{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,3,22]],"date-time":"2026-03-22T01:42:54Z","timestamp":1774143774643,"version":"3.50.1"},"reference-count":31,"publisher":"IEEE","license":[{"start":{"date-parts":[[2021,8,23]],"date-time":"2021-08-23T00:00:00Z","timestamp":1629676800000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2021,8,23]],"date-time":"2021-08-23T00:00:00Z","timestamp":1629676800000},"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":[[2021,8,23]]},"DOI":"10.23919\/eusipco54536.2021.9616228","type":"proceedings-article","created":{"date-parts":[[2021,12,8]],"date-time":"2021-12-08T16:55:53Z","timestamp":1638982553000},"page":"511-515","source":"Crossref","is-referenced-by-count":15,"title":["Data Augmentation Using CycleGAN for End-to-End Children ASR"],"prefix":"10.23919","author":[{"given":"Dipesh K.","family":"Singh","sequence":"first","affiliation":[]},{"given":"Preet P.","family":"Amin","sequence":"additional","affiliation":[]},{"given":"Hardik B.","family":"Sailor","sequence":"additional","affiliation":[]},{"given":"Hemant A.","family":"Patil","sequence":"additional","affiliation":[]}],"member":"263","reference":[{"key":"ref31","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/N18-1192"},{"key":"ref30","doi-asserted-by":"publisher","DOI":"10.1109\/ASRU46091.2019.9003750"},{"key":"ref10","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.1996.541104"},{"key":"ref11","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2020-2275"},{"key":"ref12","author":"park","year":"0","journal-title":"SpecAugment A simple data augmentation method for automatic speech recognition"},{"key":"ref13","first-page":"3446","article-title":"Prosody usage optimization for children speech recognition with zero resource children speech.","author":"li","year":"2019","journal-title":"InterSpeech"},{"key":"ref14","first-page":"3586","article-title":"Audio augmentation for speech recognition","author":"ko","year":"2015","journal-title":"InterSpeech"},{"key":"ref15","doi-asserted-by":"publisher","DOI":"10.1121\/1.421129"},{"key":"ref16","doi-asserted-by":"publisher","DOI":"10.1109\/ASRU46091.2019.9003933"},{"key":"ref17","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2020-1112"},{"key":"ref18","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2019.8682897"},{"key":"ref19","first-page":"245","article-title":"Overview of the INTERSPEECH TLT2020 Shared Task on ASR for Non-Native Children's Speech","author":"gretter","year":"2020","journal-title":"InterSpeech"},{"key":"ref28","doi-asserted-by":"publisher","DOI":"10.1587\/transinf.2015EDP7457"},{"key":"ref4","doi-asserted-by":"publisher","DOI":"10.1109\/ICACCS48705.2020.9074205"},{"key":"ref27","author":"kaneko","year":"0","journal-title":"Cyclegan-vc3 Examining and improving cyclegan-vcs for mel-spectrogram conversion"},{"key":"ref3","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2018.8462562"},{"key":"ref6","first-page":"1764","article-title":"Towards end-to-end speech recognition with recurrent neural networks","author":"graves","year":"2014","journal-title":"International Conference on Machine Learning (ICML)"},{"key":"ref29","author":"watanabe","year":"0","journal-title":"ESPnet End-to-end speech processing toolkit"},{"key":"ref5","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP40776.2020.9054715"},{"key":"ref8","doi-asserted-by":"publisher","DOI":"10.1109\/TSA.2003.818026"},{"key":"ref7","doi-asserted-by":"publisher","DOI":"10.1109\/SLT.2018.8639619"},{"key":"ref2","doi-asserted-by":"publisher","DOI":"10.1109\/IMCEC.2018.8469649"},{"key":"ref1","doi-asserted-by":"publisher","DOI":"10.1145\/1640377.1640384"},{"key":"ref9","article-title":"Challenges for computer recognition of children's speech","author":"russell","year":"2007","journal-title":"Workshop on Speech and Language Technology in Education ISCA"},{"key":"ref20","author":"gretter","year":"0","journal-title":"TIt-school A corpus of non native children speech"},{"key":"ref22","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2015.7178964"},{"key":"ref21","author":"cole","year":"2019","journal-title":"My Science Tutor and the MyST Corpus"},{"key":"ref24","author":"kaneko","year":"0","journal-title":"Parallel-data-free voice conversion using cycle-consistent adversarial networks"},{"key":"ref23","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2017.244"},{"key":"ref26","author":"goodfellow","year":"0","journal-title":"Nips 2016 tutorial Generative adversarial networks"},{"key":"ref25","author":"isola","year":"2018","journal-title":"Image-to-image translation with conditional adversarial networks"}],"event":{"name":"2021 29th European Signal Processing Conference (EUSIPCO)","location":"Dublin, Ireland","start":{"date-parts":[[2021,8,23]]},"end":{"date-parts":[[2021,8,27]]}},"container-title":["2021 29th European Signal Processing Conference (EUSIPCO)"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx7\/9615915\/9615917\/09616228.pdf?arnumber=9616228","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2022,3,21]],"date-time":"2022-03-21T16:56:38Z","timestamp":1647881798000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/9616228\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2021,8,23]]},"references-count":31,"URL":"https:\/\/doi.org\/10.23919\/eusipco54536.2021.9616228","relation":{},"subject":[],"published":{"date-parts":[[2021,8,23]]}}}