{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2025,9,28]],"date-time":"2025-09-28T11:15:33Z","timestamp":1759058133972,"version":"3.28.0"},"reference-count":25,"publisher":"IEEE","content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":[],"published-print":{"date-parts":[[2017,11]]},"DOI":"10.1109\/icsda.2017.8384469","type":"proceedings-article","created":{"date-parts":[[2018,6,14]],"date-time":"2018-06-14T23:31:04Z","timestamp":1529019064000},"page":"1-6","source":"Crossref","is-referenced-by-count":9,"title":["M2ASR: Ambitions and first year progress"],"prefix":"10.1109","author":[{"given":"Dong","family":"Wang","sequence":"first","affiliation":[]},{"given":"Thomas Fang","family":"Zheng","sequence":"additional","affiliation":[]},{"given":"Zhiyuan","family":"Tang","sequence":"additional","affiliation":[]},{"given":"Ying","family":"Shi","sequence":"additional","affiliation":[]},{"given":"Lantian","family":"Li","sequence":"additional","affiliation":[]},{"given":"Shiyue","family":"Zhang","sequence":"additional","affiliation":[]},{"given":"Hongzhi","family":"Yu","sequence":"additional","affiliation":[]},{"given":"Guanyu","family":"Li","sequence":"additional","affiliation":[]},{"given":"Shipeng","family":"Xu","sequence":"additional","affiliation":[]},{"given":"Askar","family":"Hamdulla","sequence":"additional","affiliation":[]},{"given":"Mijit","family":"Ablimit","sequence":"additional","affiliation":[]},{"given":"Gulnigar","family":"Mahmut","sequence":"additional","affiliation":[]}],"member":"263","reference":[{"key":"ref10","first-page":"577","article-title":"Attention-based models for speech recognition","author":"chorowski","year":"2015","journal-title":"Advances in neural information processing systems"},{"key":"ref11","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2016.7472618"},{"key":"ref12","first-page":"182","article-title":"Thuyg-20: A free uyghur speech database","volume":"57","author":"rouzi","year":"2017","journal-title":"Journal of Tsinghua University (Science and Technology)"},{"key":"ref13","doi-asserted-by":"publisher","DOI":"10.1109\/ICSDA.2015.7357869"},{"key":"ref14","doi-asserted-by":"crossref","first-page":"31","DOI":"10.1109\/TSA.1996.481450","article-title":"Comparison of four approaches to automatic language identification of telephone speech","volume":"4","author":"marc","year":"1996","journal-title":"IEEE Transactions on Speech and Audio Processing"},{"key":"ref15","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.1993.319323"},{"key":"ref16","first-page":"857","article-title":"Language recognition via i-vectors and dimensionality reduction","author":"najim","year":"2011","journal-title":"Proceedings of the Annual Conference of International Speech Communication Association (INTERSPEECH)"},{"key":"ref17","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2014.6854622"},{"key":"ref18","first-page":"2155","article-title":"Automatic language identification using long short-term memory recurrent neural networks","author":"gonzalez-dominguez","year":"2014","journal-title":"Conference of the International Speech Communication Association (Inter-Speech)"},{"journal-title":"Phonetic temporal neural model for language identification","year":"2017","author":"tang","key":"ref19"},{"key":"ref4","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2013.6639348"},{"key":"ref3","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2013.6639084"},{"journal-title":"Efficient Estimation of Word Representations in Vector Space","year":"2013","author":"mikolov","key":"ref6"},{"key":"ref5","first-page":"2493","article-title":"Natural language processing (almost) from scratch","volume":"12","author":"collobert","year":"2011","journal-title":"The Journal of Machine Learning Research"},{"key":"ref8","doi-asserted-by":"publisher","DOI":"10.1109\/APSIPA.2016.7820893"},{"key":"ref7","doi-asserted-by":"publisher","DOI":"10.1007\/3-540-33486-6_6"},{"key":"ref2","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2013.6639081"},{"journal-title":"Neural machine translation by jointly learning to align and translate","year":"2014","author":"bahdanau","key":"ref9"},{"key":"ref1","doi-asserted-by":"publisher","DOI":"10.1561\/2000000039"},{"key":"ref20","doi-asserted-by":"publisher","DOI":"10.1109\/APSIPA.2017.8282190"},{"key":"ref22","doi-asserted-by":"publisher","DOI":"10.1109\/APSIPA.2017.8282130"},{"key":"ref21","doi-asserted-by":"publisher","DOI":"10.1109\/TASLP.2016.2585863"},{"key":"ref24","doi-asserted-by":"publisher","DOI":"10.1109\/APSIPA.2017.8282131"},{"key":"ref23","doi-asserted-by":"publisher","DOI":"10.1109\/APSIPA.2017.8282132"},{"key":"ref25","doi-asserted-by":"publisher","DOI":"10.1016\/j.specom.2013.09.011"}],"event":{"name":"2017 20th Conference of the Oriental Chapter of the International Coordinating Committee on Speech Databases and Speech I\/O Systems and Assessment (O-COCOSDA)","start":{"date-parts":[[2017,11,1]]},"location":"Seoul","end":{"date-parts":[[2017,11,3]]}},"container-title":["2017 20th Conference of the Oriental Chapter of the International Coordinating Committee on Speech Databases and Speech I\/O Systems and Assessment (O-COCOSDA)"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx7\/8373628\/8384412\/08384469.pdf?arnumber=8384469","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2018,7,3]],"date-time":"2018-07-03T01:18:52Z","timestamp":1530580732000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/8384469\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2017,11]]},"references-count":25,"URL":"https:\/\/doi.org\/10.1109\/icsda.2017.8384469","relation":{},"subject":[],"published":{"date-parts":[[2017,11]]}}}