{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,6,9]],"date-time":"2026-06-09T14:47:55Z","timestamp":1781016475852,"version":"3.54.1"},"reference-count":31,"publisher":"IEEE","license":[{"start":{"date-parts":[[2020,5,1]],"date-time":"2020-05-01T00:00:00Z","timestamp":1588291200000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/ieeexplore.ieee.org\/Xplorehelp\/downloads\/license-information\/IEEE.html"},{"start":{"date-parts":[[2020,5,1]],"date-time":"2020-05-01T00:00:00Z","timestamp":1588291200000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2020,5,1]],"date-time":"2020-05-01T00:00:00Z","timestamp":1588291200000},"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":[[2020,5]]},"DOI":"10.1109\/icassp40776.2020.9053831","type":"proceedings-article","created":{"date-parts":[[2020,4,9]],"date-time":"2020-04-09T20:21:13Z","timestamp":1586463673000},"page":"7029-7033","source":"Crossref","is-referenced-by-count":28,"title":["Improving Speech Recognition Using Consistent Predictions on Synthesized Speech"],"prefix":"10.1109","author":[{"given":"Gary","family":"Wang","sequence":"first","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Andrew","family":"Rosenberg","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Zhehuai","family":"Chen","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Yu","family":"Zhang","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Bhuvana","family":"Ramabhadran","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Yonghui","family":"Wu","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Pedro","family":"Moreno","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"263","reference":[{"key":"ref31","first-page":"4480","article-title":"Transfer learning from speaker verification to multispeaker text-to-speech synthesis","author":"jia","year":"2018","journal-title":"Advances in neural information processing systems"},{"key":"ref30","article-title":"Adam: A method for stochastic optimization","author":"kingma","year":"2014","journal-title":"arXiv preprint arXiv 1412 6980"},{"key":"ref10","first-page":"6281","article-title":"Endto-end feedback loss in speech chain framework via straightthrough estimator","author":"tjandra","year":"2019","journal-title":"ICASSP"},{"key":"ref11","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2019.8683307"},{"key":"ref12","doi-asserted-by":"publisher","DOI":"10.1109\/SLT.2018.8639674"},{"key":"ref13","article-title":"Improving neural machine translation models with monolingual data","author":"sennrich","year":"2015","journal-title":"arXiv preprint arXiv 1511 05271"},{"key":"ref14","first-page":"426","article-title":"Backtranslation-style data augmentation for end-to-end asr","author":"hayashi","year":"2018","journal-title":"SLT"},{"key":"ref15","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2019-3167"},{"key":"ref16","doi-asserted-by":"crossref","first-page":"229","DOI":"10.1007\/BF00992696","article-title":"Simple statistical gradient-following algorithms for connectionist reinforcement learning","volume":"8","author":"williams","year":"1992","journal-title":"Machine Learning"},{"key":"ref17","article-title":"Almost unsupervised text to speech and automatic speech recognition","author":"ren","year":"2019","journal-title":"arXiv preprint arXiv 1905 00571"},{"key":"ref18","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2019.8682890"},{"key":"ref19","article-title":"Mixmatch: A holistic approach to semi-supervised learning","author":"berthelot","year":"2019","journal-title":"arXiv preprint arXiv 1905 00571"},{"key":"ref28","first-page":"1929","article-title":"Dropout: a simple way to prevent neural networks from overfitting","volume":"15","author":"srivastava","year":"2014","journal-title":"JMLR"},{"key":"ref4","article-title":"Tacotron: Towards endto-end speech synthesis","author":"wang","year":"2017","journal-title":"arXiv preprint arXiv 1703 10593"},{"key":"ref27","article-title":"Audio augmentation for speech recognition","author":"ko","year":"2015","journal-title":"Sixteenth Annual Conference of the International Speech Communication Association"},{"key":"ref3","first-page":"1764","article-title":"Towards end-to-end speech recognition with recurrent neural networks","author":"graves","year":"2014","journal-title":"ICML"},{"key":"ref6","article-title":"Training neural speech recognition systems with synthetic speech augmentation","author":"li","year":"2018","journal-title":"arXiv preprint arXiv 1811 00707"},{"key":"ref29","article-title":"Regularizing and optimizing lstm language models","author":"merity","year":"2017","journal-title":"arXiv preprint arXiv 1708 02562"},{"key":"ref5","first-page":"195","article-title":"Deep voice: Real-time neural text-to-speech","volume":"70","author":"arik","year":"2017","journal-title":"ICML"},{"key":"ref8","article-title":"Virtual adversarial training: A regularization method for supervised and semi-supervised learning","author":"miyato","year":"2017"},{"key":"ref7","article-title":"Unsupervised data augmentation","author":"xie","year":"2019","journal-title":"arXiv preprint arXiv 1904 12848"},{"key":"ref2","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2016.7472621"},{"key":"ref9","doi-asserted-by":"publisher","DOI":"10.1109\/ASRU.2017.8268950"},{"key":"ref1","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2016.7472618"},{"key":"ref20","first-page":"5206","article-title":"Librispeech: an asr corpus based on public domain audio books","author":"panayotov","year":"2015","journal-title":"ICASSP"},{"key":"ref22","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2019-1780"},{"key":"ref21","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2019-2441"},{"key":"ref24","doi-asserted-by":"publisher","DOI":"10.1109\/ASRU46091.2019.9003990"},{"key":"ref23","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2018-1616"},{"key":"ref26","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2019-2680"},{"key":"ref25","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2019-2277"}],"event":{"name":"ICASSP 2020 - 2020 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)","location":"Barcelona, Spain","start":{"date-parts":[[2020,5,4]]},"end":{"date-parts":[[2020,5,8]]}},"container-title":["ICASSP 2020 - 2020 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx7\/9040208\/9052899\/09053831.pdf?arnumber=9053831","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2022,6,28]],"date-time":"2022-06-28T00:10:28Z","timestamp":1656375028000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/9053831\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2020,5]]},"references-count":31,"URL":"https:\/\/doi.org\/10.1109\/icassp40776.2020.9053831","relation":{},"subject":[],"published":{"date-parts":[[2020,5]]}}}