{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2025,10,10]],"date-time":"2025-10-10T21:42:35Z","timestamp":1760132555086,"version":"3.37.3"},"reference-count":57,"publisher":"Institute of Electrical and Electronics Engineers (IEEE)","issue":"12","license":[{"start":{"date-parts":[[2019,12,1]],"date-time":"2019-12-01T00:00:00Z","timestamp":1575158400000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/ieeexplore.ieee.org\/Xplorehelp\/downloads\/license-information\/IEEE.html"},{"start":{"date-parts":[[2019,12,1]],"date-time":"2019-12-01T00:00:00Z","timestamp":1575158400000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2019,12,1]],"date-time":"2019-12-01T00:00:00Z","timestamp":1575158400000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-037"}],"funder":[{"DOI":"10.13039\/100004318","name":"Microsoft","doi-asserted-by":"publisher","id":[{"id":"10.13039\/100004318","id-type":"DOI","asserted-by":"publisher"}]}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":["IEEE\/ACM Trans. Audio Speech Lang. Process."],"published-print":{"date-parts":[[2019,12]]},"DOI":"10.1109\/taslp.2019.2933325","type":"journal-article","created":{"date-parts":[[2019,8,5]],"date-time":"2019-08-05T19:43:10Z","timestamp":1565034190000},"page":"1880-1892","source":"Crossref","is-referenced-by-count":17,"title":["Advancing Acoustic-to-Word CTC Model With Attention and Mixed-Units"],"prefix":"10.1109","volume":"27","author":[{"ORCID":"https:\/\/orcid.org\/0000-0002-8823-8026","authenticated-orcid":false,"given":"Amit","family":"Das","sequence":"first","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Jinyu","family":"Li","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Guoli","family":"Ye","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Rui","family":"Zhao","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Yifan","family":"Gong","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"263","reference":[{"key":"ref39","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2013.6638949"},{"key":"ref38","doi-asserted-by":"publisher","DOI":"10.1145\/1553374.1553380"},{"article-title":"Modelling out-of-vocabulary words for robust speech recognition","year":"2002","author":"bazzi","key":"ref33"},{"key":"ref32","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2018.8462209"},{"key":"ref31","doi-asserted-by":"publisher","DOI":"10.1109\/ASRU.2017.8268924"},{"key":"ref30","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2017-546"},{"key":"ref37","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2018.8461935"},{"key":"ref36","first-page":"725","article-title":"Open vocabulary speech recognition with flat hybrid models","author":"bisani","year":"0","journal-title":"Proc INTERSPEECH"},{"key":"ref35","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2004.1326093"},{"key":"ref34","first-page":"861","article-title":"Transcription of out-of-vocabulary words in large vocabulary speech recognition based on phoneme-to-grapheme conversion","volume":"1","author":"decadt","year":"0","journal-title":"Proc IEEE Int Conf Acoust Speech Signal Process"},{"key":"ref28","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2017.7953069"},{"key":"ref27","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2016-71"},{"key":"ref29","first-page":"2188","article-title":"Gram-CTC: Automatic unit selection and target decomposition for sequence labelling","author":"liu","year":"0","journal-title":"Proc Int Conf Machine Learn (ICML)"},{"key":"ref2","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2015.7178778"},{"key":"ref1","doi-asserted-by":"publisher","DOI":"10.1109\/JAS.2017.7510508"},{"key":"ref20","doi-asserted-by":"publisher","DOI":"10.1109\/ASRU.2017.8268935"},{"key":"ref22","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2019.8683510"},{"key":"ref21","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2019.8683843"},{"key":"ref24","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2019.8682256"},{"key":"ref23","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2019.8682155"},{"key":"ref26","first-page":"1468","article-title":"Fast and accurate recurrent neural network acoustic models for speech recognition","author":"sak","year":"0","journal-title":"Proc INTERSPEECH"},{"article-title":"Deep speech: Scaling up end-to-end speech recognition","year":"2014","author":"hannun","key":"ref25"},{"key":"ref50","first-page":"1045","article-title":"Recurrent neural networks based language model","author":"mikolov","year":"0","journal-title":"Proc INTERSPEECH"},{"key":"ref51","doi-asserted-by":"publisher","DOI":"10.1162\/neco.1997.9.8.1735"},{"key":"ref57","article-title":"Latent sequence decompositions","author":"chan","year":"2017","journal-title":"Int Conf Learn Represent (ICLR)"},{"article-title":"Google's neural machine translation system: bridging the gap between human and machine translation","year":"2016","author":"wu","key":"ref56"},{"key":"ref55","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/P16-1162"},{"key":"ref54","doi-asserted-by":"publisher","DOI":"10.1109\/TASLP.2016.2625459"},{"key":"ref53","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2017-505"},{"key":"ref52","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2016.90"},{"key":"ref10","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2018.8462366"},{"key":"ref11","doi-asserted-by":"publisher","DOI":"10.1145\/1143844.1143891"},{"key":"ref40","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2018.8461361"},{"key":"ref12","first-page":"1764","article-title":"Towards end-to-end speech recognition with recurrent neural networks","author":"graves","year":"0","journal-title":"Mach Learn Res"},{"key":"ref13","doi-asserted-by":"publisher","DOI":"10.3115\/v1\/D14-1179"},{"key":"ref14","article-title":"Neural machine translation by jointly learning to align and translate","author":"bahdanau","year":"0","journal-title":"Proc Int Conf Learn Represent"},{"key":"ref15","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2016.7472618"},{"key":"ref16","article-title":"Attention-based models for speech recognition","author":"chorowski","year":"0","journal-title":"Proc Conf Neural Inf Process Syst"},{"key":"ref17","article-title":"Sequence transduction with recurrent neural networks","author":"graves","year":"2012","journal-title":"Proc Int Conf Machine Learn (ICML)"},{"key":"ref18","first-page":"3249","article-title":"A study of the recurrent neural network encoder-decoder for large vocabulary speech recognition","author":"lu","year":"0","journal-title":"Proc INTERSPEECH"},{"key":"ref19","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2017-1566"},{"key":"ref4","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2016.7472621"},{"key":"ref3","doi-asserted-by":"publisher","DOI":"10.1109\/ASRU.2015.7404790"},{"key":"ref6","first-page":"206","article-title":"Improving the performance of online neural transducer models","author":"battenberg","year":"0","journal-title":"Proc IEEE Workshop Automatic Speech Recognition and Understanding (ASRU)"},{"key":"ref5","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2017-233"},{"key":"ref8","doi-asserted-by":"publisher","DOI":"10.1109\/TASLP.2018.2848701"},{"key":"ref7","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2017-1705"},{"key":"ref49","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2017-1118"},{"key":"ref9","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2018.8462105"},{"key":"ref46","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2016.7472641"},{"key":"ref45","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2018.8462017"},{"key":"ref48","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2017-1296"},{"key":"ref47","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2017.7953075"},{"key":"ref42","first-page":"1","article-title":"Attention is all you need","author":"vaswani","year":"0","journal-title":"Proc 31st Conf Neural Inf Process Syst"},{"key":"ref41","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2018.8461558"},{"key":"ref44","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2013.6639012"},{"key":"ref43","doi-asserted-by":"publisher","DOI":"10.1023\/A:1007379606734"}],"container-title":["IEEE\/ACM Transactions on Audio, Speech, and Language Processing"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx7\/6570655\/8817316\/08788608.pdf?arnumber=8788608","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2022,7,13]],"date-time":"2022-07-13T20:54:26Z","timestamp":1657745666000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/8788608\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2019,12]]},"references-count":57,"journal-issue":{"issue":"12"},"URL":"https:\/\/doi.org\/10.1109\/taslp.2019.2933325","relation":{},"ISSN":["2329-9290","2329-9304"],"issn-type":[{"type":"print","value":"2329-9290"},{"type":"electronic","value":"2329-9304"}],"subject":[],"published":{"date-parts":[[2019,12]]}}}