{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,4,3]],"date-time":"2026-04-03T15:24:21Z","timestamp":1775229861275,"version":"3.50.1"},"reference-count":40,"publisher":"Institute of Electrical and Electronics Engineers (IEEE)","license":[{"start":{"date-parts":[[2019,1,1]],"date-time":"2019-01-01T00:00:00Z","timestamp":1546300800000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/ieeexplore.ieee.org\/Xplorehelp\/downloads\/license-information\/OAPA.html"}],"funder":[{"name":"JSPS KAKENHI","award":["JP17H06101"],"award-info":[{"award-number":["JP17H06101"]}]},{"name":"JSPS KAKENHI","award":["JP17K00237"],"award-info":[{"award-number":["JP17K00237"]}]}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":["IEEE Access"],"published-print":{"date-parts":[[2019]]},"DOI":"10.1109\/access.2019.2922617","type":"journal-article","created":{"date-parts":[[2019,6,12]],"date-time":"2019-06-12T20:00:14Z","timestamp":1560369614000},"page":"79758-79769","source":"Crossref","is-referenced-by-count":10,"title":["End-to-End Speech Recognition Sequence Training With Reinforcement Learning"],"prefix":"10.1109","volume":"7","author":[{"ORCID":"https:\/\/orcid.org\/0000-0003-1246-5908","authenticated-orcid":false,"given":"Andros","family":"Tjandra","sequence":"first","affiliation":[]},{"given":"Sakriani","family":"Sakti","sequence":"additional","affiliation":[]},{"given":"Satoshi","family":"Nakamura","sequence":"additional","affiliation":[]}],"member":"263","reference":[{"key":"ref39","first-page":"2048","article-title":"Show, attend and tell: Neural image caption generation with visual attention","author":"xu","year":"2015","journal-title":"Proc Int Conf Mach Learn"},{"key":"ref38","article-title":"Empirical evaluation of rectified activations in convolutional network","author":"xu","year":"2015","journal-title":"arXiv 1505 00853"},{"key":"ref33","article-title":"Tacotron: Towards end-to-end speech synthesis","author":"wang","year":"2017","journal-title":"arXiv 1703 10135"},{"key":"ref32","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2015.7298935"},{"key":"ref31","article-title":"Sequence-to-sequence asr optimization via reinforcement learning","author":"tjandra","year":"2017","journal-title":"arXiv 1710 10774"},{"key":"ref30","first-page":"309","article-title":"Attention-based wav2text with feature transfer learning","author":"tjandra","year":"2017","journal-title":"Proc IEEE Workshop Autom Speech Recognition Understanding (ASRU)"},{"key":"ref37","article-title":"Google’s neural machine translation system: Bridging the gap between human and machine translation","author":"wu","year":"2016","journal-title":"arXiv 1609 08144"},{"key":"ref36","doi-asserted-by":"publisher","DOI":"10.1162\/neco.1989.1.2.270"},{"key":"ref35","doi-asserted-by":"publisher","DOI":"10.1007\/BF00992696"},{"key":"ref34","doi-asserted-by":"publisher","DOI":"10.1007\/BF00992698"},{"key":"ref10","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2017.7953075"},{"key":"ref40","doi-asserted-by":"publisher","DOI":"10.1016\/j.specom.2009.04.004"},{"key":"ref11","article-title":"Adam: A method for stochastic optimization","author":"kingma","year":"2014","journal-title":"arXiv 1412 6980"},{"key":"ref12","doi-asserted-by":"publisher","DOI":"10.1177\/0278364913495721"},{"key":"ref13","doi-asserted-by":"publisher","DOI":"10.1017\/CBO9780511815829"},{"key":"ref14","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/D16-1127"},{"key":"ref15","first-page":"1791","article-title":"Neural variational inference and learning in belief networks","author":"mnih","year":"2014","journal-title":"Proc 31st Int Conf Int Conf Mach Learn"},{"key":"ref16","doi-asserted-by":"crossref","first-page":"529","DOI":"10.1038\/nature14236","article-title":"Human-level control through deep reinforcement learning","volume":"518","author":"mnih","year":"2015","journal-title":"Nature"},{"key":"ref17","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/K16-1028"},{"key":"ref18","first-page":"311","article-title":"BLEU: A method for automatic evaluation of machine translation","author":"papineni","year":"2002","journal-title":"Proc Annual Meeting of the Assoc Computational Linguistics"},{"key":"ref19","doi-asserted-by":"publisher","DOI":"10.3115\/1075527.1075614"},{"key":"ref28","author":"sutton","year":"1998","journal-title":"Introduction to Reinforcement Learning"},{"key":"ref4","doi-asserted-by":"publisher","DOI":"10.1561\/2000000004"},{"key":"ref27","first-page":"3104","article-title":"Sequence to sequence learning with neural networks","author":"sutskever","year":"2014","journal-title":"Proc Adv Neural Inf Process Syst"},{"key":"ref3","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2016.7472621"},{"key":"ref6","first-page":"1471","article-title":"Variance reduction techniques for gradient estimates in reinforcement learning","volume":"5","author":"greensmith","year":"2004","journal-title":"J Mach Learn Res"},{"key":"ref29","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2018.8461705"},{"key":"ref5","doi-asserted-by":"crossref","DOI":"10.1007\/978-3-642-24797-2","volume":"385","author":"graves","year":"2012","journal-title":"Supervised Sequence Labelling with Recurrent Neural Networks"},{"key":"ref8","doi-asserted-by":"publisher","DOI":"10.1162\/neco.1997.9.8.1735"},{"key":"ref7","doi-asserted-by":"publisher","DOI":"10.1109\/MSP.2012.2205597"},{"key":"ref2","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2016.7472618"},{"key":"ref9","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2018.8462245"},{"key":"ref1","article-title":"Neural machine translation by jointly learning to align and translate","author":"bahdanau","year":"2014","journal-title":"arXiv 1409 0473"},{"key":"ref20","first-page":"1","article-title":"The Kaldi speech recognition toolkit","author":"povey","year":"2011","journal-title":"Proc IEEE Workshop Autom Speech Recog and Understanding"},{"key":"ref22","doi-asserted-by":"publisher","DOI":"10.1016\/j.neunet.2014.09.003"},{"key":"ref21","article-title":"Sequence level training with recurrent neural networks","author":"ranzato","year":"2015","journal-title":"arXiv 1511 06732"},{"key":"ref24","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/P16-1159"},{"key":"ref23","article-title":"Optimizing expected word error rate via sampling for speech recognition","author":"shannon","year":"2017","journal-title":"arXiv 1706 02776"},{"key":"ref26","first-page":"956","article-title":"Reinforcement learning for spoken dialogue systems","author":"singh","year":"2000","journal-title":"Proc Adv Neural Inf Process Syst"},{"key":"ref25","doi-asserted-by":"crossref","first-page":"484","DOI":"10.1038\/nature16961","article-title":"Mastering the game of go with deep neural networks and tree search","volume":"529","author":"silver","year":"2016","journal-title":"Nature"}],"container-title":["IEEE Access"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx7\/6287639\/8600701\/08735756.pdf?arnumber=8735756","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2022,1,27]],"date-time":"2022-01-27T17:50:50Z","timestamp":1643305850000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/8735756\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2019]]},"references-count":40,"URL":"https:\/\/doi.org\/10.1109\/access.2019.2922617","relation":{},"ISSN":["2169-3536"],"issn-type":[{"value":"2169-3536","type":"electronic"}],"subject":[],"published":{"date-parts":[[2019]]}}}