{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2025,4,10]],"date-time":"2025-04-10T05:12:59Z","timestamp":1744261979077},"reference-count":23,"publisher":"IEEE","license":[{"start":{"date-parts":[[2019,11,1]],"date-time":"2019-11-01T00:00:00Z","timestamp":1572566400000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/ieeexplore.ieee.org\/Xplorehelp\/downloads\/license-information\/IEEE.html"},{"start":{"date-parts":[[2019,11,1]],"date-time":"2019-11-01T00:00:00Z","timestamp":1572566400000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2019,11,1]],"date-time":"2019-11-01T00:00:00Z","timestamp":1572566400000},"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":[[2019,11]]},"DOI":"10.1109\/apsipaasc47483.2019.9023137","type":"proceedings-article","created":{"date-parts":[[2020,3,6]],"date-time":"2020-03-06T17:03:54Z","timestamp":1583514234000},"source":"Crossref","is-referenced-by-count":5,"title":["Multi-lingual Transformer Training for Khmer Automatic Speech Recognition"],"prefix":"10.1109","author":[{"given":"Kak","family":"Soky","sequence":"first","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Sheng","family":"Li","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Tatsuya","family":"Kawahara","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Sopheap","family":"Seng","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"263","reference":[{"key":"ref10","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2018.8462576"},{"key":"ref11","article-title":"Advances in joint CTC-Attention based End-to-End speech recognition with a deep CNN Encoder and RNN-LM","author":"hori","year":"0","journal-title":"Proc INTERSPEECH"},{"key":"ref12","author":"vaswani","year":"2017","journal-title":"Attention is all you need"},{"key":"ref13","article-title":"Creating corpora for speech-to-speech translation","author":"kikui","year":"0","journal-title":"Proc EUROSPEECH"},{"key":"ref14","article-title":"Which units for acoustic and language modeling for khmer automatic speech recognition","author":"seng","year":"0","journal-title":"Proc of International Workshop on Spoken Languages Technologies for Under-resourced languages (SLTU)"},{"key":"ref15","article-title":"First broadcast news transcription system for khmer language","author":"seng","year":"0","journal-title":"Proceedings of International Conference on Language Resources and Evaluation"},{"key":"ref16","article-title":"Word bigram vs orthographic syllable bigram in khmer word","author":"huor","year":"2007","journal-title":"PAN Localization Team Cambodia"},{"key":"ref17","doi-asserted-by":"publisher","DOI":"10.1109\/APSIPA.2014.7041822"},{"key":"ref18","article-title":"Khmer word segmentation using conditional random fields","author":"chea","year":"0","journal-title":"Proc Khmer Natural Language Processing (KNLP)"},{"key":"ref19","article-title":"Khmer electronic dictionary (grammar part)","author":"chuon","year":"1967","journal-title":"Buddhist Institute Dictionary"},{"key":"ref4","doi-asserted-by":"publisher","DOI":"10.1109\/ASRU.2015.7404790"},{"key":"ref3","article-title":"Towards End-to-End speech recognition with recurrent neural networks","author":"graves","year":"0","journal-title":"Proc ICML"},{"key":"ref6","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2016.7472621"},{"key":"ref5","article-title":"Attention-based models for speech recognition","author":"chorowski","year":"0","journal-title":"Proc NIPS"},{"key":"ref8","doi-asserted-by":"publisher","DOI":"10.1109\/JSTSP.2017.2763455"},{"key":"ref7","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2018-1423"},{"key":"ref2","doi-asserted-by":"publisher","DOI":"10.1109\/TASL.2011.2134090"},{"key":"ref1","doi-asserted-by":"publisher","DOI":"10.1109\/5.18626"},{"key":"ref9","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2018-1456"},{"key":"ref20","article-title":"Srilm: an extensible language modeling toolkit","author":"stolcke","year":"0","journal-title":"Proc Int Conf Spoken Language Processing (ICSLP)"},{"key":"ref22","first-page":"15","article-title":"Development of the SprinTra WFST speech decoder","author":"dixon","year":"2012","journal-title":"NICT Research Journal"},{"key":"ref21","article-title":"The Kaldi speech recognition toolkit","author":"povey","year":"0","journal-title":"Proceedings of IEEE ASRU"},{"key":"ref23","doi-asserted-by":"publisher","DOI":"10.1109\/APSIPA.2015.7415529"}],"event":{"name":"2019 Asia-Pacific Signal and Information Processing Association Annual Summit and Conference (APSIPA ASC)","location":"Lanzhou, China","start":{"date-parts":[[2019,11,18]]},"end":{"date-parts":[[2019,11,21]]}},"container-title":["2019 Asia-Pacific Signal and Information Processing Association Annual Summit and Conference (APSIPA ASC)"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx7\/8989870\/9023008\/09023137.pdf?arnumber=9023137","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2022,7,17]],"date-time":"2022-07-17T21:48:19Z","timestamp":1658094499000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/9023137\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2019,11]]},"references-count":23,"URL":"https:\/\/doi.org\/10.1109\/apsipaasc47483.2019.9023137","relation":{},"subject":[],"published":{"date-parts":[[2019,11]]}}}