{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,3,4]],"date-time":"2026-03-04T17:35:01Z","timestamp":1772645701010,"version":"3.50.1"},"reference-count":70,"publisher":"IEEE","license":[{"start":{"date-parts":[[2021,12,13]],"date-time":"2021-12-13T00:00:00Z","timestamp":1639353600000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2021,12,13]],"date-time":"2021-12-13T00:00:00Z","timestamp":1639353600000},"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":[[2021,12,13]]},"DOI":"10.1109\/asru51503.2021.9687894","type":"proceedings-article","created":{"date-parts":[[2022,2,3]],"date-time":"2022-02-03T15:31:00Z","timestamp":1643902260000},"page":"922-929","source":"Crossref","is-referenced-by-count":8,"title":["Fast-MD: Fast Multi-Decoder End-to-End Speech Translation with Non-Autoregressive Hidden Intermediates"],"prefix":"10.1109","author":[{"given":"Hirofumi","family":"Inaguma","sequence":"first","affiliation":[{"name":"Kyoto University,Japan"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Siddharth","family":"Dalmia","sequence":"additional","affiliation":[{"name":"Carnegie Mellon University,USA"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Brian","family":"Yan","sequence":"additional","affiliation":[{"name":"Carnegie Mellon University,USA"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Shinji","family":"Watanabe","sequence":"additional","affiliation":[{"name":"Carnegie Mellon University,USA"}],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"263","reference":[{"key":"ref70","doi-asserted-by":"publisher","DOI":"10.1145\/2792745.2792775"},{"key":"ref39","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2020.acl-demos.34"},{"key":"ref38","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2021-337"},{"key":"ref33","article-title":"WNARS: WFST based non-autoregressive streaming end-to-end speech recognition","author":"wang","year":"2021","journal-title":"ArXiv Preprint"},{"key":"ref32","article-title":"One in a hundred: Select the best predicted sequence from numerous candidates for streaming speech recognition","author":"tian","year":"2020","journal-title":"ArXiv Preprint"},{"key":"ref31","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP39728.2021.9413429"},{"key":"ref30","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP39728.2021.9414694"},{"key":"ref37","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2021-911"},{"key":"ref36","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP40776.2020.9052964"},{"key":"ref35","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP39728.2021.9414198"},{"key":"ref34","article-title":"Unified streaming and non-streaming two-pass end-to-end model for speech recognition","author":"zhang","year":"2020","journal-title":"ArXiv Preprint"},{"key":"ref60","first-page":"33","article-title":"Fairseq S2T: Fast speech-to-text modeling with fairseq","author":"wang","year":"0","journal-title":"Proc AACL System Demonstrations"},{"key":"ref62","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2021.naacl-main.150"},{"key":"ref61","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2020-2526"},{"key":"ref63","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2020-2860"},{"key":"ref28","doi-asserted-by":"publisher","DOI":"10.1109\/ASRU46091.2019.9003750"},{"key":"ref64","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2020.iwslt-1.9"},{"key":"ref27","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP39728.2021.9414594"},{"key":"ref65","article-title":"Beyond voice activity detection: Hybrid audio segmentation for direct speech translation","author":"gaido","year":"2021","journal-title":"ArXiv Preprint"},{"key":"ref66","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2021.iwslt-1.10"},{"key":"ref29","doi-asserted-by":"crossref","first-page":"1240","DOI":"10.1109\/JSTSP.2017.2763455","article-title":"Hybrid CTC\/attention architecture for end-to-end speech recognition","volume":"11","author":"shinji","year":"2017","journal-title":"IEEE Journal of Selected Topics in Signal Processing"},{"key":"ref67","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP40776.2020.9052974"},{"key":"ref68","doi-asserted-by":"publisher","DOI":"10.1145\/1553374.1553380"},{"key":"ref69","doi-asserted-by":"publisher","DOI":"10.1109\/MCSE.2014.80"},{"key":"ref2","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2017-503"},{"key":"ref1","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.1999.758176"},{"key":"ref20","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2021.acl-long.204"},{"key":"ref22","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2021.findings-acl.92"},{"key":"ref21","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP39728.2021.9415093"},{"key":"ref24","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/D19-1633"},{"key":"ref23","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2020-2404"},{"key":"ref26","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2020-3015"},{"key":"ref25","doi-asserted-by":"publisher","DOI":"10.1162\/neco.1989.1.2.270"},{"key":"ref50","first-page":"5998","article-title":"Attention is all you need","author":"ashish","year":"0","journal-title":"Proc NIPS"},{"key":"ref51","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP39728.2021.9414858"},{"key":"ref59","article-title":"Listen, Understand and Translate”: Triple supervision decouples end-to-end speech-to-text translation","author":"dong","year":"0","journal-title":"Proc AAAI"},{"key":"ref58","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2020.acl-main.344"},{"key":"ref57","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2021.acl-demo.7"},{"key":"ref56","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v34i05.6452"},{"key":"ref55","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2019-2582"},{"key":"ref54","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/W18-6319"},{"key":"ref53","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2019-2860"},{"key":"ref52","article-title":"Adam: A method for stochastic optimization","author":"kingma","year":"0","journal-title":"Proc ICLR"},{"key":"ref10","doi-asserted-by":"publisher","DOI":"10.1162\/tacl_a_00270"},{"key":"ref11","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2019.8682801"},{"key":"ref40","article-title":"Improved speech-to-text translation with the Fisher and Callhome Spanish-English speech translation corpus","author":"post","year":"0","journal-title":"Proc IWSLT"},{"key":"ref12","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2021.naacl-main.151"},{"key":"ref13","article-title":"Enforcing encoder-decoder modularity in sequence-to-sequence models","author":"dalmia","year":"2019","journal-title":"ArXiv Preprint"},{"key":"ref14","first-page":"53","article-title":"Highland Puebla Nahuatl speech translation corpus for endangered language documentation","author":"jiatong","year":"0","journal-title":"Proc AmericasNLP"},{"key":"ref15","doi-asserted-by":"publisher","DOI":"10.1145\/1143844.1143891"},{"key":"ref16","article-title":"Bridging the modality gap for speech-to-text translation","author":"liu","year":"2020","journal-title":"ArXiv Preprint"},{"key":"ref17","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2021.eacl-main.57"},{"key":"ref18","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2021.findings-acl.218"},{"key":"ref19","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2020.findings-emnlp.230"},{"key":"ref4","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/N19-1006"},{"key":"ref3","first-page":"6224","article-title":"End-to-end automatic speech translation of audio-books","author":"b\u00e9rard","year":"2018","journal-title":"Proc ICASSP"},{"key":"ref6","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v34i05.6360"},{"key":"ref5","doi-asserted-by":"publisher","DOI":"10.1109\/ASRU46091.2019.9003774"},{"key":"ref8","article-title":"Consecutive decoding for speech-to-text translation","author":"dong","year":"0","journal-title":"Proc AAAI"},{"key":"ref7","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2020.coling-main.314"},{"key":"ref49","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/D18-2012"},{"key":"ref9","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/N18-1008"},{"key":"ref46","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2019-2680"},{"key":"ref45","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2015-711"},{"key":"ref48","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/P16-1162"},{"key":"ref47","doi-asserted-by":"publisher","DOI":"10.3115\/1557769.1557821"},{"key":"ref42","article-title":"Augmenting Librispeech with French translations: A multimodal corpus for direct speech translation evaluation","author":"kocabiyikoglu","year":"0","journal-title":"Proc LREC"},{"key":"ref41","first-page":"311","article-title":"Bleu: a method for automatic evaluation of machine translation","author":"papineni","year":"2002","journal-title":"Proc ACL"},{"key":"ref44","article-title":"The kaldi speech recognition toolkit","author":"povey","year":"2011","journal-title":"Proc ASRU"},{"key":"ref43","first-page":"2012","article-title":"MuST-C: a Multilingual Speech Translation Corpus","author":"di gangi","year":"0","journal-title":"Proc NAACL-HLT"}],"event":{"name":"2021 IEEE Automatic Speech Recognition and Understanding Workshop (ASRU)","location":"Cartagena, Colombia","start":{"date-parts":[[2021,12,13]]},"end":{"date-parts":[[2021,12,17]]}},"container-title":["2021 IEEE Automatic Speech Recognition and Understanding Workshop (ASRU)"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx7\/9687821\/9687855\/09687894.pdf?arnumber=9687894","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2022,5,16]],"date-time":"2022-05-16T16:41:50Z","timestamp":1652719310000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/9687894\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2021,12,13]]},"references-count":70,"URL":"https:\/\/doi.org\/10.1109\/asru51503.2021.9687894","relation":{},"subject":[],"published":{"date-parts":[[2021,12,13]]}}}