{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,6,10]],"date-time":"2026-06-10T10:28:31Z","timestamp":1781087311818,"version":"3.54.1"},"reference-count":28,"publisher":"IEEE","license":[{"start":{"date-parts":[[2023,11,14]],"date-time":"2023-11-14T00:00:00Z","timestamp":1699920000000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2023,11,14]],"date-time":"2023-11-14T00:00:00Z","timestamp":1699920000000},"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":[[2023,11,14]]},"DOI":"10.1109\/icspcc59353.2023.10400369","type":"proceedings-article","created":{"date-parts":[[2024,1,29]],"date-time":"2024-01-29T18:34:19Z","timestamp":1706553259000},"page":"1-5","source":"Crossref","is-referenced-by-count":1,"title":["Improving End-to-End Automatic Speech Recognition with Multi-Layer-Enriched Supervised Learning"],"prefix":"10.1109","author":[{"given":"Jingyu","family":"Zhao","sequence":"first","affiliation":[{"name":"Beijing University of Technology,Facult of Information Technology,Department of Information and Communication Engineering,Beijing,China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Ruwei","family":"Li","sequence":"additional","affiliation":[{"name":"Beijing University of Technology,Facult of Information Technology,Department of Information and Communication Engineering,Beijing,China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Weidong","family":"An","sequence":"additional","affiliation":[{"name":"Beijing University of Technology,Facult of Information Technology,Department of Information and Communication Engineering,Beijing,China"}],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"263","reference":[{"key":"ref1","first-page":"1764","article-title":"Towards end-to-end speech recognition with recurrent neural networks","volume-title":"International conference on machine learning","author":"Graves","year":"2014"},{"key":"ref2","article-title":"End-to-end continuous speech recognition using attention -based recurrent NN: First results","author":"Chorowski","year":"2014","journal-title":"arXiv preprint"},{"key":"ref3","doi-asserted-by":"publisher","DOI":"10.1109\/ASRU.2015.7404790"},{"key":"ref4","doi-asserted-by":"publisher","DOI":"10.3390\/sym11081018"},{"key":"ref5","doi-asserted-by":"publisher","DOI":"10.1561\/116.00000050"},{"key":"ref6","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2017.7953075"},{"key":"ref7","article-title":"Unified streaming and non-streaming two-pass end-to-end model for speech recognition","volume":"abs\/2012.05481","author":"Zhang","year":"2020","journal-title":"ArXiv"},{"key":"ref8","doi-asserted-by":"publisher","DOI":"10.1145\/1143844.1143891"},{"key":"ref9","first-page":"173","article-title":"Deep speech 2: End-to-end speech recognition in English and mandarin","volume-title":"International conference on machine learning","author":"Amodei","year":"2016"},{"key":"ref10","doi-asserted-by":"publisher","DOI":"10.1109\/icassp.2016.7472621"},{"key":"ref11","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2016.7472618"},{"key":"ref12","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2016.7472621"},{"key":"ref13","article-title":"Wav2letter: an end-to-end convnet-based speech recognition system","author":"Collobert","year":"2016","journal-title":"arXiv pre print"},{"key":"ref14","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2017-233"},{"key":"ref15","doi-asserted-by":"publisher","DOI":"10.1109\/TASLP.2021.3122291"},{"key":"ref16","article-title":"Unsupervised speech recognition","author":"Baevski","year":"2021","journal-title":"arXiv preprint"},{"key":"ref17","doi-asserted-by":"publisher","DOI":"10.21437\/interspeech.2021-1775"},{"key":"ref18","doi-asserted-by":"publisher","DOI":"10.1109\/ICSDA.2017.8384449"},{"key":"ref19","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2016.90"},{"key":"ref20","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2019-2680"},{"key":"ref21","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP40776.2020.9053205"},{"key":"ref22","article-title":"Accumulated gradient normalization","author":"Hermans","year":"2017","journal-title":"vol. abs\/1710.02368"},{"key":"ref23","first-page":"1929","article-title":"Dropout: a simple way to prevent neural networks from overfitting","volume":"15","author":"Srivastava","year":"2014","journal-title":"J. Mach. Learn. Res."},{"key":"ref24","doi-asserted-by":"publisher","DOI":"10.1109\/ASRU46091.2019.9003750"},{"key":"ref25","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2020-2732"},{"key":"ref26","doi-asserted-by":"publisher","DOI":"10.21437\/interspeech.2018-1456"},{"key":"ref27","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2021-1983"},{"key":"ref28","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2022-483"}],"event":{"name":"2023 IEEE International Conference on Signal Processing, Communications and Computing (ICSPCC)","location":"ZHENGZHOU, China","start":{"date-parts":[[2023,11,14]]},"end":{"date-parts":[[2023,11,17]]}},"container-title":["2023 IEEE International Conference on Signal Processing, Communications and Computing (ICSPCC)"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx7\/10400066\/10400207\/10400369.pdf?arnumber=10400369","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2024,3,3]],"date-time":"2024-03-03T07:34:57Z","timestamp":1709451297000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/10400369\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2023,11,14]]},"references-count":28,"URL":"https:\/\/doi.org\/10.1109\/icspcc59353.2023.10400369","relation":{},"subject":[],"published":{"date-parts":[[2023,11,14]]}}}