{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,4,4]],"date-time":"2026-04-04T05:34:15Z","timestamp":1775280855876,"version":"3.50.1"},"reference-count":31,"publisher":"IEEE","content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":[],"published-print":{"date-parts":[[2021,1,19]]},"DOI":"10.1109\/slt48900.2021.9383608","type":"proceedings-article","created":{"date-parts":[[2021,3,25]],"date-time":"2021-03-25T16:46:54Z","timestamp":1616690814000},"page":"1117-1123","source":"Crossref","is-referenced-by-count":13,"title":["The SLT 2021 Children Speech Recognition Challenge: Open Datasets, Rules and Baselines"],"prefix":"10.1109","author":[{"given":"Fan","family":"Yu","sequence":"first","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Zhuoyuan","family":"Yao","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Xiong","family":"Wang","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Keyu","family":"An","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Lei","family":"Xie","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Zhijian","family":"Ou","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Bo","family":"Liu","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Xiulin","family":"Li","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Guanqiong","family":"Miao","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"263","reference":[{"key":"ref31","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2018-1456"},{"key":"ref30","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2019.8682256"},{"key":"ref10","doi-asserted-by":"publisher","DOI":"10.1109\/IJCNN.2015.7280336"},{"key":"ref11","first-page":"135","article-title":"Vocal tract length normalisation approaches to DNN-based children’s and adults’ speech recognition","author":"serizel","year":"2014","journal-title":"IEEE Spoken Language Technology Workshop"},{"key":"ref12","author":"liao","year":"2015","journal-title":"Large vocabulary automatic speech recognition for children"},{"key":"ref13","first-page":"1","article-title":"Mismatched training data enhancement for automatic recognition of children’s speech using DNN-HMM","author":"qian","year":"2016","journal-title":"International Symposium on Chinese Spoken Language Processing"},{"key":"ref14","first-page":"1598","article-title":"Improving children’s speech recognition through out-of-domain data augmentation","author":"fainberg","year":"2016","journal-title":"INTER-SPEECH"},{"key":"ref15","doi-asserted-by":"publisher","DOI":"10.21437\/WOCCI.2016-7"},{"key":"ref16","first-page":"36","article-title":"Transfer learning for children’s speech recognition","author":"tong","year":"2017","journal-title":"International Conference on Asian Language Processing"},{"key":"ref17","first-page":"6229","article-title":"Non-native children speech recognition through transfer learning","author":"matassoni","year":"2018","journal-title":"IEEE International Conference on Acoustics Speech and Signal Processing"},{"key":"ref18","first-page":"101077","article-title":"Transfer learning from adult to children for speech recognition: Evaluation, analysis and recommendations","author":"shivakumar","year":"2020"},{"key":"ref19","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2016-595"},{"key":"ref28","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2019-1868"},{"key":"ref4","doi-asserted-by":"publisher","DOI":"10.1121\/1.426686"},{"key":"ref27","doi-asserted-by":"publisher","DOI":"10.1109\/ASRU46091.2019.9003750"},{"key":"ref3","doi-asserted-by":"publisher","DOI":"10.1121\/1.419259"},{"key":"ref6","first-page":"433","article-title":"Improvements in children’s speech recognition performance","author":"das","year":"1998","journal-title":"IEEE International Conference on Acoustics Speech and Signal Processing"},{"key":"ref29","first-page":"1408","article-title":"Improving transformer-based end-to-end speech recognition with connectionist temporal classification and language model integration","author":"nakatani","year":"2019","journal-title":"TERSPEECH"},{"key":"ref5","doi-asserted-by":"crossref","DOI":"10.21437\/Eurospeech.1997-623","article-title":"Automatic speech recognition for children","author":"potamianos","year":"1997","journal-title":"Fifth European Conference on Speech Communication and Technology"},{"key":"ref8","first-page":"21","article-title":"Child automatic speech recognition for US english: child interaction with living-room-electronic-devices","author":"gray","year":"2014","journal-title":"Workshop on Child Computer Interaction"},{"key":"ref7","first-page":"2337","article-title":"An analysis of the causes of increased error rates in childrens speech recognition","author":"li","year":"2002","journal-title":"International Conference on Spoken Language Processing"},{"key":"ref2","article-title":"Challenges for computer recognition of children’s speech","author":"russell","year":"2007","journal-title":"Work-shop on SLT in Education"},{"key":"ref9","first-page":"1635","article-title":"Large vocabulary children’s speech recognition with DNN-HMM and SGMM acoustic modeling","author":"giuliani","year":"2015","journal-title":"InterSpeech"},{"key":"ref1","doi-asserted-by":"crossref","first-page":"436","DOI":"10.1038\/nature14539","article-title":"Deep learning","volume":"521","author":"lecun","year":"2015","journal-title":"Nature"},{"key":"ref20","first-page":"5998","article-title":"Attention is all you need","author":"vaswani","year":"2017","journal-title":"Advances in neural information processing systems"},{"key":"ref22","article-title":"The KALDI speech recognition toolkit","author":"povey","year":"2011","journal-title":"IEEE Workshop on Automatic Speech Recognition and Unde rstanding"},{"key":"ref21","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2020-2732"},{"key":"ref24","first-page":"5884","article-title":"Speech-transformer: A no-recurrence sequence-to-sequence model for speech recognition","author":"dong","year":"2018","journal-title":"IEEE International Conference on Acoustics Speech and Signal Processing"},{"key":"ref23","doi-asserted-by":"publisher","DOI":"10.1145\/1143844.1143891"},{"key":"ref26","doi-asserted-by":"publisher","DOI":"10.1109\/ASRU46091.2019.9004025"},{"key":"ref25","first-page":"7095","article-title":"The speechtrans-former for large-scale mandarin chinese speech recognition","author":"li","year":"2019","journal-title":"IEEE International Conference on Acoustics Speech and Signal Processing"}],"event":{"name":"2021 IEEE Spoken Language Technology Workshop (SLT)","location":"Shenzhen, China","start":{"date-parts":[[2021,1,19]]},"end":{"date-parts":[[2021,1,22]]}},"container-title":["2021 IEEE Spoken Language Technology Workshop (SLT)"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx7\/9383468\/9383452\/09383608.pdf?arnumber=9383608","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2022,12,22]],"date-time":"2022-12-22T08:16:25Z","timestamp":1671696985000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/9383608\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2021,1,19]]},"references-count":31,"URL":"https:\/\/doi.org\/10.1109\/slt48900.2021.9383608","relation":{},"subject":[],"published":{"date-parts":[[2021,1,19]]}}}