{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,7,11]],"date-time":"2026-07-11T10:33:24Z","timestamp":1783766004840,"version":"3.55.0"},"reference-count":32,"publisher":"IEEE","license":[{"start":{"date-parts":[[2020,10,17]],"date-time":"2020-10-17T00:00:00Z","timestamp":1602892800000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/ieeexplore.ieee.org\/Xplorehelp\/downloads\/license-information\/IEEE.html"},{"start":{"date-parts":[[2020,10,17]],"date-time":"2020-10-17T00:00:00Z","timestamp":1602892800000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2020,10,17]],"date-time":"2020-10-17T00:00:00Z","timestamp":1602892800000},"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":[[2020,10,17]]},"DOI":"10.1109\/cisp-bmei51763.2020.9263564","type":"proceedings-article","created":{"date-parts":[[2020,11,25]],"date-time":"2020-11-25T22:28:41Z","timestamp":1606343321000},"page":"439-444","source":"Crossref","is-referenced-by-count":34,"title":["You Do Not Need More Data: Improving End-To-End Speech Recognition by Text-To-Speech Data Augmentation"],"prefix":"10.1109","author":[{"given":"Aleksandr","family":"Laptev","sequence":"first","affiliation":[{"name":"ITMO University,St. Petersburg,Russia,197101"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Roman","family":"Korostik","sequence":"additional","affiliation":[{"name":"ITMO University,St. Petersburg,Russia,197101"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Aleksey","family":"Svischev","sequence":"additional","affiliation":[{"name":"ITMO University,St. Petersburg,Russia,197101"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Andrei","family":"Andrusenko","sequence":"additional","affiliation":[{"name":"ITMO University,St. Petersburg,Russia,197101"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Ivan","family":"Medennikov","sequence":"additional","affiliation":[{"name":"ITMO University,St. Petersburg,Russia,197101"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Sergey","family":"Rybin","sequence":"additional","affiliation":[{"name":"ITMO University,St. Petersburg,Russia,197101"}],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"263","reference":[{"key":"ref32","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/D18-2012"},{"key":"ref31","doi-asserted-by":"crossref","DOI":"10.21437\/Blizzard.2019-15","article-title":"The stc text-to-speech system for blizzard challenge 2019","author":"korostik","year":"2019","journal-title":"Proceedings of Blizzard Challenge 2019"},{"key":"ref30","doi-asserted-by":"publisher","DOI":"10.21437\/SSW.2019-2"},{"key":"ref10","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2019.8683480"},{"key":"ref11","first-page":"3586","article-title":"Audio augmentation for speech recognition","author":"ko","year":"2015","journal-title":"InterSpeech"},{"key":"ref12","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2019-2680"},{"key":"ref13","first-page":"7069","article-title":"Generating Synthetic Audio Data for Attention-Based Speech Recognition Systems","author":"rossenbach","year":"2020","journal-title":"IEEE International Conference on Acoustics Speech and Signal Processing (ICASSP)"},{"key":"ref14","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2015.7178964"},{"key":"ref15","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.1984.1172423"},{"key":"ref16","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2019.8682804"},{"key":"ref17","first-page":"5167","article-title":"Style tokens: Unsupervised style modeling, control and transfer in end-to-end speech synthesis","volume":"80","author":"wang","year":"2018","journal-title":"International Conference on Machine Learning (ICML)"},{"key":"ref18","article-title":"Auto-encoding variational bayes","author":"kingma","year":"2014","journal-title":"International Conference on Learning Representations (ICLR)"},{"key":"ref19","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP40776.2020.9053436"},{"key":"ref28","article-title":"Maximizing mutual information for tacotron","author":"liu","year":"2019"},{"key":"ref4","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2019-3254"},{"key":"ref27","article-title":"Hierarchical generative modeling for controllable speech synthesis","author":"hsu","year":"2019","journal-title":"International Conference on Learning Representations (ICLR)"},{"key":"ref3","article-title":"The stc system for the chime-6 challenge","author":"medennikov","year":"2020","journal-title":"CHiME 2020 Workshop on Speech Processing in Everyday Environments"},{"key":"ref6","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2016-1382"},{"key":"ref29","article-title":"Effective use of variational embedding capacity in expressive end-to-end speech synthesis","author":"battenberg","year":"2019"},{"key":"ref5","article-title":"End-to-end asr: from supervised to semi-supervised learning with modern architectures","author":"synnaeve","year":"2019"},{"key":"ref8","article-title":"Training neural speech recognition systems with synthetic speech augmentation","author":"li","year":"2018"},{"key":"ref7","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2018.8461368"},{"key":"ref2","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2020-1074"},{"key":"ref9","doi-asserted-by":"publisher","DOI":"10.1109\/ASRU46091.2019.9003990"},{"key":"ref1","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2019-1780"},{"key":"ref20","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2018-1456"},{"key":"ref22","first-page":"5998","article-title":"Attention is all you need","volume":"30","author":"vaswani","year":"2017","journal-title":"Advances in neural information processing systems"},{"key":"ref21","doi-asserted-by":"publisher","DOI":"10.1109\/ASRU46091.2019.9003750"},{"key":"ref24","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2017-1452"},{"key":"ref23","doi-asserted-by":"publisher","DOI":"10.1145\/1143844.1143891"},{"key":"ref26","first-page":"577","article-title":"Attention-based models for speech recognition","author":"chorowski","year":"2015","journal-title":"Advances in neural information processing systems"},{"key":"ref25","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP40776.2020.9054106"}],"event":{"name":"2020 13th International Congress on Image and Signal Processing, BioMedical Engineering and Informatics (CISP-BMEI)","location":"Chengdu, China","start":{"date-parts":[[2020,10,17]]},"end":{"date-parts":[[2020,10,19]]}},"container-title":["2020 13th International Congress on Image and Signal Processing, BioMedical Engineering and Informatics (CISP-BMEI)"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx7\/9263486\/9263487\/09263564.pdf?arnumber=9263564","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2024,8,18]],"date-time":"2024-08-18T02:21:29Z","timestamp":1723947689000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/9263564\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2020,10,17]]},"references-count":32,"URL":"https:\/\/doi.org\/10.1109\/cisp-bmei51763.2020.9263564","relation":{},"subject":[],"published":{"date-parts":[[2020,10,17]]}}}