{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,7,11]],"date-time":"2026-07-11T16:27:57Z","timestamp":1783787277811,"version":"3.55.0"},"reference-count":30,"publisher":"IEEE","license":[{"start":{"date-parts":[[2022,11,1]],"date-time":"2022-11-01T00:00:00Z","timestamp":1667260800000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2022,11,1]],"date-time":"2022-11-01T00:00:00Z","timestamp":1667260800000},"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":[[2022,11]]},"DOI":"10.1109\/o-cocosda202257103.2022.9997917","type":"proceedings-article","created":{"date-parts":[[2022,12,28]],"date-time":"2022-12-28T18:48:53Z","timestamp":1672253333000},"page":"1-5","source":"Crossref","is-referenced-by-count":5,"title":["Nict-Tib1: A Public Speech Corpus Of Lhasa Dialect For Benchmarking Tibetan Language Speech Recognition Systems"],"prefix":"10.1109","author":[{"given":"Kak","family":"Soky","sequence":"first","affiliation":[{"name":"Kyoto University,Kyoto,Japan"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Zhuo","family":"Gong","sequence":"additional","affiliation":[{"name":"Kyoto University,Kyoto,Japan"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Sheng","family":"Li","sequence":"additional","affiliation":[{"name":"National Institute of Information and Communications Technology (NICT),Kyoto,Japan"}],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"263","reference":[{"key":"ref1","doi-asserted-by":"publisher","DOI":"10.1109\/5.18626"},{"key":"ref2","doi-asserted-by":"publisher","DOI":"10.1109\/TASL.2011.2134090"},{"key":"ref3","doi-asserted-by":"publisher","DOI":"10.1109\/APSIPA.2016.7820795"},{"key":"ref4","doi-asserted-by":"publisher","DOI":"10.1109\/ISCSLP.2016.7918447"},{"key":"ref5","article-title":"Towards End-to-End speech recognition with recurrent neural networks","volume-title":"Proc. ICML","author":"Graves"},{"key":"ref6","doi-asserted-by":"publisher","DOI":"10.1109\/ASRU.2015.7404790"},{"key":"ref7","article-title":"Attention-based models for speech recognition","volume-title":"Proc. NIPS","author":"Chorowski"},{"key":"ref8","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2016.7472621"},{"key":"ref9","doi-asserted-by":"publisher","DOI":"10.1109\/JSTSP.2017.2763455"},{"key":"ref10","article-title":"Attention is all you need","author":"Vaswani","year":"2017","journal-title":"arXiv preprint arxiv:1706.03762"},{"key":"ref11","doi-asserted-by":"publisher","DOI":"10.1109\/APSIPAASC47483.2019.9023100"},{"key":"ref12","doi-asserted-by":"publisher","DOI":"10.1186\/s13636-021-00233-4"},{"key":"ref13","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2022-10015"},{"key":"ref14","article-title":"The royalflush-nict system description for ap21-olr challenge (silk-road team, full tasks)","author":"Wang","year":"2021","journal-title":"OLR2021 (oriental language recognition challenge)"},{"key":"ref15","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2021-374"},{"key":"ref16","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2019-2104"},{"key":"ref17","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2019-2092"},{"key":"ref18","doi-asserted-by":"publisher","DOI":"10.1109\/APSIPAASC47483.2019.9023137"},{"key":"ref19","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP40776.2020.9054233"},{"key":"ref20","volume-title":"Tibeto-Chinese Lhasa Vernacular Dictionary (Tibetan)","year":"1983"},{"key":"ref21","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2018.8462506"},{"key":"ref22","article-title":"Multilingual end-to-end speech recognition with a single transformer on low-resource languages","author":"Zhou","year":"2018","journal-title":"arXiv preprint arxiv:1806.05059"},{"key":"ref23","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-04221-9_19"},{"key":"ref24","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2018-1107"},{"key":"ref25","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2018\u20131423"},{"key":"ref26","doi-asserted-by":"publisher","DOI":"10.21437\/interspeech.2018-1456"},{"key":"ref27","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2018.8462576"},{"key":"ref28","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2017-1296"},{"key":"ref29","article-title":"wav2vec2.0: A framework for self-supervised learning of speech representations","volume-title":"Proc. NeurlPS","author":"Baevski"},{"key":"ref30","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2019-2647"}],"event":{"name":"2022 25th Conference of the Oriental COCOSDA International Committee for the Co-ordination and Standardisation of Speech Databases and Assessment Techniques (O-COCOSDA)","location":"Hanoi, Vietnam","start":{"date-parts":[[2022,11,24]]},"end":{"date-parts":[[2022,11,26]]}},"container-title":["2022 25th Conference of the Oriental COCOSDA International Committee for the Co-ordination and Standardisation of Speech Databases and Assessment Techniques (O-COCOSDA)"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx7\/9997569\/9997817\/09997917.pdf?arnumber=9997917","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2024,3,2]],"date-time":"2024-03-02T12:23:59Z","timestamp":1709382239000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/9997917\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2022,11]]},"references-count":30,"URL":"https:\/\/doi.org\/10.1109\/o-cocosda202257103.2022.9997917","relation":{},"subject":[],"published":{"date-parts":[[2022,11]]}}}