{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2025,2,21]],"date-time":"2025-02-21T01:07:16Z","timestamp":1740100036648,"version":"3.37.3"},"reference-count":24,"publisher":"IEEE","license":[{"start":{"date-parts":[[2021,7,5]],"date-time":"2021-07-05T00:00:00Z","timestamp":1625443200000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2021,7,5]],"date-time":"2021-07-05T00:00:00Z","timestamp":1625443200000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-037"}],"funder":[{"DOI":"10.13039\/501100012166","name":"National Key Research and Development Program of China","doi-asserted-by":"publisher","id":[{"id":"10.13039\/501100012166","id-type":"DOI","asserted-by":"publisher"}]}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":[],"published-print":{"date-parts":[[2021,7,5]]},"DOI":"10.1109\/icme51207.2021.9428111","type":"proceedings-article","created":{"date-parts":[[2021,6,9]],"date-time":"2021-06-09T21:14:21Z","timestamp":1623273261000},"page":"1-6","source":"Crossref","is-referenced-by-count":0,"title":["Spiker-Converter: A Semi-Supervised Framework for Low-Resource Speech Recognition with Stable Adversarial Training"],"prefix":"10.1109","author":[{"given":"Cheng","family":"Yi","sequence":"first","affiliation":[{"name":"Chinese Academy of Sciences (CASIA),Institute of Automation,Beijing,China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Bo","family":"Xu","sequence":"additional","affiliation":[{"name":"Chinese Academy of Sciences (CASIA),Institute of Automation,Beijing,China"}],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"263","reference":[{"key":"ref10","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2019-2068"},{"article-title":"Towards better decoding and language model integration in sequence to sequence models","year":"2016","author":"chorowski","key":"ref11"},{"article-title":"An analysis of incorporating an external language model into a sequence-to-sequence model","year":"2017","author":"kannan","key":"ref12"},{"article-title":"Cold fusion: Training seq2seq models together with language models","year":"2017","author":"sriram","key":"ref13"},{"article-title":"Effectiveness of self-supervised pre-training for speech recognition","year":"2019","author":"baevski","key":"ref14"},{"key":"ref15","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2019-3246"},{"article-title":"Self-training for end-to-end speech recognition","year":"2019","author":"kahn","key":"ref16"},{"key":"ref17","doi-asserted-by":"publisher","DOI":"10.1109\/SLT.2018.8639541"},{"key":"ref18","doi-asserted-by":"publisher","DOI":"10.1145\/1143844.1143891"},{"key":"ref19","article-title":"The kaldi speech recognition toolkit","author":"povey","year":"2011","journal-title":"2011 IEEE Workshop on Automatic Speech Recognition &amp; Understanding"},{"key":"ref4","first-page":"57","article-title":"Semi-supervised classification by low density separation","author":"chapelle","year":"2005","journal-title":"AISTATS"},{"key":"ref3","doi-asserted-by":"publisher","DOI":"10.1093\/nsr\/nwx106"},{"article-title":"Self-supervised sequence-to-sequence asr using unpaired speech and text","year":"2019","author":"baskar","key":"ref6"},{"key":"ref5","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2018-1746"},{"key":"ref8","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2019.8683307"},{"key":"ref7","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2019.8683602"},{"article-title":"Self-supervised speech recognition via local prior matching","year":"2020","author":"hsu","key":"ref2"},{"key":"ref1","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2018.8462105"},{"article-title":"Unsupervised speech recognition via segmental empirical output distribution matching","year":"2018","author":"yeh","key":"ref9"},{"key":"ref20","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2019-1212"},{"key":"ref22","first-page":"5767","article-title":"Improved training of wasserstein gans","author":"gulrajani","year":"2017","journal-title":"Advances in neural information processing systems"},{"article-title":"Wasserstein gan","year":"2017","author":"arjovsky","key":"ref21"},{"article-title":"Deep speech: Scaling up end-to-end speech recognition","year":"2014","author":"hannun","key":"ref24"},{"key":"ref23","doi-asserted-by":"publisher","DOI":"10.1109\/ICSDA.2017.8384449"}],"event":{"name":"2021 IEEE International Conference on Multimedia and Expo (ICME)","start":{"date-parts":[[2021,7,5]]},"location":"Shenzhen, China","end":{"date-parts":[[2021,7,9]]}},"container-title":["2021 IEEE International Conference on Multimedia and Expo (ICME)"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx7\/9428049\/9428068\/09428111.pdf?arnumber=9428111","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2022,8,3]],"date-time":"2022-08-03T00:23:46Z","timestamp":1659486226000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/9428111\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2021,7,5]]},"references-count":24,"URL":"https:\/\/doi.org\/10.1109\/icme51207.2021.9428111","relation":{},"subject":[],"published":{"date-parts":[[2021,7,5]]}}}