangi","year":"2019","journal-title":"Proc of NAACL-HLT"}],"event":{"name":"ICASSP 2021 - 2021 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)","location":"Toronto, ON, Canada","start":{"date-parts":[[2021,6,6]]},"end":{"date-parts":[[2021,6,11]]}},"container-title":["ICASSP 2021 - 2021 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx7\/9413349\/9413350\/09415093.pdf?arnumber=9415093","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2022,8,2]],"date-time":"2022-08-02T20:20:22Z","timestamp":1659471622000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/9415093\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2021,6,6]]},"references-count":56,"URL":"https:\/\/doi.org\/10.1109\/icassp39728.2021.9415093","relation":{},"subject":[],"published":{"date-parts":[[2021,6,6]]}}}