{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,1,10]],"date-time":"2026-01-10T23:13:31Z","timestamp":1768086811148,"version":"3.49.0"},"reference-count":49,"publisher":"IEEE","license":[{"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"}],"funder":[{"DOI":"10.13039\/501100012166","name":"National Key Research and Development Program of China","doi-asserted-by":"publisher","award":["2017yfb1002102"],"award-info":[{"award-number":["2017yfb1002102"]}],"id":[{"id":"10.13039\/501100012166","id-type":"DOI","asserted-by":"publisher"}]}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":[],"published-print":{"date-parts":[[2021,7,18]]},"DOI":"10.1109\/ijcnn52387.2021.9533587","type":"proceedings-article","created":{"date-parts":[[2021,9,20]],"date-time":"2021-09-20T21:27:41Z","timestamp":1632173261000},"page":"1-6","source":"Crossref","is-referenced-by-count":16,"title":["Transfer Ability of Monolingual Wav2vec2.0 for Low-resource Speech Recognition"],"prefix":"10.1109","author":[{"given":"Cheng","family":"Yi","sequence":"first","affiliation":[{"name":"Institute of Automation, Chinese Academy of Sciences, University of Chinese Academy of Sciences,Beijing,China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Jianzong","family":"Wang","sequence":"additional","affiliation":[{"name":"Ping An Technology Co., Ltd.,Shenzhen,China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Ning","family":"Cheng","sequence":"additional","affiliation":[{"name":"Ping An Technology Co., Ltd.,Shenzhen,China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Shiyu","family":"Zhou","sequence":"additional","affiliation":[{"name":"Institute of Automation, Chinese Academy of Sciences,Beijing,China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Bo","family":"Xu","sequence":"additional","affiliation":[{"name":"Institute of Automation, Chinese Academy of Sciences, University of Chinese Academy of Sciences,Beijing,China"}],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"263","reference":[{"key":"ref39","article-title":"Bert: Pre-training of deep bidirectional transformers for language understanding","author":"devlin","year":"2019","journal-title":"NAACL-HLT"},{"key":"ref38","article-title":"Attention is all you need","author":"vaswani","year":"2017","journal-title":"ArXiv Preprint"},{"key":"ref33","article-title":"Improving transformer-based speech recognition using unsupervised pre-training","author":"jiang","year":"2019","journal-title":"ArXiv Preprint"},{"key":"ref32","doi-asserted-by":"publisher","DOI":"10.21437\/Odyssey.2020-2"},{"key":"ref31","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP40776.2020.9053176"},{"key":"ref30","first-page":"6419","article-title":"Mockingjay: Unsupervised speech representation learning with deep bidirectional transformer encoders","author":"liu","year":"0","journal-title":"ICASSP 2020-2020 IEEE International Conference on Acoustics Speech and Signal Processing (ICASSP)"},{"key":"ref37","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2019.8682586"},{"key":"ref36","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP40776.2020.9054250"},{"key":"ref35","article-title":"Layer normalization","author":"ba","year":"2016","journal-title":"ArXiv Preprint"},{"key":"ref34","article-title":"Gaussian error linear units (gelus)","author":"hendrycks","year":"2016","journal-title":"ArXiv Preprint"},{"key":"ref28","doi-asserted-by":"publisher","DOI":"10.1109\/TASLP.2019.2922832"},{"key":"ref27","first-page":"1304","article-title":"A survey of domain adaptation for neural machine translation","author":"chu","year":"0","journal-title":"Proceedings of the 27th International Conference on Computational Linguistics"},{"key":"ref29","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2019-1473"},{"key":"ref2","doi-asserted-by":"crossref","first-page":"2041","DOI":"10.1109\/TASLP.2019.2938863","article-title":"Unsu-pervised speech representation learning using wavenet autoencoders","volume":"27","author":"chorowski","year":"0","journal-title":"IEEE\/ACM Transactions on Audio Speech and Language Processing"},{"key":"ref1","article-title":"Wav2vec 2.0: A framework for self-supervised learning of speech representations","volume":"33","author":"baevski","year":"2020","journal-title":"Advances in neural information processing systems"},{"key":"ref20","article-title":"Sequence transduction with recurrent neural networks","author":"graves","year":"2012","journal-title":"ArXiv Preprint"},{"key":"ref22","article-title":"Cross-lingual language model pretraining","author":"lample","year":"2019","journal-title":"ArXiv Preprint"},{"key":"ref21","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2019.8683535"},{"key":"ref24","article-title":"From english to foreign languages: Transferring pre-trained language models","author":"tran","year":"2020","journal-title":"ArXiv Preprint"},{"key":"ref23","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2019-2730"},{"key":"ref26","article-title":"An introduction to domain adaptation and transfer learning","author":"kouw","year":"2018","journal-title":"ArXiv Preprint"},{"key":"ref25","article-title":"Un-supervised cross-lingual representation learning for speech recognition","author":"conneau","year":"2020","journal-title":"ArXiv Preprint"},{"key":"ref10","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2000.859138"},{"key":"ref11","doi-asserted-by":"publisher","DOI":"10.1109\/TASL.2009.2021723"},{"key":"ref40","article-title":"Cold fusion: Training seq2seq models together with language models","author":"sriram","year":"2017","journal-title":"ArXiv Preprint"},{"key":"ref12","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2019-2858"},{"key":"ref13","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2018.8462180"},{"key":"ref14","doi-asserted-by":"publisher","DOI":"10.1109\/SLT.2018.8639655"},{"key":"ref15","first-page":"677","article-title":"Transfer learning via dimensionality reduction","volume":"8","author":"pan","year":"2008","journal-title":"AAAI"},{"key":"ref16","article-title":"Multilingual end-to-end speech recognition with a single transformer on low-resource languages","author":"zhou","year":"2018","journal-title":"ArXiv Preprint"},{"key":"ref17","article-title":"Representation learning with contrastive predictive coding","author":"oord","year":"2018","journal-title":"ArXiv Preprint"},{"key":"ref18","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2019-1873"},{"key":"ref19","article-title":"Vq-wav2vec: Self-supervised learning of discrete speech representations","author":"baevski","year":"0","journal-title":"International Conference on Learning Representations (ICLR)"},{"key":"ref4","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2018.8462105"},{"key":"ref3","article-title":"Achieving human parity in conversational speech recognition","author":"xiong","year":"2016","journal-title":"ArXiv Preprint"},{"key":"ref6","author":"campbell","year":"2008","journal-title":"Ethnologue Languages of the World"},{"key":"ref5","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2020-2846"},{"key":"ref8","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2013.6639081"},{"key":"ref7","doi-asserted-by":"publisher","DOI":"10.23919\/APSIPA.2018.8659556"},{"key":"ref49","article-title":"Attention is all you need","author":"waswani","year":"2017","journal-title":"NIPS"},{"key":"ref9","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP40776.2020.9054548"},{"key":"ref46","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2019-1212"},{"key":"ref45","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/P16-1162"},{"key":"ref48","article-title":"Neural machine translation by jointly learning to align and translate","author":"bahdanau","year":"0","journal-title":"International Conference on Learning Representations (ICLR)"},{"key":"ref47","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2017-1705"},{"key":"ref42","doi-asserted-by":"publisher","DOI":"10.1007\/11939993_73"},{"key":"ref41","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2017-111"},{"key":"ref44","first-page":"7669","article-title":"Libri-light: A benchmark for asr with limited or no supervision","author":"kahn","year":"0","journal-title":"ICASSP 2020-2020 IEEE International Conference on Acoustics Speech and Signal Processing (ICASSP)"},{"key":"ref43","first-page":"5206","article-title":"Librispeech: An asr corpus based on public domain audio books","author":"panayotov","year":"2015","journal-title":"ICASSP"}],"event":{"name":"2021 International Joint Conference on Neural Networks (IJCNN)","location":"Shenzhen, China","start":{"date-parts":[[2021,7,18]]},"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\/09533587.pdf?arnumber=9533587","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2022,8,2]],"date-time":"2022-08-02T23:33:26Z","timestamp":1659483206000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/9533587\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2021,7,18]]},"references-count":49,"URL":"https:\/\/doi.org\/10.1109\/ijcnn52387.2021.9533587","relation":{},"subject":[],"published":{"date-parts":[[2021,7,18]]}}}