{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2024,9,6]],"date-time":"2024-09-06T21:32:27Z","timestamp":1725658347253},"reference-count":25,"publisher":"IEEE","license":[{"start":{"date-parts":[[2021,7,18]],"date-time":"2021-07-18T00:00:00Z","timestamp":1626566400000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/ieeexplore.ieee.org\/Xplorehelp\/downloads\/license-information\/IEEE.html"},{"start":{"date-parts":[[2021,7,18]],"date-time":"2021-07-18T00:00:00Z","timestamp":1626566400000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2021,7,18]],"date-time":"2021-07-18T00:00:00Z","timestamp":1626566400000},"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":[[2021,7,18]]},"DOI":"10.1109\/ijcnn52387.2021.9534170","type":"proceedings-article","created":{"date-parts":[[2021,9,22]],"date-time":"2021-09-22T20:32:37Z","timestamp":1632342757000},"page":"1-6","source":"Crossref","is-referenced-by-count":1,"title":["Two-Stage Pre-Training for Sequence to Sequence Speech Recognition"],"prefix":"10.1109","author":[{"given":"Zhiyun","family":"Fan","sequence":"first","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Shiyu","family":"Zhou","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Bo","family":"Xu","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"263","reference":[{"key":"ref10","first-page":"7354","article-title":"Unsupervised cross-modal alignment of speech and text embedding spaces","author":"chung","year":"0","journal-title":"Advances in neural information processing systems"},{"key":"ref11","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2018-1746"},{"key":"ref12","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2019.8682172"},{"key":"ref13","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/P19-1356"},{"key":"ref14","article-title":"Improving transformer-based speech recognition using unsupervised pre-training","author":"jiang","year":"2019","journal-title":"ArXiv Preprint"},{"key":"ref15","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP40776.2020.9053541"},{"key":"ref16","article-title":"vq-wav2vec: Self-supervised learning of discrete speech representations","author":"baevski","year":"2019","journal-title":"ArXiv Preprint"},{"key":"ref17","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2019-3233"},{"key":"ref18","article-title":"On using mono-lingual corpora in neural machine translation","author":"gulcehre","year":"2015","journal-title":"ArXiv Preprint"},{"key":"ref19","article-title":"Towards better decoding and language model integration in sequence to sequence models","author":"chorowski","year":"2016","journal-title":"ArXiv Preprint"},{"key":"ref4","article-title":"Neural machine translation by jointly learning to align and translate","author":"bahdanau","year":"2014","journal-title":"ArXiv Preprint"},{"key":"ref3","doi-asserted-by":"publisher","DOI":"10.3115\/v1\/D14-1179"},{"key":"ref6","first-page":"577","article-title":"Attention-based models for speech recognition","author":"chorowski","year":"0","journal-title":"Advances in neural information processing systems"},{"key":"ref5","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2016.7472618"},{"key":"ref8","article-title":"Sequence transduction with recurrent neural networks","author":"graves","year":"2012","journal-title":"ArXiv Preprint"},{"key":"ref7","first-page":"5998","article-title":"Attention is all you need","author":"vaswani","year":"0","journal-title":"Advances in neural information processing systems"},{"key":"ref2","first-page":"1764","article-title":"Towards end-to-end speech recognition with recurrent neural networks","author":"graves","year":"0","journal-title":"International Conference on Machine Learning"},{"key":"ref9","doi-asserted-by":"publisher","DOI":"10.29007\/3b2l"},{"key":"ref1","doi-asserted-by":"publisher","DOI":"10.1145\/1143844.1143891"},{"key":"ref20","article-title":"Bert: Pre-training of deep bidirectional transformers for language understanding","author":"devlin","year":"2018","journal-title":"ArXiv Preprint"},{"key":"ref22","doi-asserted-by":"publisher","DOI":"10.1109\/ICSDA.2017.8384449"},{"key":"ref21","article-title":"Aishell-2: Transforming mandarin asr research into industrial scale","author":"du","year":"2018","journal-title":"ArXiv Preprint"},{"journal-title":"Chinese standard mandarin speech copus (10000 sentences)","year":"0","key":"ref24"},{"key":"ref23","doi-asserted-by":"crossref","first-page":"724","DOI":"10.1007\/11939993_73","article-title":"Hkust\/mts: A very large scale mandarin telephone speech corpus","author":"liu","year":"2006","journal-title":"International Symposium on Chinese Spoken Language Processing"},{"key":"ref25","first-page":"2818","article-title":"Re-thinking the inception architecture for computer vision","author":"szegedy","year":"0","journal-title":"Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition"}],"event":{"name":"2021 International Joint Conference on Neural Networks (IJCNN)","start":{"date-parts":[[2021,7,18]]},"location":"Shenzhen, China","end":{"date-parts":[[2021,7,22]]}},"container-title":["2021 International Joint Conference on Neural Networks (IJCNN)"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx7\/9533266\/9533267\/09534170.pdf?arnumber=9534170","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2022,5,10]],"date-time":"2022-05-10T15:46:17Z","timestamp":1652197577000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/9534170\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2021,7,18]]},"references-count":25,"URL":"https:\/\/doi.org\/10.1109\/ijcnn52387.2021.9534170","relation":{},"subject":[],"published":{"date-parts":[[2021,7,18]]}}}