{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2024,10,22]],"date-time":"2024-10-22T17:26:13Z","timestamp":1729617973541,"version":"3.28.0"},"reference-count":35,"publisher":"IEEE","license":[{"start":{"date-parts":[[2021,1,24]],"date-time":"2021-01-24T00:00:00Z","timestamp":1611446400000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/ieeexplore.ieee.org\/Xplorehelp\/downloads\/license-information\/IEEE.html"},{"start":{"date-parts":[[2021,1,24]],"date-time":"2021-01-24T00:00:00Z","timestamp":1611446400000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2021,1,24]],"date-time":"2021-01-24T00:00:00Z","timestamp":1611446400000},"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":[[2021,1,24]]},"DOI":"10.1109\/iscslp49672.2021.9362055","type":"proceedings-article","created":{"date-parts":[[2021,3,1]],"date-time":"2021-03-01T23:37:05Z","timestamp":1614641825000},"page":"1-5","source":"Crossref","is-referenced-by-count":0,"title":["Improving Attention-based End-to-end ASR by Incorporating an N-gram Neural Network"],"prefix":"10.1109","author":[{"given":"Junyi","family":"Ao","sequence":"first","affiliation":[]},{"given":"Tom","family":"Ko","sequence":"additional","affiliation":[]}],"member":"263","reference":[{"key":"ref33","article-title":"Neural machine translation by jointly learning to align and translate","author":"bahdanau","year":"2014","journal-title":"arXiv preprint arXiv 1409 0473"},{"key":"ref32","article-title":"ADADELTA: An adaptive learning rate method","author":"zeiler","year":"2012","journal-title":"arXiv preprint arXiv 1212 5701"},{"key":"ref31","doi-asserted-by":"publisher","DOI":"10.1109\/ASRU.2013.6707742"},{"key":"ref30","article-title":"Very deep convolutional networks for large-scale image recognition","author":"simonyan","year":"2014","journal-title":"arXiv preprint arXiv 1409 1556"},{"key":"ref35","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2017.7953152"},{"article-title":"Audio augmentation for speech recognition","year":"0","author":"ko","key":"ref34"},{"key":"ref10","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2017.7953075"},{"key":"ref11","doi-asserted-by":"publisher","DOI":"10.1109\/JSTSP.2017.2763455"},{"key":"ref12","first-page":"1137","article-title":"A neural probabilistic language model","volume":"3","author":"bengio","year":"2003","journal-title":"Journal of Machine Learning Research"},{"key":"ref13","doi-asserted-by":"crossref","first-page":"1045","DOI":"10.21437\/Interspeech.2010-343","article-title":"Recurrent neural network based language model","author":"mikolov","year":"2010","journal-title":"Proceedings of Interspeech"},{"key":"ref14","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2011.5947611"},{"key":"ref15","doi-asserted-by":"crossref","DOI":"10.21437\/Interspeech.2011-242","article-title":"Empirical evaluation and combination of advanced language modeling techniques","author":"mikolov","year":"2011","journal-title":"Proceedings of Interspeech"},{"key":"ref16","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2013.6639310"},{"key":"ref17","doi-asserted-by":"publisher","DOI":"10.1109\/ASRU.2015.7404792"},{"key":"ref18","article-title":"The kaldi speech recognition toolkit","author":"povey","year":"2011","journal-title":"Proceedings of IEEE Workshop on Automatic Speech Recognition and Understanding"},{"key":"ref19","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2018.8461974"},{"key":"ref28","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2018-1456"},{"key":"ref4","article-title":"Sequence transduction with recurrent neural net-works","author":"graves","year":"2012","journal-title":"arXiv preprint arXiv 1211 3711"},{"key":"ref27","doi-asserted-by":"publisher","DOI":"10.1162\/neco.1997.9.8.1735"},{"key":"ref3","first-page":"173","article-title":"Deep speech 2 : End-to-end speech recognition in english and mandarin","volume":"48","author":"amodei","year":"2016","journal-title":"Proceedings of the 33rd International Conference on Machine Learning"},{"key":"ref6","first-page":"577","article-title":"Attention-based models for speech recognition","author":"chorowski","year":"2015","journal-title":"Proceedings of the 28th International Conference on Neural Information Pro-cessing Systems"},{"key":"ref29","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/P16-1162"},{"key":"ref5","article-title":"End-to-end continuous speech recognition using attention-based recurrent NN: First results","author":"chorowski","year":"2014","journal-title":"arXiv preprint arXiv 1412 1602"},{"key":"ref8","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2016.7472618"},{"key":"ref7","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2016.7472621"},{"key":"ref2","first-page":"1764","article-title":"Towards end-to-end speech recognition with recurrent neural networks","author":"graves","year":"2014","journal-title":"Proceedings of the 31st International Conference on Machine Learning"},{"key":"ref9","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2018.8462105"},{"key":"ref1","doi-asserted-by":"publisher","DOI":"10.1145\/1143844.1143891"},{"key":"ref20","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2018.8462682"},{"key":"ref22","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2018.8462682"},{"key":"ref21","article-title":"On using mono-lingual corpora in neural machine translation","author":"g\u00fcl\u00e7ehre","year":"2015","journal-title":"arXiv preprint arXiv 1503"},{"key":"ref24","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2019.8683862"},{"key":"ref23","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2018-1392"},{"key":"ref26","article-title":"Efficient estimation of word representations in vector space","author":"mikolov","year":"2013","journal-title":"arXiv preprint arXiv 1301 3781"},{"key":"ref25","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP40776.2020.9054116"}],"event":{"name":"2021 12th International Symposium on Chinese Spoken Language Processing (ISCSLP)","start":{"date-parts":[[2021,1,24]]},"location":"Hong Kong","end":{"date-parts":[[2021,1,27]]}},"container-title":["2021 12th International Symposium on Chinese Spoken Language Processing (ISCSLP)"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx7\/9362048\/9362049\/09362055.pdf?arnumber=9362055","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2022,12,19]],"date-time":"2022-12-19T14:09:43Z","timestamp":1671458983000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/9362055\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2021,1,24]]},"references-count":35,"URL":"https:\/\/doi.org\/10.1109\/iscslp49672.2021.9362055","relation":{},"subject":[],"published":{"date-parts":[[2021,1,24]]}}}