{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,1,1]],"date-time":"2026-01-01T10:11:40Z","timestamp":1767262300265,"version":"3.28.0"},"reference-count":35,"publisher":"IEEE","license":[{"start":{"date-parts":[[2023,1,9]],"date-time":"2023-01-09T00:00:00Z","timestamp":1673222400000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2023,1,9]],"date-time":"2023-01-09T00:00:00Z","timestamp":1673222400000},"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":[[2023,1,9]]},"DOI":"10.1109\/slt54892.2023.10022448","type":"proceedings-article","created":{"date-parts":[[2023,1,27]],"date-time":"2023-01-27T13:54:03Z","timestamp":1674827643000},"page":"822-829","source":"Crossref","is-referenced-by-count":2,"title":["Improving Semi-Supervised End-To-End Automatic Speech Recognition Using Cyclegan and Inter-Domain Losses"],"prefix":"10.1109","author":[{"given":"Chia-Yu","family":"Li","sequence":"first","affiliation":[{"name":"Institute for Natural Language Processing (IMS), University of Stuttgart,Germany"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Ngoc Thang","family":"Vu","sequence":"additional","affiliation":[{"name":"Institute for Natural Language Processing (IMS), University of Stuttgart,Germany"}],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"263","reference":[{"key":"ref13","doi-asserted-by":"publisher","DOI":"10.1109\/JSTSP.2017.2763455"},{"key":"ref35","first-page":"2579","article-title":"Visualizing data using t-SNE","author":"van der maaten","year":"2018","journal-title":"Journal of Machine Learning Research"},{"key":"ref12","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2017.7953075"},{"key":"ref34","article-title":"Very deep convolutional networks for large-scale image recognition","author":"simonyan","year":"2015","journal-title":"Proceedings of International Conference on Learning Representations"},{"key":"ref15","article-title":"A Comparison of Sequence-to-Sequence Models for Speech Recognition","author":"prabhavalkar","year":"2017","journal-title":"Proceedings of Interspeech"},{"key":"ref14","article-title":"Neural machine translation by jointly learning to align and translate","author":"bahdanau","year":"2015","journal-title":"Proceedings of International Conference on Learning Representations"},{"key":"ref31","article-title":"The design for the wall street journal-based CSR corpus","author":"paul","year":"1992","journal-title":"Proceedings of the Workshop on Speech and Natural Language Association for Computational Linguistics"},{"key":"ref30","first-page":"723","article-title":"A kernel two-sample test","author":"gretton","year":"2012","journal-title":"Journal of Machine Learning Research"},{"key":"ref11","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2017-1566"},{"key":"ref33","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2018-1456"},{"key":"ref10","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2017.7953077"},{"journal-title":"Free speech recognition voxforge org","year":"0","key":"ref32"},{"key":"ref2","article-title":"End-to-end continuous speech recognition using attention-based recurrent NN: First results","author":"chorowski","year":"2014","journal-title":"Proceedings of Deep Learning and Representation Learning Workshop"},{"key":"ref1","first-page":"1764","article-title":"Towards end-to-end speech recognition with recurrent neural networks","author":"graves","year":"2014","journal-title":"Proceedings of International Conference on Machine Learning"},{"key":"ref17","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2017.244"},{"key":"ref16","first-page":"173","article-title":"Deep Speech 2: End-to-End Speech Recognition in English and Mandarin","volume":"48","author":"amodei","year":"2016","journal-title":"Machine Learning Research"},{"key":"ref19","doi-asserted-by":"publisher","DOI":"10.1109\/SLT.2018.8639619"},{"key":"ref18","article-title":"Listening while speaking: Speech chain by deep learning","author":"tjandra","year":"2017","journal-title":"Proceedings of ASRU"},{"key":"ref24","first-page":"700","article-title":"Unsupervised Image-to-Image Translation Networks","author":"liu","year":"2017","journal-title":"Proceedings of Deep Learning and Representation Learning Workshop"},{"key":"ref23","article-title":"Semi-supervised sequence-to-sequence asr using un-paired speech and text","author":"baskar","year":"2019","journal-title":"Proceedings of Interspeech"},{"key":"ref26","article-title":"Unsupervised Machine Translation Using Monolingual Corpora Only","author":"lample","year":"2018","journal-title":"Proceedings of International Conference on Learning Representations"},{"key":"ref25","article-title":"Unsupervised Neural Machine Translation","author":"artetxe","year":"2018","journal-title":"Proceedings of International Conference on Learning Representations"},{"key":"ref20","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2018-2456"},{"key":"ref22","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2019.8683307"},{"key":"ref21","article-title":"Semisupervised end-to-end speech recognition","author":"karital","year":"2018","journal-title":"Proceedings of Interspeech"},{"key":"ref28","article-title":"Generative adversarial nets","author":"goodfellow","year":"2014","journal-title":"Proceedings of NIPS"},{"key":"ref27","doi-asserted-by":"crossref","first-page":"504","DOI":"10.1126\/science.1127647","article-title":"Reducing the dimensionality of data with neural networks","volume":"313","author":"hinton","year":"2006","journal-title":"Science"},{"key":"ref29","first-page":"298","article-title":"Multivariate analysis: Other hypothesis","author":"kullback","year":"1959","journal-title":"Information Theory and Statistics"},{"key":"ref8","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2016-334"},{"key":"ref7","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2016.7472621"},{"key":"ref9","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2016.7472641"},{"key":"ref4","doi-asserted-by":"publisher","DOI":"10.1109\/ASRU.2015.7404790"},{"key":"ref3","article-title":"Deep speech: Scaling up end-to-end speech recognition","volume":"abs 1412 5567","author":"hannun","year":"2014","journal-title":"CoRR"},{"key":"ref6","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2016.7472618"},{"key":"ref5","first-page":"577","article-title":"Attention-based models for speech recognition","author":"chorowski","year":"2015","journal-title":"Proceedings of Deep Learning and Representation Learning Workshop"}],"event":{"name":"2022 IEEE Spoken Language Technology Workshop (SLT)","start":{"date-parts":[[2023,1,9]]},"location":"Doha, Qatar","end":{"date-parts":[[2023,1,12]]}},"container-title":["2022 IEEE Spoken Language Technology Workshop (SLT)"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx7\/10022052\/10022330\/10022448.pdf?arnumber=10022448","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2023,2,20]],"date-time":"2023-02-20T17:08:34Z","timestamp":1676912914000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/10022448\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2023,1,9]]},"references-count":35,"URL":"https:\/\/doi.org\/10.1109\/slt54892.2023.10022448","relation":{},"subject":[],"published":{"date-parts":[[2023,1,9]]}}}