{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,5,21]],"date-time":"2026-05-21T17:38:32Z","timestamp":1779385112155,"version":"3.53.1"},"reference-count":26,"publisher":"IEEE","license":[{"start":{"date-parts":[[2019,5,1]],"date-time":"2019-05-01T00:00:00Z","timestamp":1556668800000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2019,5,1]],"date-time":"2019-05-01T00:00:00Z","timestamp":1556668800000},"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":[[2019,5]]},"DOI":"10.1109\/icassp.2019.8683745","type":"proceedings-article","created":{"date-parts":[[2019,4,17]],"date-time":"2019-04-17T16:01:56Z","timestamp":1555516916000},"page":"5651-5655","source":"Crossref","is-referenced-by-count":89,"title":["A Spelling Correction Model for End-to-end Speech Recognition"],"prefix":"10.1109","author":[{"given":"Jinxi","family":"Guo","sequence":"first","affiliation":[{"name":"University of California, Los Angeles, USA"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Tara N.","family":"Sainath","sequence":"additional","affiliation":[{"name":"Google Inc., USA"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Ron J.","family":"Weiss","sequence":"additional","affiliation":[{"name":"Google Inc., USA"}],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"263","reference":[{"key":"ref10","doi-asserted-by":"publisher","DOI":"10.1016\/j.procs.2018.03.005"},{"key":"ref11","doi-asserted-by":"publisher","DOI":"10.3115\/1613984.1614006"},{"key":"ref12","article-title":"Asr context-sensitive error correction based on microsoft n-gram dataset","volume":"abs 1203 5262","author":"assil","year":"2012","journal-title":"CoRR"},{"key":"ref13","article-title":"Neural language correction with character-based attention","volume":"abs 1603 9727","author":"xie","year":"2016","journal-title":"CoRR"},{"key":"ref14","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2017.7953077"},{"key":"ref15","article-title":"Google’s neural machine translation system: Bridging the gap between human and machine translation","volume":"abs 1609 8144","author":"wu","year":"2016","journal-title":"CoRR"},{"key":"ref16","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2018-1616"},{"key":"ref17","article-title":"On using monolingual corpora in neural machine translation","volume":"abs 1503 3535","author":"gulcehre","year":"2015","journal-title":"CoRR"},{"key":"ref18","article-title":"Cold fusion: Training seq2seq models together with language models","volume":"abs 1708 6426","author":"sriram","year":"2017","journal-title":"CoRR"},{"key":"ref19","first-page":"3918","article-title":"Parallel WaveNet: Fast high-fidelity speech synthesis","author":"van den oord","year":"2018","journal-title":"Proc ICML"},{"key":"ref4","doi-asserted-by":"publisher","DOI":"10.1145\/1143844.1143891"},{"key":"ref3","article-title":"Sequence transduction with recurrent neural networks","volume":"abs 1211 3711","author":"graves","year":"2012","journal-title":"CoRR"},{"key":"ref6","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2017-343"},{"key":"ref5","article-title":"State-of-the-art speech recognition with sequence-to-sequence models","author":"chen","year":"2018","journal-title":"Proc ICASSP"},{"key":"ref8","article-title":"A comparison of techniques for language model integration in encoder-decoder speech recognition","author":"toshniwal","year":"2018","journal-title":"Proc SLT"},{"key":"ref7","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2018.8462682"},{"key":"ref2","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2016.7472618"},{"key":"ref9","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/P16-1009"},{"key":"ref1","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2016.7472621"},{"key":"ref20","article-title":"Back-translation-style data augmentation for end-to-end ASR","author":"hayashi","year":"2018","journal-title":"arXiv preprint arXiv 1807 10893"},{"key":"ref22","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2012.6289079"},{"key":"ref21","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/P18-1008"},{"key":"ref24","article-title":"TensorFlow: Large-Scale Machine Learning on Heterogeneous Distributed Systems","author":"abadi","year":"2015"},{"key":"ref23","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2015.7178964"},{"key":"ref26","article-title":"Generated of large-scale simulated utterances in virtual rooms to train deep-neural networks for far-field speech recognition in google home","author":"kim","year":"2017","journal-title":"Proc In-terspeech"},{"key":"ref25","article-title":"Adam: A method for stochastic optimization","author":"kingma","year":"2015","journal-title":"Proc ICLR"}],"event":{"name":"ICASSP 2019 - 2019 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)","location":"Brighton, UK","start":{"date-parts":[[2019,5,12]]},"end":{"date-parts":[[2019,5,17]]}},"container-title":["ICASSP 2019 - 2019 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx7\/8671773\/8682151\/08683745.pdf?arnumber=8683745","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,8,21]],"date-time":"2025-08-21T18:19:04Z","timestamp":1755800344000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/8683745\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2019,5]]},"references-count":26,"URL":"https:\/\/doi.org\/10.1109\/icassp.2019.8683745","relation":{},"subject":[],"published":{"date-parts":[[2019,5]]}}}