{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2025,2,21]],"date-time":"2025-02-21T01:28:48Z","timestamp":1740101328894,"version":"3.37.3"},"reference-count":24,"publisher":"IEEE","license":[{"start":{"date-parts":[[2022,12,11]],"date-time":"2022-12-11T00:00:00Z","timestamp":1670716800000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2022,12,11]],"date-time":"2022-12-11T00:00:00Z","timestamp":1670716800000},"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":[[2022,12,11]]},"DOI":"10.1109\/iscslp57327.2022.10037938","type":"proceedings-article","created":{"date-parts":[[2023,2,8]],"date-time":"2023-02-08T18:53:24Z","timestamp":1675882404000},"page":"11-15","source":"Crossref","is-referenced-by-count":0,"title":["Multilingual Zero Resource Speech Recognition Base on Self-Supervise Pre-Trained Acoustic Models"],"prefix":"10.1109","author":[{"given":"Haoyu","family":"Wang","sequence":"first","affiliation":[{"name":"Tsinghua University,Beijing National Research Center for Information Science and Technology,Department of Electronic Engineering,Beijing,China,100084"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Wei-Qiang","family":"Zhang","sequence":"additional","affiliation":[{"name":"Tsinghua University,Beijing National Research Center for Information Science and Technology,Department of Electronic Engineering,Beijing,China,100084"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Hongbin","family":"Suo","sequence":"additional","affiliation":[{"name":"OPPO,Data & AI Engineering System,Beijing,China,100026"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Yulong","family":"Wan","sequence":"additional","affiliation":[{"name":"OPPO,Data & AI Engineering System,Beijing,China,100026"}],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"263","reference":[{"key":"ref1","first-page":"12449","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":"ref2","doi-asserted-by":"publisher","DOI":"10.1109\/TASLP.2021.3122291"},{"key":"ref3","first-page":"201","article-title":"Why does unsupervised pre-training help deep learning?","volume-title":"Proceedings of the thirteenth international conference on artificial intelligence and statistics","author":"Erhan"},{"key":"ref4","article-title":"Applying wav2vec2. 0 to speech recognition in various low-resource languages","author":"Yi","year":"2020","journal-title":"arXiv preprint arXiv:2012.12121"},{"key":"ref5","article-title":"Noise robust tts for low resource speakers using pre-trained model and speech enhancement","author":"Dai","year":"2020","journal-title":"arXiv preprint arXiv:2005.12531"},{"key":"ref6","doi-asserted-by":"publisher","DOI":"10.26599\/TST.2020.9010029"},{"key":"ref7","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v34i05.6341"},{"key":"ref8","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP40776.2020.9054362"},{"key":"ref9","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2021-1944"},{"key":"ref10","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2021-1843"},{"key":"ref11","doi-asserted-by":"publisher","DOI":"10.21437\/interspeech.2022-60"},{"key":"ref12","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2019-1775"},{"key":"ref13","doi-asserted-by":"publisher","DOI":"10.1016\/j.specom.2008.01.002"},{"key":"ref14","doi-asserted-by":"publisher","DOI":"10.21437\/interspeech.2021-329"},{"key":"ref15","article-title":"Data2vec: A general framework for self-supervised learning in speech, vision and language","author":"Baevski","year":"2022","journal-title":"arXiv preprint arXiv:2202.03555"},{"key":"ref16","article-title":"Categorical reparameterization with gumbel-softmax","author":"Jang","year":"2016","journal-title":"arXiv preprint arXiv:1611.01144"},{"key":"ref17","article-title":"Common voice: A massively-multilingual speech corpus","author":"Ardila","year":"2019","journal-title":"arXiv preprint arXiv:1912.06670"},{"key":"ref18","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2015.7178964"},{"issue":"CONF","key":"ref19","article-title":"The kaldi speech recognition toolkit","volume-title":"IEEE 2011 workshop on automatic speech recognition and understanding","author":"Povey"},{"key":"ref20","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2018-1456"},{"key":"ref21","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2019-2680"},{"key":"ref22","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/N19-4009"},{"article-title":"Flashlight: Enabling innovation in tools for machine learning","year":"2022","author":"Kahn","key":"ref23"},{"key":"ref24","first-page":"187","article-title":"Kenlm: Faster and smaller language model queries","volume-title":"Proceedings of the sixth workshop on statistical machine translation","author":"Heafield"}],"event":{"name":"2022 13th International Symposium on Chinese Spoken Language Processing (ISCSLP)","start":{"date-parts":[[2022,12,11]]},"location":"Singapore, Singapore","end":{"date-parts":[[2022,12,14]]}},"container-title":["2022 13th International Symposium on Chinese Spoken Language Processing (ISCSLP)"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx7\/10037756\/10037573\/10037938.pdf?arnumber=10037938","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2024,2,13]],"date-time":"2024-02-13T13:58:09Z","timestamp":1707832689000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/10037938\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2022,12,11]]},"references-count":24,"URL":"https:\/\/doi.org\/10.1109\/iscslp57327.2022.10037938","relation":{},"subject":[],"published":{"date-parts":[[2022,12,11]]}}}