{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,5,15]],"date-time":"2026-05-15T02:14:32Z","timestamp":1778811272605,"version":"3.51.4"},"reference-count":21,"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\/icassp39728.2021.9414778","type":"proceedings-article","created":{"date-parts":[[2021,5,13]],"date-time":"2021-05-13T19:53:45Z","timestamp":1620935625000},"page":"5674-5678","source":"Crossref","is-referenced-by-count":45,"title":["Using Synthetic Audio to Improve the Recognition of Out-of-Vocabulary Words in End-to-End Asr Systems"],"prefix":"10.1109","author":[{"given":"Xianrui","family":"Zheng","sequence":"first","affiliation":[{"name":"University of Cambridge"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Yulan","family":"Liu","sequence":"additional","affiliation":[{"name":"Amazon Alexa"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Deniz","family":"Gunceler","sequence":"additional","affiliation":[{"name":"Amazon Alexa"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Daniel","family":"Willett","sequence":"additional","affiliation":[{"name":"Amazon Alexa"}],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"263","reference":[{"key":"ref10","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2019.8683745"},{"key":"ref11","doi-asserted-by":"publisher","DOI":"10.1109\/ASRU46091.2019.9003990"},{"key":"ref12","article-title":"Training neural speech recognition systems with synthetic speech augmentation","author":"li","year":"2018"},{"key":"ref13","first-page":"439","article-title":"You do not need more data: Improving end-to-end speech recognition by text-to-speech data augmentation","author":"laptev","year":"2020","journal-title":"Proc CISP-BMEI"},{"key":"ref14","doi-asserted-by":"publisher","DOI":"10.1109\/SLT.2018.8639589"},{"key":"ref15","article-title":"End-to-end continuous speech recognition using attention-based recurrent NN: First results","author":"chorowski","year":"2014","journal-title":"Proc NIPS"},{"key":"ref16","article-title":"Attention-based models for speech recognition","author":"chorowski","year":"2015","journal-title":"Proc NIPS"},{"key":"ref17","doi-asserted-by":"publisher","DOI":"10.1073\/pnas.1611835114"},{"key":"ref18","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2019.8682336"},{"key":"ref19","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP40776.2020.9053008"},{"key":"ref4","doi-asserted-by":"publisher","DOI":"10.1109\/SLT.2018.8639038"},{"key":"ref3","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2020-1465"},{"key":"ref6","article-title":"Few-shot learning with attention-based sequence-to-sequence models","author":"higy","year":"2018"},{"key":"ref5","doi-asserted-by":"publisher","DOI":"10.1109\/ASRU46091.2019.9003790"},{"key":"ref8","doi-asserted-by":"publisher","DOI":"10.1109\/ASRU46091.2019.9003775"},{"key":"ref7","article-title":"On using monolingual corpora in neural machine translation","author":"gulcehre","year":"2015"},{"key":"ref2","article-title":"Sequence transduction with recurrent neural networks","author":"graves","year":"2012","journal-title":"Proc ICML"},{"key":"ref1","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2016.7472621"},{"key":"ref9","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2020-3016"},{"key":"ref20","doi-asserted-by":"publisher","DOI":"10.1109\/IJCNN48605.2020.9206891"},{"key":"ref21","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/D18-2012"}],"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\/09414778.pdf?arnumber=9414778","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2022,8,3]],"date-time":"2022-08-03T00:19:36Z","timestamp":1659485976000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/9414778\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2021,6,6]]},"references-count":21,"URL":"https:\/\/doi.org\/10.1109\/icassp39728.2021.9414778","relation":{},"subject":[],"published":{"date-parts":[[2021,6,6]]}}}