{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2024,10,29]],"date-time":"2024-10-29T19:36:10Z","timestamp":1730230570497,"version":"3.28.0"},"reference-count":27,"publisher":"IEEE","license":[{"start":{"date-parts":[[2021,6,6]],"date-time":"2021-06-06T00:00:00Z","timestamp":1622937600000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/ieeexplore.ieee.org\/Xplorehelp\/downloads\/license-information\/IEEE.html"},{"start":{"date-parts":[[2021,6,6]],"date-time":"2021-06-06T00:00:00Z","timestamp":1622937600000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2021,6,6]],"date-time":"2021-06-06T00:00:00Z","timestamp":1622937600000},"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":[[2021,6,6]]},"DOI":"10.1109\/icassp39728.2021.9414724","type":"proceedings-article","created":{"date-parts":[[2021,5,13]],"date-time":"2021-05-13T19:53:45Z","timestamp":1620935625000},"page":"7368-7372","source":"Crossref","is-referenced-by-count":1,"title":["Large Margin Training Improves Language Models for ASR"],"prefix":"10.1109","author":[{"given":"Jilin","family":"Wang","sequence":"first","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Jiaji","family":"Huang","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Kenneth Ward","family":"Church","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"263","reference":[{"doi-asserted-by":"publisher","key":"ref10","DOI":"10.18653\/v1\/W18-5446"},{"year":"2019","author":"l\u00fcscher","article-title":"Rwth asr systems for librispeech: Hybrid vs attention–w\/o data augmentation","key":"ref11"},{"doi-asserted-by":"publisher","key":"ref12","DOI":"10.1109\/ASRU46091.2019.9003750"},{"doi-asserted-by":"publisher","key":"ref13","DOI":"10.21437\/Interspeech.2020-1800"},{"doi-asserted-by":"publisher","key":"ref14","DOI":"10.1109\/ICASSP.1998.674474"},{"doi-asserted-by":"publisher","key":"ref15","DOI":"10.3115\/1218955.1218962"},{"doi-asserted-by":"publisher","key":"ref16","DOI":"10.18653\/v1\/D18-1150"},{"key":"ref17","first-page":"2699","article-title":"Masked language model scoring","author":"salazar","year":"2019","journal-title":"Proceedings annual meeting of the Association for Computational Linguistics"},{"doi-asserted-by":"publisher","key":"ref18","DOI":"10.21437\/Interspeech.2017-513"},{"doi-asserted-by":"publisher","key":"ref19","DOI":"10.18653\/v1\/W19-2304"},{"year":"2018","author":"devlin","article-title":"Bert: Pre-training of deep bidirectional transformers for language understanding","key":"ref4"},{"doi-asserted-by":"publisher","key":"ref27","DOI":"10.1109\/CCOMS.2017.8075276"},{"doi-asserted-by":"publisher","key":"ref3","DOI":"10.1006\/csla.1999.0128"},{"year":"2018","author":"radford","article-title":"Improving language understanding by generative pre-training","key":"ref6"},{"doi-asserted-by":"publisher","key":"ref5","DOI":"10.1609\/aaai.v34i05.6428"},{"doi-asserted-by":"publisher","key":"ref8","DOI":"10.1162\/neco.1997.9.8.1735"},{"doi-asserted-by":"publisher","key":"ref7","DOI":"10.1016\/j.specom.2003.08.002"},{"doi-asserted-by":"publisher","key":"ref2","DOI":"10.1016\/S0167-6393(01)00041-3"},{"key":"ref9","first-page":"5998","article-title":"Attention is all you need","author":"vaswani","year":"2017","journal-title":"Advances in neural information processing systems"},{"doi-asserted-by":"publisher","key":"ref1","DOI":"10.1109\/ICASSP.2015.7179000"},{"key":"ref20","first-page":"9","article-title":"Language models are unsupervised multitask learners","volume":"1","author":"radford","year":"2019","journal-title":"OpenAIRE blog"},{"doi-asserted-by":"publisher","key":"ref22","DOI":"10.1109\/ICCV.2015.11"},{"doi-asserted-by":"publisher","key":"ref21","DOI":"10.1109\/ICASSP.2015.7178964"},{"key":"ref24","article-title":"The kaldi speech recognition toolkit","author":"povey","year":"2011","journal-title":"2011 IEEE Workshop on Automatic Speech Recognition & Understanding"},{"doi-asserted-by":"publisher","key":"ref23","DOI":"10.21437\/Interspeech.2018-1417"},{"key":"ref26","first-page":"842","article-title":"Large margin deep networks for classification","author":"elsayed","year":"2018","journal-title":"Advances in neural information processing systems"},{"key":"ref25","first-page":"1081","article-title":"Effective sentence scoring method using bert for speech recognition","author":"shin","year":"2019","journal-title":"Asian Conference on Machine Learning"}],"event":{"name":"ICASSP 2021 - 2021 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)","start":{"date-parts":[[2021,6,6]]},"location":"Toronto, ON, Canada","end":{"date-parts":[[2021,6,11]]}},"container-title":["ICASSP 2021 - 2021 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx7\/9413349\/9413350\/09414724.pdf?arnumber=9414724","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2022,5,10]],"date-time":"2022-05-10T15:40:51Z","timestamp":1652197251000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/9414724\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2021,6,6]]},"references-count":27,"URL":"https:\/\/doi.org\/10.1109\/icassp39728.2021.9414724","relation":{},"subject":[],"published":{"date-parts":[[2021,6,6]]}}}