{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2024,10,30]],"date-time":"2024-10-30T12:52:06Z","timestamp":1730292726838,"version":"3.28.0"},"reference-count":21,"publisher":"IEEE","license":[{"start":{"date-parts":[[2019,3,1]],"date-time":"2019-03-01T00:00:00Z","timestamp":1551398400000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/ieeexplore.ieee.org\/Xplorehelp\/downloads\/license-information\/IEEE.html"},{"start":{"date-parts":[[2019,3,1]],"date-time":"2019-03-01T00:00:00Z","timestamp":1551398400000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2019,3,1]],"date-time":"2019-03-01T00:00:00Z","timestamp":1551398400000},"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":[[2019,3]]},"DOI":"10.1109\/rivf.2019.8713758","type":"proceedings-article","created":{"date-parts":[[2019,5,16]],"date-time":"2019-05-16T17:27:30Z","timestamp":1558027650000},"page":"1-6","source":"Crossref","is-referenced-by-count":4,"title":["An End-to-End Model for Vietnamese Speech Recognition"],"prefix":"10.1109","author":[{"given":"Van","family":"Huy Nguyen","sequence":"first","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"263","reference":[{"key":"ref10","doi-asserted-by":"publisher","DOI":"10.1109\/29.21701"},{"key":"ref11","doi-asserted-by":"publisher","DOI":"10.1109\/ASRU.2015.7404779"},{"journal-title":"Ngu am tieng Viet (Vietnamese Acoustic)","year":"2003","author":"thuat","key":"ref12"},{"key":"ref13","doi-asserted-by":"publisher","DOI":"10.1109\/ICSDA.2015.7357876"},{"key":"ref14","doi-asserted-by":"publisher","DOI":"10.1109\/ASRU.2009.5373424"},{"key":"ref15","doi-asserted-by":"publisher","DOI":"10.1109\/ASRU.2013.6707740"},{"key":"ref16","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2014.6854049"},{"key":"ref17","article-title":"A time delay neural network architecture for efficient modeling of long temporal contexts","author":"peddinti","year":"2015","journal-title":"InterSpeech"},{"journal-title":"VLSP 2018 - Automatic Speech Recognition","year":"2018","key":"ref18"},{"key":"ref19","article-title":"Distance Measures for Speech Recognition-Psychological and Instrumental","author":"mermelstein","year":"1976","journal-title":"Joint Workshop in Pattern Recognition and Artificial Intelligence"},{"key":"ref4","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2018.8462105"},{"key":"ref3","article-title":"Wav2Letter: an End-to-End ConvNet-based Speech Recognition System","volume":"1609","author":"collobert","year":"2016","journal-title":"CoRR"},{"key":"ref6","article-title":"Listen, attend and spell","volume":"abs 1508 1211","author":"chan","year":"2015","journal-title":"CoRR"},{"key":"ref5","article-title":"State-of-the-art speech recognition with sequence-to-sequence models","author":"chiu","year":"2017","journal-title":"CoRR vol abs\/1712 01769"},{"key":"ref8","first-page":"1764","article-title":"Towards End-to-end Speech Recognition with Recurrent Neural Networks","volume":"32","author":"graves","year":"2014","journal-title":"Proceedings of the 31st International Conference on International Conference on Machine Learning"},{"key":"ref7","doi-asserted-by":"publisher","DOI":"10.1145\/1143844.1143891"},{"key":"ref2","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2018-1456"},{"key":"ref1","article-title":"Deep Speech 2: End-to-End Speech Recognition in English and Mandarin","author":"amodei","year":"2015","journal-title":"CoRR vol abs\/1512 02595"},{"key":"ref9","doi-asserted-by":"publisher","DOI":"10.1162\/neco.1997.9.8.1735"},{"key":"ref20","article-title":"The Kaldi Speech Recognition Toolkit","author":"povey","year":"2011","journal-title":"2011 IEEE Workshop on Automatic Speech Recognition & Understanding"},{"key":"ref21","first-page":"901","article-title":"SRILM: An extensible language modeling toolkit","author":"stolcke","year":"2002","journal-title":"IN PROCEEDINGS OF THE 7TH INTERNATIONAL CONFERENCE ON SPOKEN LANGUAGE PROCESSING (ICSLP 2002)"}],"event":{"name":"2019 IEEE-RIVF International Conference on Computing and Communication Technologies (RIVF)","start":{"date-parts":[[2019,3,20]]},"location":"Danang, Vietnam","end":{"date-parts":[[2019,3,22]]}},"container-title":["2019 IEEE-RIVF International Conference on Computing and Communication Technologies (RIVF)"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx7\/8705149\/8713612\/08713758.pdf?arnumber=8713758","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2022,7,19]],"date-time":"2022-07-19T16:19:21Z","timestamp":1658247561000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/8713758\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2019,3]]},"references-count":21,"URL":"https:\/\/doi.org\/10.1109\/rivf.2019.8713758","relation":{},"subject":[],"published":{"date-parts":[[2019,3]]}}}