{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,6,9]],"date-time":"2026-06-09T19:11:56Z","timestamp":1781032316544,"version":"3.54.1"},"reference-count":53,"publisher":"IEEE","license":[{"start":{"date-parts":[[2023,6,4]],"date-time":"2023-06-04T00:00:00Z","timestamp":1685836800000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2023,6,4]],"date-time":"2023-06-04T00:00:00Z","timestamp":1685836800000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-037"}],"funder":[{"DOI":"10.13039\/501100001809","name":"National Natural Science Foundation of China","doi-asserted-by":"publisher","id":[{"id":"10.13039\/501100001809","id-type":"DOI","asserted-by":"publisher"}]}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":[],"published-print":{"date-parts":[[2023,6,4]]},"DOI":"10.1109\/icassp49357.2023.10095547","type":"proceedings-article","created":{"date-parts":[[2023,5,5]],"date-time":"2023-05-05T17:28:30Z","timestamp":1683307710000},"page":"1-5","source":"Crossref","is-referenced-by-count":17,"title":["Adversarial Data Augmentation Using VAE-GAN for Disordered Speech Recognition"],"prefix":"10.1109","author":[{"given":"Zengrui","family":"Jin","sequence":"first","affiliation":[{"name":"The Chinese University of Hong Kong,Hong Kong SAR,China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Xurong","family":"Xie","sequence":"additional","affiliation":[{"name":"Chinese Academy of Sciences,Institute of Software,China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Mengzhe","family":"Geng","sequence":"additional","affiliation":[{"name":"The Chinese University of Hong Kong,Hong Kong SAR,China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Tianzi","family":"Wang","sequence":"additional","affiliation":[{"name":"The Chinese University of Hong Kong,Hong Kong SAR,China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Shujie","family":"Hu","sequence":"additional","affiliation":[{"name":"The Chinese University of Hong Kong,Hong Kong SAR,China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Jiajun","family":"Deng","sequence":"additional","affiliation":[{"name":"The Chinese University of Hong Kong,Hong Kong SAR,China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Guinan","family":"Li","sequence":"additional","affiliation":[{"name":"The Chinese University of Hong Kong,Hong Kong SAR,China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Xunying","family":"Liu","sequence":"additional","affiliation":[{"name":"The Chinese University of Hong Kong,Hong Kong SAR,China"}],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"263","reference":[{"key":"ref1","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2012-484"},{"key":"ref2","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2013-324"},{"key":"ref3","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/W15-5112"},{"key":"ref4","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2018-1541"},{"key":"ref5","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2020-2282"},{"key":"ref6","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP43922.2022.9746989"},{"key":"ref7","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2020-1161"},{"key":"ref8","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2021-173"},{"key":"ref9","doi-asserted-by":"publisher","DOI":"10.1036\/1097-8542.643000"},{"key":"ref10","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.1993.319366"},{"key":"ref11","doi-asserted-by":"publisher","DOI":"10.1109\/ASRU.2013.6707748"},{"key":"ref12","article-title":"Vocal Tract Length Perturbation (VTLP) Improves Speech Recognition","author":"Jaitly","year":"2013","journal-title":"ICML WDLASL"},{"key":"ref13","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2015-711"},{"key":"ref14","doi-asserted-by":"publisher","DOI":"10.1109\/taslp.2015.2438544"},{"key":"ref15","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2017.7953152"},{"key":"ref16","doi-asserted-by":"publisher","DOI":"10.1109\/SLT.2018.8639619"},{"key":"ref17","article-title":"Generative Adversarial Nets","author":"Goodfellow","year":"2014","journal-title":"NIPS"},{"key":"ref18","doi-asserted-by":"publisher","DOI":"10.1109\/icassp43922.2022.9747442"},{"key":"ref19","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2021-1351"},{"key":"ref20","doi-asserted-by":"publisher","DOI":"10.1109\/SPCOM50965.2020.9179511"},{"key":"ref21","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP43922.2022.9747550"},{"key":"ref22","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2020-2898"},{"key":"ref23","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP39728.2021.9414438"},{"key":"ref24","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP43922.2022.9747755"},{"key":"ref25","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2021-230"},{"key":"ref26","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2020-2639"},{"key":"ref27","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2022-190"},{"key":"ref28","doi-asserted-by":"publisher","DOI":"10.1109\/TASLP.2021.3091805"},{"key":"ref29","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2021-168"},{"key":"ref30","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP39728.2021.9414869"},{"key":"ref31","article-title":"Auto-Encoding Variational Bayes","author":"Kingma","year":"2014","journal-title":"ICLR"},{"key":"ref32","article-title":"Neural Discrete Representation Learning","author":"Van Den Oord","year":"2017","journal-title":"NIPS"},{"key":"ref33","article-title":"Autoencoding Beyond Pixels Using a Learned Similarity Metric","author":"Larsen","year":"2016","journal-title":"ICML"},{"key":"ref34","article-title":"Wav2vec 2.0: A Framework for Self-Supervised Learning of Speech Representations","author":"Baevski","year":"2020","journal-title":"NIPS"},{"key":"ref35","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2008-480"},{"key":"ref36","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2022-443"},{"key":"ref37","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2019-1398"},{"key":"ref38","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2019-2486"},{"key":"ref39","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2018-1841"},{"key":"ref40","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2022-952"},{"key":"ref41","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2021-2121"},{"key":"ref42","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2020-1647"},{"key":"ref43","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2020-1520"},{"key":"ref44","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2019.8683290"},{"key":"ref45","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2022-696"},{"key":"ref46","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2015-647"},{"key":"ref47","doi-asserted-by":"publisher","DOI":"10.21437\/interspeech.2016-595"},{"key":"ref48","article-title":"The HTK book","volume":"3","author":"Young","year":"2006","journal-title":"Cambridge University Engineering Department"},{"key":"ref49","doi-asserted-by":"publisher","DOI":"10.1109\/TASLP.2016.2560534"},{"key":"ref50","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2019.8683091"},{"key":"ref51","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP40776.2020.9054694"},{"key":"ref52","article-title":"Improved End-to-End Dysarthric Speech Recognition via Meta-Learning Based Model ReInitialization","author":"Wang","year":"2021","journal-title":"ISCSLP"},{"key":"ref53","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2021-60"}],"event":{"name":"ICASSP 2023 - 2023 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)","location":"Rhodes Island, Greece","start":{"date-parts":[[2023,6,4]]},"end":{"date-parts":[[2023,6,10]]}},"container-title":["ICASSP 2023 - 2023 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx7\/10094559\/10094560\/10095547.pdf?arnumber=10095547","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2024,2,29]],"date-time":"2024-02-29T22:41:58Z","timestamp":1709246518000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/10095547\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2023,6,4]]},"references-count":53,"URL":"https:\/\/doi.org\/10.1109\/icassp49357.2023.10095547","relation":{},"subject":[],"published":{"date-parts":[[2023,6,4]]}}}