{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2024,9,7]],"date-time":"2024-09-07T16:32:48Z","timestamp":1725726768732},"reference-count":24,"publisher":"IEEE","license":[{"start":{"date-parts":[[2022,12,11]],"date-time":"2022-12-11T00:00:00Z","timestamp":1670716800000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2022,12,11]],"date-time":"2022-12-11T00:00:00Z","timestamp":1670716800000},"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":[[2022,12,11]]},"DOI":"10.1109\/iscslp57327.2022.10037977","type":"proceedings-article","created":{"date-parts":[[2023,2,8]],"date-time":"2023-02-08T13:53:24Z","timestamp":1675864404000},"page":"443-447","source":"Crossref","is-referenced-by-count":1,"title":["Improving Speech Recognition with Augmented Synthesized Data and Conditional Model Training"],"prefix":"10.1109","author":[{"given":"Shaofei","family":"Xue","sequence":"first","affiliation":[{"name":"AIspeech Ltd.,Suzhou,China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Jian","family":"Tang","sequence":"additional","affiliation":[{"name":"AIspeech Ltd.,Suzhou,China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Yazhu","family":"Liu","sequence":"additional","affiliation":[{"name":"AIspeech Ltd.,Suzhou,China"}],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"263","reference":[{"key":"ref13","doi-asserted-by":"publisher","DOI":"10.1109\/ICSDA.2017.8384449"},{"article-title":"Automatic differentiation in pytorch","year":"2017","author":"paszke","key":"ref24"},{"key":"ref12","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP43922.2022.9746217"},{"key":"ref23","doi-asserted-by":"publisher","DOI":"10.1109\/DSLW51110.2021.9523402"},{"key":"ref15","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2019.8682804"},{"key":"ref14","article-title":"Adaspeech: Adaptive text to speech for custom voice","author":"chen","year":"2021","journal-title":"arXiv preprint arXiv 2103 05767"},{"key":"ref20","doi-asserted-by":"publisher","DOI":"10.1109\/89.294352"},{"key":"ref11","doi-asserted-by":"publisher","DOI":"10.1109\/ASRU51503.2021.9688218"},{"key":"ref22","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2018-1456"},{"key":"ref10","doi-asserted-by":"publisher","DOI":"10.1109\/SLT.2018.8639589"},{"key":"ref21","first-page":"933","article-title":"Language modeling with gated convolutional networks","author":"dauphin","year":"2017","journal-title":"Int Conference on Machine Learning"},{"key":"ref2","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP39728.2021.9413448"},{"key":"ref1","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP40776.2020.9053193"},{"key":"ref17","doi-asserted-by":"publisher","DOI":"10.1145\/1143844.1143891"},{"key":"ref16","article-title":"Improving opus low bit rate quality with neural speech synthesis","author":"skoglund","year":"2019","journal-title":"arXiv preprint arXiv 1905 05992"},{"key":"ref19","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2021.acl-long.8"},{"key":"ref18","article-title":"Aishell-2: Transforming mandarin asr research into industrial scale","author":"du","year":"2018","journal-title":"arXiv preprint arXiv 1808 10393"},{"key":"ref8","doi-asserted-by":"publisher","DOI":"10.1109\/CISP-BMEI51763.2020.9263564"},{"key":"ref7","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2020-1475"},{"key":"ref9","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP39728.2021.9414778"},{"key":"ref4","doi-asserted-by":"publisher","DOI":"10.1109\/ASRU46091.2019.9003990"},{"key":"ref3","article-title":"Training neural speech recognition systems with synthetic speech augmentation","author":"li","year":"2018","journal-title":"arXiv preprint arXiv 1811 00707"},{"key":"ref6","doi-asserted-by":"publisher","DOI":"10.1109\/ASRU51503.2021.9688255"},{"key":"ref5","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP39728.2021.9413432"}],"event":{"name":"2022 13th International Symposium on Chinese Spoken Language Processing (ISCSLP)","start":{"date-parts":[[2022,12,11]]},"location":"Singapore, Singapore","end":{"date-parts":[[2022,12,14]]}},"container-title":["2022 13th International Symposium on Chinese Spoken Language Processing (ISCSLP)"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx7\/10037756\/10037573\/10037977.pdf?arnumber=10037977","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2023,3,6]],"date-time":"2023-03-06T13:37:15Z","timestamp":1678109835000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/10037977\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2022,12,11]]},"references-count":24,"URL":"https:\/\/doi.org\/10.1109\/iscslp57327.2022.10037977","relation":{},"subject":[],"published":{"date-parts":[[2022,12,11]]}}}